{"name":"SIscope models API","version":"v0","built_at":"2026-11-04T00:39:47Z","score":{"version":"0.2.0","coverage_gate":0.7,"weights":{"coding":25,"agents":25,"reasoning":20,"math":15,"chat":10,"instructions":5},"docs":"https://siscope.app/methodology"},"sources":[{"id":"arena","name":"Arena (formerly LMArena) leaderboard dataset","home":"https://arena.ai/leaderboard","license":"CC BY 4.0","license_url":"https://creativecommons.org/licenses/by/4.0/","attribution":"Arena (lmarena-ai), leaderboard-dataset on Hugging Face","as_of":"2026-10-28"},{"id":"epoch","name":"Epoch AI Benchmarking Hub","home":"https://epoch.ai","license":"CC BY 4.0","license_url":"https://creativecommons.org/licenses/by/4.0/","attribution":"Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks","as_of":"2026-11-02"},{"id":"openrouter","name":"OpenRouter models API","home":"https://openrouter.ai","license":"OpenRouter API terms (cited, prices only)","license_url":"https://openrouter.ai/terms","attribution":"Source: OpenRouter (openrouter.ai), models API","as_of":"2026-11-04T00:26:02Z"},{"id":"exgentic","name":"Open Agent Leaderboard results (Exgentic)","home":"https://huggingface.co/spaces/open-agent-leaderboard/leaderboard","license":"CDLA-Permissive-2.0","license_url":"https://cdla.dev/permissive-2-0/","attribution":"Open Agent Leaderboard (Exgentic), arXiv:2602.22953","as_of":"2026-05-20"}],"attribution":"Please credit SIscope and the original sources listed here.","count":490,"models":[{"slug":"gemini-4-carbon-high","name":"Gemini 4 Carbon (High)","source_name":"Gemini 4 Carbon (High)","base":"Gemini 4 Carbon","variant":"High","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":99.3,"rank":1,"coverage":1,"categories":{"coding":99,"agents":98.2,"reasoning":100,"math":99.8,"chat":100,"instructions":100}},"arena":{"text":{"rank":1,"date":"2026-10-28","rating":1540,"lo":1530.7,"hi":1549.4,"votes":4403,"pct":100,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":4,"date":"2026-10-28","rating":1768.2,"lo":1753.2,"hi":1783.2,"votes":2230,"pct":98,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":2,"date":"2026-11-02","score":0.1656,"lo":0.1575,"hi":0.1736,"sessions":39245,"cost_per_task_p50":1.734,"pct":98.2,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1569.5,"rank":1,"pct":100,"board_size":414},"math":{"rating":1536.2,"rank":2,"pct":99.8,"board_size":405},"creative_writing":{"rating":1530.9,"rank":2,"pct":99.8,"board_size":417},"instruction_following":{"rating":1539.2,"rank":1,"pct":100,"board_size":419},"hard_prompts":{"rating":1552.5,"rank":1,"pct":100,"board_size":419},"multi_turn":{"rating":1564.7,"rank":1,"pct":100,"board_size":417},"longer_query":{"rating":1553.2,"rank":1,"pct":100,"board_size":397},"non_english":{"rating":1536.9,"rank":1,"pct":100,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemini-4-carbon-high"},{"slug":"gemini-4-argon-high","name":"Gemini 4 Argon (High)","source_name":"Gemini 4 Argon (High)","base":"Gemini 4 Argon","variant":"High","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":95.7,"rank":6,"coverage":1,"categories":{"coding":96.5,"agents":89.3,"reasoning":99.9,"math":95.7,"chat":99.8,"instructions":99.5}},"arena":{"text":{"rank":2,"date":"2026-10-28","rating":1528.6,"lo":1522.3,"hi":1534.8,"votes":11889,"pct":99.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":11,"date":"2026-10-28","rating":1679.2,"lo":1667.8,"hi":1690.6,"votes":3437,"pct":93.4,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":7,"date":"2026-11-02","score":0.1061,"lo":0.0976,"hi":0.1145,"sessions":52038,"cost_per_task_p50":0.999,"pct":89.3,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1538.2,"rank":3,"pct":99.5,"board_size":414},"math":{"rating":1538.5,"rank":1,"pct":100,"board_size":405},"creative_writing":{"rating":1527.4,"rank":3,"pct":99.5,"board_size":417},"instruction_following":{"rating":1532.6,"rank":3,"pct":99.5,"board_size":419},"hard_prompts":{"rating":1541.7,"rank":2,"pct":99.8,"board_size":419},"multi_turn":{"rating":1541.8,"rank":2,"pct":99.8,"board_size":417},"longer_query":{"rating":1542,"rank":2,"pct":99.7,"board_size":397},"non_english":{"rating":1520.7,"rank":2,"pct":99.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.964,"stderr":0.0119,"tested_as":"gemini-4-argon_high","approx":false,"run_date":"2026-10-13","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FQEouTvczNsxgkR4i7i8wBF.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":100,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.76,"stderr":0.0135,"tested_as":"gemini-4-argon_high","approx":false,"run_date":"2026-10-13","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Fiq4Y9tXpiyLP25yotySxJW.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":100,"tested_models":100},{"benchmark":"otis_mock_aime","score":1,"stderr":0,"tested_as":"gemini-4-argon_high","approx":false,"run_date":"2026-10-13","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F43f36RTDoJGxXWQDVvTLJj.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":96.2,"tested_models":313},{"benchmark":"frontiermath","score":0.8596,"stderr":0.0206,"tested_as":"gemini-4-argon_high","approx":false,"run_date":"2026-10-13","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":90.9,"tested_models":122}],"price":{"openrouter_id":"google/gemini-4-argon","input_per_m":2,"output_per_m":10,"blended_per_m":4,"context_length":1048576,"modalities_in":["audio","file","image","text","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gemini-4-argon-high"},{"slug":"claude-opus-5-5-high","name":"Claude Opus 5.5 (High)","source_name":"Claude Opus 5.5 (High)","base":"Claude Opus 5.5","variant":"High","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":99.1,"rank":2,"coverage":0.75,"categories":{"coding":99.8,"reasoning":99.5,"math":98.3,"chat":99.5,"instructions":99.8}},"arena":{"text":{"rank":3,"date":"2026-10-28","rating":1515.8,"lo":1509.2,"hi":1522.4,"votes":11415,"pct":99.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":2,"date":"2026-10-19","rating":1320.8,"lo":1309.1,"hi":1332.5,"votes":3035,"pct":99.4,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1547.2,"rank":2,"pct":99.8,"board_size":414},"math":{"rating":1516.7,"rank":8,"pct":98.3,"board_size":405},"creative_writing":{"rating":1534.4,"rank":1,"pct":100,"board_size":417},"instruction_following":{"rating":1538.9,"rank":2,"pct":99.8,"board_size":419},"hard_prompts":{"rating":1536.1,"rank":3,"pct":99.5,"board_size":419},"multi_turn":{"rating":1500.2,"rank":10,"pct":97.8,"board_size":417},"longer_query":{"rating":1533.2,"rank":3,"pct":99.5,"board_size":397},"non_english":{"rating":1506,"rank":4,"pct":99.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"anthropic/claude-opus-5.5","input_per_m":4,"output_per_m":20,"blended_per_m":8,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-opus-5-5-high"},{"slug":"claude-fable-5-1-max","name":"Claude Fable 5.1 (Max)","source_name":"Claude Fable 5.1 (Max)","base":"Claude Fable 5.1","variant":"Max","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":96.5,"rank":4,"coverage":1,"categories":{"coding":97.4,"agents":92.9,"reasoning":97.1,"math":97.4,"chat":99.3,"instructions":99}},"arena":{"text":{"rank":4,"date":"2026-10-28","rating":1513.8,"lo":1508,"hi":1519.6,"votes":17178,"pct":99.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":6,"date":"2026-10-28","rating":1745.9,"lo":1737.3,"hi":1754.4,"votes":8614,"pct":96.7,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":4,"date":"2026-10-19","rating":1319.5,"lo":1310.2,"hi":1328.8,"votes":5026,"pct":98.2,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":5,"date":"2026-11-02","score":0.1315,"lo":0.1127,"hi":0.1502,"sessions":17467,"cost_per_task_p50":6.955,"pct":92.9,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1530.1,"rank":9,"pct":98.1,"board_size":414},"math":{"rating":1531,"rank":3,"pct":99.3,"board_size":405},"creative_writing":{"rating":1512,"rank":4,"pct":99.3,"board_size":417},"instruction_following":{"rating":1518.7,"rank":5,"pct":99,"board_size":419},"hard_prompts":{"rating":1529,"rank":4,"pct":99.3,"board_size":419},"multi_turn":{"rating":1495.4,"rank":13,"pct":97.1,"board_size":417},"longer_query":{"rating":1525.4,"rank":4,"pct":99.2,"board_size":397},"non_english":{"rating":1509.7,"rank":3,"pct":99.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"simpleqa_verified","score":0.708,"stderr":0.0144,"tested_as":"claude-fable-5-1_max","approx":false,"run_date":"2026-09-01","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FExyL3GN8s34tizrXV3VmS3.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":94.9,"tested_models":100},{"benchmark":"otis_mock_aime","score":1,"stderr":0,"tested_as":"claude-fable-5-1_max","approx":false,"run_date":"2026-09-01","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FmRAASXsUuoJmc2oR5G89zR.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":96.2,"tested_models":313},{"benchmark":"frontiermath","score":0.9018,"stderr":0.0177,"tested_as":"claude-fable-5-1_max","approx":false,"run_date":"2026-09-01","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":96.7,"tested_models":122}],"price":{"openrouter_id":"anthropic/claude-fable-5.1","input_per_m":10,"output_per_m":50,"blended_per_m":20,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-fable-5-1-max"},{"slug":"claude-opus-5-max","name":"Claude Opus 5 (Max)","source_name":"Claude Opus 5 (Max)","base":"Claude Opus 5","variant":"Max","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":92,"rank":12,"coverage":1,"categories":{"coding":96.3,"agents":82.1,"reasoning":92.8,"math":93.7,"chat":99,"instructions":98.8}},"arena":{"text":{"rank":5,"date":"2026-10-28","rating":1507.9,"lo":1503.2,"hi":1512.6,"votes":35531,"pct":99,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":10,"date":"2026-10-28","rating":1690.5,"lo":1684.4,"hi":1696.6,"votes":19641,"pct":94,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":11,"date":"2026-11-02","score":0.076,"lo":0.0636,"hi":0.0884,"sessions":31955,"cost_per_task_p50":5.624,"pct":82.1,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1531.8,"rank":7,"pct":98.5,"board_size":414},"math":{"rating":1530.5,"rank":5,"pct":99,"board_size":405},"creative_writing":{"rating":1494.6,"rank":6,"pct":98.8,"board_size":417},"instruction_following":{"rating":1518,"rank":6,"pct":98.8,"board_size":419},"hard_prompts":{"rating":1526.4,"rank":5,"pct":99,"board_size":419},"multi_turn":{"rating":1498.8,"rank":11,"pct":97.6,"board_size":417},"longer_query":{"rating":1517.2,"rank":6,"pct":98.7,"board_size":397},"non_english":{"rating":1501.6,"rank":5,"pct":99,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9388,"stderr":0.0148,"tested_as":"claude-opus-5_max","approx":false,"run_date":"2026-07-24","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FD3mtasTumfvjR4fjmnHWRy.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":95.5,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.599,"stderr":0.0155,"tested_as":"claude-opus-5_max","approx":false,"run_date":"2026-08-10","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":83.8,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9889,"stderr":0.0111,"tested_as":"claude-opus-5_max","approx":false,"run_date":"2026-07-24","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FKxvHAT9SV2dTDn7jBnTk6f.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":92,"tested_models":313},{"benchmark":"frontiermath","score":0.8561,"stderr":0.0208,"tested_as":"claude-opus-5_max","approx":false,"run_date":"2026-07-24","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Fff7GeS7rdperjxSBZ7MHZY.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":90.1,"tested_models":122}],"price":{"openrouter_id":"anthropic/claude-opus-5","input_per_m":5,"output_per_m":25,"blended_per_m":10,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-opus-5-max"},{"slug":"claude-opus-5-high","name":"Claude Opus 5 (High)","source_name":"Claude Opus 5 (High)","base":"Claude Opus 5","variant":"High","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":96.5,"rank":5,"coverage":0.75,"categories":{"coding":94.1,"reasoning":98.6,"math":99.3,"chat":98.8,"instructions":98.6}},"arena":{"text":{"rank":6,"date":"2026-10-28","rating":1504.1,"lo":1500.5,"hi":1507.6,"votes":73167,"pct":98.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":17,"date":"2026-10-28","rating":1658.2,"lo":1652.9,"hi":1663.5,"votes":26887,"pct":89.4,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":3,"date":"2026-10-19","rating":1319.6,"lo":1313,"hi":1326.2,"votes":17743,"pct":98.8,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1532.8,"rank":6,"pct":98.8,"board_size":414},"math":{"rating":1531,"rank":4,"pct":99.3,"board_size":405},"creative_writing":{"rating":1487.7,"rank":10,"pct":97.8,"board_size":417},"instruction_following":{"rating":1515.3,"rank":7,"pct":98.6,"board_size":419},"hard_prompts":{"rating":1523.3,"rank":7,"pct":98.6,"board_size":419},"multi_turn":{"rating":1494.3,"rank":14,"pct":96.9,"board_size":417},"longer_query":{"rating":1513.8,"rank":8,"pct":98.2,"board_size":397},"non_english":{"rating":1497.6,"rank":6,"pct":98.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"anthropic/claude-opus-5","input_per_m":5,"output_per_m":25,"blended_per_m":10,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-opus-5-high"},{"slug":"claude-opus-4-6-high","name":"Claude Opus 4.6 (High)","source_name":"Claude Opus 4.6 (High)","base":"Claude Opus 4.6","variant":"High","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":91.3,"rank":14,"coverage":0.75,"categories":{"coding":83.9,"reasoning":98.8,"math":98.5,"chat":98.6,"instructions":99.3}},"arena":{"text":{"rank":7,"date":"2026-10-28","rating":1501.7,"lo":1498.5,"hi":1505,"votes":84512,"pct":98.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":47,"date":"2026-10-28","rating":1546.2,"lo":1540.8,"hi":1551.7,"votes":19316,"pct":69.5,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":6,"date":"2026-10-19","rating":1315.7,"lo":1309.3,"hi":1322,"votes":22286,"pct":97,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1531.4,"rank":8,"pct":98.3,"board_size":414},"math":{"rating":1517.5,"rank":7,"pct":98.5,"board_size":405},"creative_writing":{"rating":1504.5,"rank":5,"pct":99,"board_size":417},"instruction_following":{"rating":1520.9,"rank":4,"pct":99.3,"board_size":419},"hard_prompts":{"rating":1524.6,"rank":6,"pct":98.8,"board_size":419},"multi_turn":{"rating":1512.2,"rank":3,"pct":99.5,"board_size":417},"longer_query":{"rating":1517.5,"rank":5,"pct":99,"board_size":397},"non_english":{"rating":1487.5,"rank":9,"pct":98.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"anthropic/claude-opus-4.6","input_per_m":5,"output_per_m":25,"blended_per_m":10,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-opus-4-6-high"},{"slug":"muse-wonder-max","name":"Muse Wonder (Max)","source_name":"Muse Wonder (Max)","base":"Muse Wonder","variant":"Max","org":"meta","open_weights":false,"model_license":"Proprietary","siscope":{"score":88.3,"rank":22,"coverage":1,"categories":{"coding":92.5,"agents":69.6,"reasoning":97.4,"math":90.8,"chat":98.3,"instructions":97.6}},"arena":{"text":{"rank":8,"date":"2026-10-28","rating":1499.2,"lo":1491.9,"hi":1506.5,"votes":7749,"pct":98.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":20,"date":"2026-10-28","rating":1652.1,"lo":1641,"hi":1663.2,"votes":3724,"pct":87.4,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":18,"date":"2026-11-02","score":0.0251,"lo":0.0114,"hi":0.0388,"sessions":13075,"cost_per_task_p50":1.432,"pct":69.6,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1518.4,"rank":11,"pct":97.6,"board_size":414},"math":{"rating":1477.5,"rank":38,"pct":90.8,"board_size":405},"creative_writing":{"rating":1488.3,"rank":9,"pct":98.1,"board_size":417},"instruction_following":{"rating":1493.6,"rank":11,"pct":97.6,"board_size":419},"hard_prompts":{"rating":1506.9,"rank":12,"pct":97.4,"board_size":419},"multi_turn":{"rating":1505.1,"rank":6,"pct":98.8,"board_size":417},"longer_query":{"rating":1495.1,"rank":14,"pct":96.7,"board_size":397},"non_english":{"rating":1490.2,"rank":8,"pct":98.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"meta/muse-wonder","input_per_m":4,"output_per_m":20,"blended_per_m":8,"context_length":1048576,"modalities_in":["text","image","video","file","audio"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/muse-wonder-max"},{"slug":"gemini-3-8-flash-high","name":"Gemini 3.8 Flash (High)","source_name":"Gemini 3.8 Flash (High)","base":"Gemini 3.8 Flash","variant":"High","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":86.6,"rank":28,"coverage":1,"categories":{"coding":86.2,"agents":71.4,"reasoning":96.2,"math":88.4,"chat":98.1,"instructions":97.4}},"arena":{"text":{"rank":9,"date":"2026-10-28","rating":1498.5,"lo":1494.1,"hi":1502.9,"votes":47803,"pct":98.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":37,"date":"2026-10-28","rating":1583.3,"lo":1576.3,"hi":1590.3,"votes":12342,"pct":76.2,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":7,"date":"2026-10-19","rating":1315.4,"lo":1305.6,"hi":1325.1,"votes":4645,"pct":96.4,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":17,"date":"2026-11-02","score":0.0256,"lo":0.0174,"hi":0.0338,"sessions":52949,"cost_per_task_p50":0.758,"pct":71.4,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1509.2,"rank":16,"pct":96.1,"board_size":414},"math":{"rating":1529.9,"rank":6,"pct":98.8,"board_size":405},"creative_writing":{"rating":1491.2,"rank":8,"pct":98.3,"board_size":417},"instruction_following":{"rating":1492.7,"rank":12,"pct":97.4,"board_size":419},"hard_prompts":{"rating":1508.3,"rank":10,"pct":97.8,"board_size":419},"multi_turn":{"rating":1503.7,"rank":8,"pct":98.3,"board_size":417},"longer_query":{"rating":1508.6,"rank":10,"pct":97.7,"board_size":397},"non_english":{"rating":1491.5,"rank":7,"pct":98.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9539,"stderr":0.014,"tested_as":"gemini-3.8-flash_high","approx":false,"run_date":"2026-09-02","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FBr3mjs2GrYcCwX9AMwcihU.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":98.8,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.697,"stderr":0.0145,"tested_as":"gemini-3.8-flash_high","approx":false,"run_date":"2026-09-02","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FgZ4bwozTKtpmZTqnqX3a33.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":91.9,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9889,"stderr":0.0087,"tested_as":"gemini-3.8-flash_high","approx":false,"run_date":"2026-09-02","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FNeYuqgQyWtFWAHEjQYPm5Z.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":92,"tested_models":313},{"benchmark":"frontiermath","score":0.6842,"stderr":0.0276,"tested_as":"gemini-3.8-flash_high","approx":false,"run_date":"2026-09-02","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":74.4,"tested_models":122}],"price":{"openrouter_id":"google/gemini-3.8-flash","input_per_m":0.825,"output_per_m":4.125,"blended_per_m":1.65,"context_length":1048576,"modalities_in":["text","image","video","file","audio"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gemini-3-8-flash-high"},{"slug":"claude-opus-4-6","name":"Claude Opus 4.6","source_name":"Claude Opus 4.6","base":"Claude Opus 4.6","variant":null,"org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":91.8,"rank":13,"coverage":0.75,"categories":{"coding":85.5,"reasoning":98.3,"math":97.8,"chat":97.8,"instructions":98.3}},"arena":{"text":{"rank":10,"date":"2026-10-28","rating":1496.2,"lo":1493.1,"hi":1499.4,"votes":89324,"pct":97.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":52,"date":"2026-10-28","rating":1537,"lo":1531.7,"hi":1542.4,"votes":20576,"pct":66.2,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":11,"date":"2026-10-19","rating":1312.4,"lo":1306.2,"hi":1318.7,"votes":26841,"pct":94,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1533.4,"rank":5,"pct":99,"board_size":414},"math":{"rating":1509.1,"rank":10,"pct":97.8,"board_size":405},"creative_writing":{"rating":1483.1,"rank":13,"pct":97.1,"board_size":417},"instruction_following":{"rating":1509.2,"rank":8,"pct":98.3,"board_size":419},"hard_prompts":{"rating":1521.7,"rank":8,"pct":98.3,"board_size":419},"multi_turn":{"rating":1505.6,"rank":4,"pct":99.3,"board_size":417},"longer_query":{"rating":1514,"rank":7,"pct":98.5,"board_size":397},"non_english":{"rating":1483.9,"rank":11,"pct":97.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"swe_bench_verified","score":0.7872,"stderr":0.0186,"tested_as":"claude-opus-4-6","approx":false,"run_date":"2026-02-18","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2hH2GAPUFaJR7pfVKhhicg.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":91.2,"tested_models":35}],"price":{"openrouter_id":"anthropic/claude-opus-4.6","input_per_m":5,"output_per_m":25,"blended_per_m":10,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-opus-4-6"},{"slug":"claude-fable-5-high","name":"Claude Fable 5 (High)","source_name":"Claude Fable 5 (High)","base":"Claude Fable 5","variant":"High","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":88.9,"rank":21,"coverage":1,"categories":{"coding":90.4,"agents":83.9,"reasoning":80.6,"math":97.1,"chat":97.6,"instructions":98.1}},"arena":{"text":{"rank":11,"date":"2026-10-28","rating":1491.6,"lo":1487.4,"hi":1495.7,"votes":45341,"pct":97.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":26,"date":"2026-10-28","rating":1624.1,"lo":1618.1,"hi":1630.1,"votes":16951,"pct":83.4,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":1,"date":"2026-10-19","rating":1324.9,"lo":1317.8,"hi":1331.9,"votes":14714,"pct":100,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":10,"date":"2026-11-02","score":0.0778,"lo":0.0666,"hi":0.0889,"sessions":51112,"cost_per_task_p50":3.917,"pct":83.9,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1517.8,"rank":12,"pct":97.3,"board_size":414},"math":{"rating":1516.2,"rank":9,"pct":98,"board_size":405},"creative_writing":{"rating":1493.4,"rank":7,"pct":98.6,"board_size":417},"instruction_following":{"rating":1502.5,"rank":9,"pct":98.1,"board_size":419},"hard_prompts":{"rating":1507.6,"rank":11,"pct":97.6,"board_size":419},"multi_turn":{"rating":1503.4,"rank":9,"pct":98.1,"board_size":417},"longer_query":{"rating":1510.2,"rank":9,"pct":98,"board_size":397},"non_english":{"rating":1481.8,"rank":13,"pct":97.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8333,"stderr":0.0266,"tested_as":"claude-fable-5_high","approx":false,"run_date":"2026-08-06","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Fd23hYvSNGFo7rniLFyBWiu.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":63.6,"tested_models":333},{"benchmark":"otis_mock_aime","score":1,"stderr":0,"tested_as":"claude-fable-5_high","approx":false,"run_date":"2026-08-06","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FhwrnvtEbDAocFtjcsHqsQh.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":96.2,"tested_models":313}],"price":{"openrouter_id":"anthropic/claude-fable-5","input_per_m":10,"output_per_m":50,"blended_per_m":20,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-fable-5-high"},{"slug":"mimo-v2-6-pro","name":"MiMo-V2.6-Pro","source_name":"MiMo-V2.6-Pro","base":"MiMo-V2.6-Pro","variant":null,"org":"xiaomi","open_weights":true,"model_license":"MIT","siscope":{"score":88.1,"rank":24,"coverage":1,"categories":{"coding":91.7,"agents":66.1,"reasoning":98.1,"math":96,"chat":97.4,"instructions":96.9}},"arena":{"text":{"rank":12,"date":"2026-10-28","rating":1491.4,"lo":1482,"hi":1500.7,"votes":4037,"pct":97.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":25,"date":"2026-10-28","rating":1625.4,"lo":1617,"hi":1633.8,"votes":6820,"pct":84.1,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":53,"date":"2026-10-19","rating":1262.8,"lo":1248.1,"hi":1277.5,"votes":1754,"pct":68.7,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":20,"date":"2026-11-02","score":0.0244,"lo":0.0154,"hi":0.0335,"sessions":47901,"cost_per_task_p50":0.156,"pct":66.1,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1533.5,"rank":4,"pct":99.3,"board_size":414},"math":{"rating":1501.4,"rank":17,"pct":96,"board_size":405},"creative_writing":{"rating":1463.9,"rank":22,"pct":94.7,"board_size":417},"instruction_following":{"rating":1491.7,"rank":14,"pct":96.9,"board_size":419},"hard_prompts":{"rating":1511.2,"rank":9,"pct":98.1,"board_size":419},"multi_turn":{"rating":1465.6,"rank":43,"pct":89.9,"board_size":417},"longer_query":{"rating":1501.9,"rank":12,"pct":97.2,"board_size":397},"non_english":{"rating":1474.4,"rank":18,"pct":95.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"xiaomi/mimo-v2.6-pro","input_per_m":0.435,"output_per_m":0.87,"blended_per_m":0.5437,"context_length":1050000,"modalities_in":["text","image","video","audio"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/mimo-v2-6-pro"},{"slug":"muse-spark-1-3-max","name":"Muse Spark 1.3 (Max)","source_name":"Muse Spark 1.3 (Max)","base":"Muse Spark 1.3","variant":"Max","org":"meta","open_weights":false,"model_license":"Proprietary","siscope":{"score":86.7,"rank":27,"coverage":1,"categories":{"coding":92.4,"agents":66.1,"reasoning":96.9,"math":88.4,"chat":97.1,"instructions":94.5}},"arena":{"text":{"rank":13,"date":"2026-10-28","rating":1490.6,"lo":1485.4,"hi":1495.8,"votes":22134,"pct":97.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":19,"date":"2026-10-28","rating":1656.2,"lo":1648.8,"hi":1663.7,"votes":10796,"pct":88.1,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":12,"date":"2026-10-19","rating":1308.4,"lo":1299.3,"hi":1317.6,"votes":5392,"pct":93.4,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":19,"date":"2026-11-02","score":0.0244,"lo":0.0162,"hi":0.0326,"sessions":80904,"cost_per_task_p50":0.449,"pct":66.1,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1509.4,"rank":15,"pct":96.6,"board_size":414},"math":{"rating":1500.7,"rank":18,"pct":95.8,"board_size":405},"creative_writing":{"rating":1463.9,"rank":23,"pct":94.7,"board_size":417},"instruction_following":{"rating":1477.6,"rank":24,"pct":94.5,"board_size":419},"hard_prompts":{"rating":1502.5,"rank":14,"pct":96.9,"board_size":419},"multi_turn":{"rating":1487.9,"rank":17,"pct":96.2,"board_size":417},"longer_query":{"rating":1487.7,"rank":19,"pct":95.5,"board_size":397},"non_english":{"rating":1481.9,"rank":12,"pct":97.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"frontiermath","score":0.7404,"stderr":0.026,"tested_as":"muse-spark-1.3_max","approx":false,"run_date":"2026-09-18","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":81,"tested_models":122}],"price":{"openrouter_id":"meta/muse-spark-1.3","input_per_m":1.25,"output_per_m":4.25,"blended_per_m":2,"context_length":1048576,"modalities_in":["text","image","video","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/muse-spark-1-3-max"},{"slug":"claude-opus-4-7-high","name":"Claude Opus 4.7 (High)","source_name":"Claude Opus 4.7 (High)","base":"Claude Opus 4.7","variant":"High","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":90.8,"rank":16,"coverage":0.75,"categories":{"coding":85,"reasoning":97.1,"math":95.5,"chat":96.9,"instructions":97.8}},"arena":{"text":{"rank":14,"date":"2026-10-28","rating":1489.7,"lo":1486,"hi":1493.5,"votes":65110,"pct":96.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":43,"date":"2026-10-28","rating":1557.5,"lo":1551.8,"hi":1563.3,"votes":17859,"pct":72.2,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":9,"date":"2026-10-19","rating":1313.1,"lo":1306.6,"hi":1319.6,"votes":22731,"pct":95.2,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1518.7,"rank":10,"pct":97.8,"board_size":414},"math":{"rating":1498.7,"rank":19,"pct":95.5,"board_size":405},"creative_writing":{"rating":1486,"rank":12,"pct":97.4,"board_size":417},"instruction_following":{"rating":1497.9,"rank":10,"pct":97.8,"board_size":419},"hard_prompts":{"rating":1505.6,"rank":13,"pct":97.1,"board_size":419},"multi_turn":{"rating":1505.3,"rank":5,"pct":99,"board_size":417},"longer_query":{"rating":1505.2,"rank":11,"pct":97.5,"board_size":397},"non_english":{"rating":1480.3,"rank":14,"pct":96.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"anthropic/claude-opus-4.7","input_per_m":5,"output_per_m":25,"blended_per_m":10,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-opus-4-7-high"},{"slug":"gemini-3-7-flash-high","name":"Gemini 3.7 Flash (High)","source_name":"Gemini 3.7 Flash (High)","base":"Gemini 3.7 Flash","variant":"High","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":78.9,"rank":50,"coverage":1,"categories":{"coding":85.9,"agents":42.9,"reasoning":95.3,"math":87.5,"chat":96.7,"instructions":96.4}},"arena":{"text":{"rank":15,"date":"2026-10-28","rating":1489.1,"lo":1484.5,"hi":1493.8,"votes":32289,"pct":96.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":35,"date":"2026-10-28","rating":1589.7,"lo":1583.2,"hi":1596.2,"votes":14473,"pct":77.5,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":8,"date":"2026-10-19","rating":1314.2,"lo":1305.1,"hi":1323.4,"votes":5369,"pct":95.8,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":33,"date":"2026-11-02","score":-0.0163,"lo":-0.0249,"hi":-0.0076,"sessions":63681,"cost_per_task_p50":0.589,"pct":42.9,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1499.8,"rank":25,"pct":94.2,"board_size":414},"math":{"rating":1507.1,"rank":11,"pct":97.5,"board_size":405},"creative_writing":{"rating":1487.4,"rank":11,"pct":97.6,"board_size":417},"instruction_following":{"rating":1485.8,"rank":16,"pct":96.4,"board_size":419},"hard_prompts":{"rating":1497.3,"rank":16,"pct":96.4,"board_size":419},"multi_turn":{"rating":1484.9,"rank":19,"pct":95.7,"board_size":417},"longer_query":{"rating":1494.1,"rank":16,"pct":96.2,"board_size":397},"non_english":{"rating":1485.7,"rank":10,"pct":97.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9482,"stderr":0.0135,"tested_as":"gemini-3.7-flash_high","approx":false,"run_date":"2026-08-14","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FXyVL3VffJ6UboY97vxpohL.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":98.5,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.692,"stderr":0.0146,"tested_as":"gemini-3.7-flash_high","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F84ARuGyhQsjgh8umRmBvas.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":90.9,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9722,"stderr":0.0186,"tested_as":"gemini-3.7-flash_high","approx":false,"run_date":"2026-08-14","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FkQjrYCaa7yYyMXofeR23Dd.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":86.5,"tested_models":313},{"benchmark":"frontiermath","score":0.7158,"stderr":0.0268,"tested_as":"gemini-3.7-flash_high","approx":false,"run_date":"2026-08-14","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FaxMdgNDC8UYYLnZYLHZpF5.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":78.5,"tested_models":122}],"price":{"openrouter_id":"google/gemini-3.7-flash","input_per_m":0.75,"output_per_m":3.75,"blended_per_m":1.5,"context_length":1048576,"modalities_in":["text","image","video","file","audio"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gemini-3-7-flash-high"},{"slug":"qwen3-8-max","name":"Qwen3.8-Max","source_name":"Qwen3.8-Max","base":"Qwen3.8-Max","variant":null,"org":"alibaba","open_weights":false,"model_license":"Proprietary","siscope":{"score":84,"rank":32,"coverage":1,"categories":{"coding":93.1,"agents":50,"reasoning":96.2,"math":97,"chat":96.4,"instructions":95.2}},"arena":{"text":{"rank":16,"date":"2026-10-28","rating":1483.3,"lo":1478.5,"hi":1488.1,"votes":31915,"pct":96.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":15,"date":"2026-10-28","rating":1671.9,"lo":1659.8,"hi":1684,"votes":3406,"pct":90.7,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":10,"date":"2026-10-19","rating":1312.9,"lo":1305.5,"hi":1320.4,"votes":9957,"pct":94.6,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":29,"date":"2026-11-02","score":0.004,"lo":-0.0024,"hi":0.0105,"sessions":79589,"cost_per_task_p50":1.353,"pct":50,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1503.5,"rank":20,"pct":95.4,"board_size":414},"math":{"rating":1506,"rank":13,"pct":97,"board_size":405},"creative_writing":{"rating":1478.4,"rank":17,"pct":96.2,"board_size":417},"instruction_following":{"rating":1480.4,"rank":21,"pct":95.2,"board_size":419},"hard_prompts":{"rating":1496.4,"rank":17,"pct":96.2,"board_size":419},"multi_turn":{"rating":1491,"rank":15,"pct":96.6,"board_size":417},"longer_query":{"rating":1488.5,"rank":18,"pct":95.7,"board_size":397},"non_english":{"rating":1472.4,"rank":22,"pct":95,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen3-8-max"},{"slug":"claude-opus-4-7","name":"Claude Opus 4.7","source_name":"Claude Opus 4.7","base":"Claude Opus 4.7","variant":null,"org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":90,"rank":19,"coverage":0.75,"categories":{"coding":84,"reasoning":96.7,"math":94.8,"chat":96.2,"instructions":96.7}},"arena":{"text":{"rank":17,"date":"2026-10-28","rating":1483,"lo":1479.2,"hi":1486.7,"votes":66140,"pct":96.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":45,"date":"2026-10-28","rating":1555.4,"lo":1549.8,"hi":1561.1,"votes":18167,"pct":70.9,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":5,"date":"2026-10-19","rating":1316.9,"lo":1310.4,"hi":1323.5,"votes":23139,"pct":97.6,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1514.8,"rank":13,"pct":97.1,"board_size":414},"math":{"rating":1489.3,"rank":22,"pct":94.8,"board_size":405},"creative_writing":{"rating":1480.1,"rank":16,"pct":96.4,"board_size":417},"instruction_following":{"rating":1488.5,"rank":15,"pct":96.7,"board_size":419},"hard_prompts":{"rating":1499.5,"rank":15,"pct":96.7,"board_size":419},"multi_turn":{"rating":1504,"rank":7,"pct":98.6,"board_size":417},"longer_query":{"rating":1498.9,"rank":13,"pct":97,"board_size":397},"non_english":{"rating":1474.4,"rank":19,"pct":95.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"anthropic/claude-opus-4.7","input_per_m":5,"output_per_m":25,"blended_per_m":10,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-opus-4-7"},{"slug":"muse-spark-1-2-xhigh","name":"Muse Spark 1.2 (xHigh)","source_name":"Muse Spark 1.2 (xHigh)","base":"Muse Spark 1.2","variant":"xHigh","org":"meta","open_weights":false,"model_license":"Proprietary","siscope":{"score":70.1,"rank":83,"coverage":1,"categories":{"coding":80.3,"agents":16.1,"reasoning":90,"math":92.8,"chat":95.9,"instructions":90.9}},"arena":{"text":{"rank":18,"date":"2026-10-28","rating":1482.7,"lo":1476.3,"hi":1489,"votes":11724,"pct":95.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":54,"date":"2026-10-28","rating":1533.7,"lo":1520,"hi":1547.3,"votes":2155,"pct":64.9,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":17,"date":"2026-10-19","rating":1304.2,"lo":1289.9,"hi":1318.5,"votes":1948,"pct":90.4,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":48,"date":"2026-11-02","score":-0.0774,"lo":-0.0858,"hi":-0.069,"sessions":54988,"cost_per_task_p50":0.439,"pct":16.1,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1505.9,"rank":19,"pct":95.6,"board_size":414},"math":{"rating":1484.6,"rank":30,"pct":92.8,"board_size":405},"creative_writing":{"rating":1436.9,"rank":53,"pct":87.5,"board_size":417},"instruction_following":{"rating":1464.8,"rank":39,"pct":90.9,"board_size":419},"hard_prompts":{"rating":1491.6,"rank":21,"pct":95.2,"board_size":419},"multi_turn":{"rating":1496.2,"rank":12,"pct":97.4,"board_size":417},"longer_query":{"rating":1473.8,"rank":41,"pct":89.9,"board_size":397},"non_english":{"rating":1475.2,"rank":17,"pct":96.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"simpleqa_verified","score":0.603,"stderr":0.0155,"tested_as":"muse-spark-1.2_xhigh","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FmLLmVVvo6t23MM5yxq7ryW.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":84.8,"tested_models":100}],"price":{"openrouter_id":"meta/muse-spark-1.2","input_per_m":1.25,"output_per_m":4.25,"blended_per_m":2,"context_length":1048576,"modalities_in":["text","image","video","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/muse-spark-1-2-xhigh"},{"slug":"gemini-3-5-flash-high","name":"Gemini 3.5 Flash (High)","source_name":"Gemini 3.5 Flash (High)","base":"Gemini 3.5 Flash","variant":"High","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":85.4,"rank":29,"coverage":0.75,"categories":{"coding":81.2,"reasoning":91.6,"math":81.8,"chat":95.7,"instructions":92.3}},"arena":{"text":{"rank":19,"date":"2026-10-28","rating":1482.2,"lo":1478.3,"hi":1486,"votes":48376,"pct":95.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":65,"date":"2026-10-28","rating":1499.3,"lo":1492,"hi":1506.5,"votes":9331,"pct":57.6,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":13,"date":"2026-10-19","rating":1308.3,"lo":1301.5,"hi":1315.1,"votes":13862,"pct":92.8,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1493,"rank":34,"pct":92,"board_size":414},"math":{"rating":1504.2,"rank":14,"pct":96.8,"board_size":405},"creative_writing":{"rating":1468.7,"rank":20,"pct":95.4,"board_size":417},"instruction_following":{"rating":1467.2,"rank":33,"pct":92.3,"board_size":419},"hard_prompts":{"rating":1488.2,"rank":24,"pct":94.5,"board_size":419},"multi_turn":{"rating":1481,"rank":24,"pct":94.5,"board_size":417},"longer_query":{"rating":1482.8,"rank":24,"pct":94.2,"board_size":397},"non_english":{"rating":1475.7,"rank":16,"pct":96.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.928,"stderr":0.0164,"tested_as":"gemini-3.5-flash_high","approx":false,"run_date":"2026-05-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FdYYtcwENFRtm9jZTDA2p9C.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":92.5,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.662,"stderr":0.015,"tested_as":"gemini-3.5-flash_high","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FGJ6YsSuzyRD9YXe6SBwvsu.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":87.9,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9556,"stderr":0.0267,"tested_as":"gemini-3.5-flash_high","approx":false,"run_date":"2026-05-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FeYmgjYJfM7Utm46nfoRfZ6.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":81.7,"tested_models":313},{"benchmark":"frontiermath","score":0.6281,"stderr":0.0287,"tested_as":"gemini-3.5-flash_high","approx":false,"run_date":"2026-06-10","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F72DQVwbYiQW5pjhshjBaGU.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":66.9,"tested_models":122},{"benchmark":"swe_bench_verified","score":0.7934,"stderr":0.0184,"tested_as":"gemini-3.5-flash_high","approx":false,"run_date":"2026-06-01","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FdwRzFGTghYEy4HNZajJXoc.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":94.1,"tested_models":35}],"price":{"openrouter_id":"google/gemini-3.5-flash","input_per_m":1.5,"output_per_m":9,"blended_per_m":3.375,"context_length":1048576,"modalities_in":["text","image","video","file","audio"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gemini-3-5-flash-high"},{"slug":"gemini-3-1-pro-preview","name":"Gemini 3.1 Pro Preview","source_name":"Gemini 3.1 Pro Preview","base":"Gemini 3.1 Pro Preview","variant":null,"org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":69.8,"rank":86,"coverage":1,"categories":{"coding":67.8,"agents":30.4,"reasoning":94.8,"math":81.3,"chat":95.5,"instructions":91.6}},"arena":{"text":{"rank":20,"date":"2026-10-28","rating":1480.1,"lo":1477.2,"hi":1483,"votes":132547,"pct":95.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":80,"date":"2026-10-28","rating":1446.6,"lo":1441.6,"hi":1451.7,"votes":24129,"pct":47.7,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":22,"date":"2026-10-19","rating":1295.8,"lo":1290.7,"hi":1300.9,"votes":47114,"pct":87.3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":40,"date":"2026-11-02","score":-0.0461,"lo":-0.06,"hi":-0.0323,"sessions":88001,"cost_per_task_p50":0.633,"pct":30.4,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1483.5,"rank":50,"pct":87.9,"board_size":414},"math":{"rating":1485.3,"rank":28,"pct":93.1,"board_size":405},"creative_writing":{"rating":1482.3,"rank":14,"pct":96.9,"board_size":417},"instruction_following":{"rating":1466,"rank":36,"pct":91.6,"board_size":419},"hard_prompts":{"rating":1484.6,"rank":31,"pct":92.8,"board_size":419},"multi_turn":{"rating":1486.3,"rank":18,"pct":95.9,"board_size":417},"longer_query":{"rating":1482.1,"rank":26,"pct":93.7,"board_size":397},"non_english":{"rating":1476.3,"rank":15,"pct":96.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.941,"stderr":0.017,"tested_as":"gemini-3.1-pro-preview","approx":false,"run_date":"2026-02-20","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FkR9F3oHBCnwQW4AiTPKwpd.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":96.7,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.956,"stderr":0.031,"tested_as":"gemini-3.1-pro-preview","approx":false,"run_date":"2026-02-20","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FbXgZZgzRE3wXoSRUgrbsVf.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":84.6,"tested_models":313},{"benchmark":"frontiermath","score":0.5965,"stderr":0.0291,"tested_as":"gemini-3.1-pro-preview","approx":false,"run_date":"2026-06-11","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FhVifTUdQZrFEYabgCRu8Qq.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":66.1,"tested_models":122}],"price":{"openrouter_id":"google/gemini-3.1-pro-preview","input_per_m":2,"output_per_m":12,"blended_per_m":4.5,"context_length":1048576,"modalities_in":["audio","file","image","text","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gemini-3-1-pro-preview"},{"slug":"gemini-3-6-flash-high","name":"Gemini 3.6 Flash (High)","source_name":"Gemini 3.6 Flash (High)","base":"Gemini 3.6 Flash","variant":"High","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":84.5,"rank":30,"coverage":0.75,"categories":{"coding":79.4,"reasoning":92.8,"math":80.6,"chat":95.2,"instructions":92.1}},"arena":{"text":{"rank":21,"date":"2026-10-28","rating":1479.8,"lo":1475.4,"hi":1484.2,"votes":36028,"pct":95.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":51,"date":"2026-10-28","rating":1537.5,"lo":1530.1,"hi":1545,"votes":8722,"pct":66.9,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":20,"date":"2026-10-19","rating":1298.9,"lo":1291,"hi":1306.7,"votes":8979,"pct":88.6,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1491.4,"rank":35,"pct":91.8,"board_size":414},"math":{"rating":1506.7,"rank":12,"pct":97.3,"board_size":405},"creative_writing":{"rating":1466.2,"rank":21,"pct":95.2,"board_size":417},"instruction_following":{"rating":1467,"rank":34,"pct":92.1,"board_size":419},"hard_prompts":{"rating":1485.7,"rank":28,"pct":93.5,"board_size":419},"multi_turn":{"rating":1481.3,"rank":23,"pct":94.7,"board_size":417},"longer_query":{"rating":1474.8,"rank":39,"pct":90.4,"board_size":397},"non_english":{"rating":1469.5,"rank":25,"pct":94.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9413,"stderr":0.014,"tested_as":"gemini-3.6-flash_high","approx":false,"run_date":"2026-08-02","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F86SY5JbPB49xXhHFQW6tHu.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":97,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.662,"stderr":0.015,"tested_as":"gemini-3.6-flash_high","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FF83pa7Gfsb4UNVttTnS5Hk.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":87.9,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9417,"stderr":0.0309,"tested_as":"gemini-3.6-flash_high","approx":false,"run_date":"2026-08-02","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FajQFZGMjvyMTH2ULDZhwtz.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":80.1,"tested_models":313},{"benchmark":"frontiermath","score":0.5895,"stderr":0.0292,"tested_as":"gemini-3.6-flash_high","approx":false,"run_date":"2026-08-02","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Fnb9LnDeeQyvRCqsbsTANGD.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":64.5,"tested_models":122}],"price":{"openrouter_id":"google/gemini-3.6-flash","input_per_m":0.75,"output_per_m":3.75,"blended_per_m":1.5,"context_length":1048576,"modalities_in":["text","image","video","file","audio"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gemini-3-6-flash-high"},{"slug":"gemini-3-pro","name":"Gemini 3 Pro","source_name":"Gemini 3 Pro","base":"Gemini 3 Pro","variant":null,"org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":78.7,"rank":51,"coverage":0.75,"categories":{"coding":66.1,"reasoning":90.7,"math":90.3,"chat":95,"instructions":89.5}},"arena":{"text":{"rank":22,"date":"2026-10-28","rating":1479.4,"lo":1475.6,"hi":1483.2,"votes":42057,"pct":95,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":83,"date":"2026-10-28","rating":1440,"lo":1431.5,"hi":1448.4,"votes":14054,"pct":45.7,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":16,"date":"2026-10-19","rating":1304.8,"lo":1297.4,"hi":1312.1,"votes":13623,"pct":91,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1481.2,"rank":57,"pct":86.4,"board_size":414},"math":{"rating":1476.1,"rank":40,"pct":90.3,"board_size":405},"creative_writing":{"rating":1482.1,"rank":15,"pct":96.6,"board_size":417},"instruction_following":{"rating":1457.8,"rank":45,"pct":89.5,"board_size":419},"hard_prompts":{"rating":1480.3,"rank":40,"pct":90.7,"board_size":419},"multi_turn":{"rating":1484,"rank":20,"pct":95.4,"board_size":417},"longer_query":{"rating":1471,"rank":43,"pct":89.4,"board_size":397},"non_english":{"rating":1474.2,"rank":20,"pct":95.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemini-3-pro"},{"slug":"muse-spark-1-1","name":"Muse Spark 1.1","source_name":"Muse Spark 1.1","base":"Muse Spark 1.1","variant":null,"org":"meta","open_weights":false,"model_license":"Proprietary","siscope":{"score":70.2,"rank":82,"coverage":1,"categories":{"coding":80.9,"agents":17.9,"reasoning":88.6,"math":92.3,"chat":94.7,"instructions":89.2}},"arena":{"text":{"rank":23,"date":"2026-10-28","rating":1478.3,"lo":1474.2,"hi":1482.4,"votes":46354,"pct":94.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":49,"date":"2026-10-28","rating":1542.5,"lo":1534.9,"hi":1550.1,"votes":7935,"pct":68.2,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":26,"date":"2026-10-19","rating":1292.5,"lo":1285.6,"hi":1299.4,"votes":12804,"pct":84.9,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":47,"date":"2026-11-02","score":-0.0768,"lo":-0.0833,"hi":-0.0702,"sessions":150517,"cost_per_task_p50":0.372,"pct":17.9,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1497.7,"rank":28,"pct":93.5,"board_size":414},"math":{"rating":1481.9,"rank":32,"pct":92.3,"board_size":405},"creative_writing":{"rating":1435.4,"rank":55,"pct":86.5,"board_size":417},"instruction_following":{"rating":1456.7,"rank":46,"pct":89.2,"board_size":419},"hard_prompts":{"rating":1485.9,"rank":25,"pct":94.3,"board_size":419},"multi_turn":{"rating":1483.8,"rank":21,"pct":95.2,"board_size":417},"longer_query":{"rating":1461.7,"rank":51,"pct":87.4,"board_size":397},"non_english":{"rating":1471.3,"rank":24,"pct":94.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"simpleqa_verified","score":0.5779,"stderr":0.0157,"tested_as":"muse-spark-1.1","approx":false,"run_date":"2026-08-31","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FbCdwpRXgZtvQLYC4wA9JXr.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":82.8,"tested_models":100}],"price":{"openrouter_id":"meta/muse-spark-1.1","input_per_m":1.25,"output_per_m":4.25,"blended_per_m":2,"context_length":1048576,"modalities_in":["text","image","video","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/muse-spark-1-1"},{"slug":"gemini-3-5-flash-medium","name":"Gemini 3.5 Flash (Medium)","source_name":"Gemini 3.5 Flash (Medium)","base":"Gemini 3.5 Flash","variant":"Medium","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":83.3,"rank":33,"coverage":0.75,"categories":{"coding":73.2,"reasoning":93.3,"math":93.8,"chat":94.5,"instructions":91.1}},"arena":{"text":{"rank":24,"date":"2026-10-28","rating":1478.2,"lo":1474,"hi":1482.3,"votes":47196,"pct":94.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":67,"date":"2026-10-28","rating":1490.6,"lo":1484,"hi":1497.3,"votes":12075,"pct":56.3,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":14,"date":"2026-10-19","rating":1306.3,"lo":1299.5,"hi":1313.1,"votes":14061,"pct":92.2,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1487.5,"rank":41,"pct":90.1,"board_size":414},"math":{"rating":1486.2,"rank":26,"pct":93.8,"board_size":405},"creative_writing":{"rating":1471.3,"rank":18,"pct":95.9,"board_size":417},"instruction_following":{"rating":1464.9,"rank":38,"pct":91.1,"board_size":419},"hard_prompts":{"rating":1485.2,"rank":29,"pct":93.3,"board_size":419},"multi_turn":{"rating":1476,"rank":28,"pct":93.5,"board_size":417},"longer_query":{"rating":1477.3,"rank":35,"pct":91.4,"board_size":397},"non_english":{"rating":1471.9,"rank":23,"pct":94.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"google/gemini-3.5-flash","input_per_m":1.5,"output_per_m":9,"blended_per_m":3.375,"context_length":1048576,"modalities_in":["text","image","video","file","audio"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gemini-3-5-flash-medium"},{"slug":"kimi-k3-max","name":"Kimi K3 (Max)","source_name":"Kimi K3 (Max)","base":"Kimi K3","variant":"Max","org":"moonshot","open_weights":true,"model_license":"Kimi K3 license","siscope":{"score":82.1,"rank":35,"coverage":1,"categories":{"coding":92.3,"agents":57.1,"reasoning":87.6,"math":86.9,"chat":94.3,"instructions":96.2}},"arena":{"text":{"rank":25,"date":"2026-10-28","rating":1475.7,"lo":1471.3,"hi":1480.1,"votes":36780,"pct":94.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":18,"date":"2026-10-28","rating":1656.4,"lo":1650.6,"hi":1662.2,"votes":21281,"pct":88.7,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":25,"date":"2026-11-02","score":0.0086,"lo":0.0028,"hi":0.0143,"sessions":161000,"cost_per_task_p50":1.123,"pct":57.1,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1508.4,"rank":18,"pct":95.9,"board_size":414},"math":{"rating":1492.4,"rank":21,"pct":95,"board_size":405},"creative_writing":{"rating":1457.2,"rank":28,"pct":93.5,"board_size":417},"instruction_following":{"rating":1485.2,"rank":17,"pct":96.2,"board_size":419},"hard_prompts":{"rating":1495.5,"rank":18,"pct":95.9,"board_size":419},"multi_turn":{"rating":1489.6,"rank":16,"pct":96.4,"board_size":417},"longer_query":{"rating":1493.5,"rank":17,"pct":96,"board_size":397},"non_english":{"rating":1465.9,"rank":27,"pct":93.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9312,"stderr":0.0149,"tested_as":"kimi-k3_max","approx":false,"run_date":"2026-07-16","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FB8MaPUe3EYwUZASsNqE7C9.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":93.1,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.506,"stderr":0.0158,"tested_as":"kimi-k3_max","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FmZLWt2JSYvJyGhMvji7CT8.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":73.7,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9722,"stderr":0.0112,"tested_as":"kimi-k3_max","approx":false,"run_date":"2026-07-16","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FA33om9MTYMC7xYeLv9X7Ha.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":86.5,"tested_models":313},{"benchmark":"frontiermath","score":0.7218,"stderr":0.0266,"tested_as":"kimi-k3_max","approx":false,"run_date":"2026-07-17","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":79.3,"tested_models":122}],"price":{"openrouter_id":"moonshotai/kimi-k3","input_per_m":0.276,"output_per_m":9.6,"blended_per_m":2.607,"context_length":1048576,"modalities_in":["text","image","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/kimi-k3-max"},{"slug":"qwen3-7-max-preview","name":"Qwen3.7 Max Preview","source_name":"Qwen3.7-Max-Preview","base":"Qwen3.7 Max Preview","variant":null,"org":"alibaba","open_weights":false,"model_license":"Proprietary","siscope":{"score":92.1,"rank":11,"coverage":0.75,"categories":{"coding":93,"reasoning":91.4,"math":94.1,"chat":94,"instructions":90.2}},"arena":{"text":{"rank":26,"date":"2026-10-28","rating":1474.7,"lo":1465,"hi":1484.3,"votes":3932,"pct":94,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1496.6,"rank":30,"pct":93,"board_size":414},"math":{"rating":1486.4,"rank":25,"pct":94.1,"board_size":405},"creative_writing":{"rating":1446.5,"rank":37,"pct":91.3,"board_size":417},"instruction_following":{"rating":1460,"rank":42,"pct":90.2,"board_size":419},"hard_prompts":{"rating":1481.9,"rank":37,"pct":91.4,"board_size":419},"multi_turn":{"rating":1479.9,"rank":25,"pct":94.2,"board_size":417},"longer_query":{"rating":1481.2,"rank":27,"pct":93.4,"board_size":397},"non_english":{"rating":1472.9,"rank":21,"pct":95.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen3-7-max-preview"},{"slug":"muse-spark","name":"Muse Spark","source_name":"Muse Spark","base":"Muse Spark","variant":null,"org":"meta","open_weights":false,"model_license":"Proprietary","siscope":{"score":84.1,"rank":31,"coverage":0.75,"categories":{"coding":86.7,"reasoning":87,"math":78.3,"chat":93.8,"instructions":86.1}},"arena":{"text":{"rank":27,"date":"2026-10-28","rating":1474,"lo":1468.3,"hi":1479.7,"votes":14140,"pct":93.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":15,"date":"2026-10-19","rating":1305.8,"lo":1296.7,"hi":1314.8,"votes":5865,"pct":91.6,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1481.3,"rank":56,"pct":86.7,"board_size":414},"math":{"rating":1455.8,"rank":68,"pct":83.4,"board_size":405},"creative_writing":{"rating":1458.7,"rank":27,"pct":93.8,"board_size":417},"instruction_following":{"rating":1442.3,"rank":59,"pct":86.1,"board_size":419},"hard_prompts":{"rating":1474.2,"rank":42,"pct":90.2,"board_size":419},"multi_turn":{"rating":1476.7,"rank":27,"pct":93.8,"board_size":417},"longer_query":{"rating":1450.3,"rank":64,"pct":84.1,"board_size":397},"non_english":{"rating":1463.3,"rank":31,"pct":92.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.898,"stderr":0.022,"tested_as":"muse-spark","approx":false,"run_date":"2026-04-08","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":83.7,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.889,"stderr":0.047,"tested_as":"muse-spark","approx":false,"run_date":"2026-04-08","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":73.1,"tested_models":313}],"price":null,"url":"https://siscope.app/models/muse-spark"},{"slug":"glm-5-3-max","name":"GLM-5.3 (Max)","source_name":"GLM-5.3 (Max)","base":"GLM-5.3","variant":"Max","org":"zai","open_weights":true,"model_license":"MIT","siscope":{"score":79,"rank":49,"coverage":1,"categories":{"coding":88,"agents":60.7,"reasoning":77.2,"math":81.4,"chat":93.5,"instructions":95.7}},"arena":{"text":{"rank":28,"date":"2026-10-28","rating":1473.8,"lo":1468.8,"hi":1478.7,"votes":26606,"pct":93.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":27,"date":"2026-10-28","rating":1622.8,"lo":1615.6,"hi":1630.1,"votes":11150,"pct":82.8,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":23,"date":"2026-11-02","score":0.0117,"lo":0.0037,"hi":0.0196,"sessions":96216,"cost_per_task_p50":1.141,"pct":60.7,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1496.9,"rank":29,"pct":93.2,"board_size":414},"math":{"rating":1497.2,"rank":20,"pct":95.3,"board_size":405},"creative_writing":{"rating":1459.4,"rank":26,"pct":94,"board_size":417},"instruction_following":{"rating":1481.3,"rank":19,"pct":95.7,"board_size":419},"hard_prompts":{"rating":1490.3,"rank":22,"pct":95,"board_size":419},"multi_turn":{"rating":1470,"rank":38,"pct":91.1,"board_size":417},"longer_query":{"rating":1483.5,"rank":23,"pct":94.4,"board_size":397},"non_english":{"rating":1459.6,"rank":33,"pct":92.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9091,"stderr":0.0159,"tested_as":"glm-5.3_max","approx":false,"run_date":"2026-08-24","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FdLDBahYBTGRNjbsXA5pyr3.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":88,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.41,"stderr":0.0156,"tested_as":"glm-5.3_max","approx":false,"run_date":"2026-08-28","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FTY8R8FV7zCwByEipkqyg2P.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":48.5,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9111,"stderr":0.0345,"tested_as":"glm-5.3_max","approx":false,"run_date":"2026-08-24","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FgoZR5yGxZic9TZ23ezCL3w.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":73.7,"tested_models":313},{"benchmark":"frontiermath","score":0.6877,"stderr":0.0275,"tested_as":"glm-5.3_max","approx":false,"run_date":"2026-08-25","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":75.2,"tested_models":122}],"price":{"openrouter_id":"z-ai/glm-5.3","input_per_m":0.08,"output_per_m":3.6,"blended_per_m":0.96,"context_length":1048576,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/glm-5-3-max"},{"slug":"glm-5-3-flash","name":"GLM-5.3 Flash","source_name":"GLM-5.3-Flash","base":"GLM-5.3 Flash","variant":null,"org":"zai","open_weights":true,"model_license":"MIT","siscope":{"score":79.4,"rank":46,"coverage":1,"categories":{"coding":87.8,"agents":39.3,"reasoning":95.5,"math":96.3,"chat":93.3,"instructions":95.5}},"arena":{"text":{"rank":29,"date":"2026-10-28","rating":1473,"lo":1468.4,"hi":1477.7,"votes":41642,"pct":93.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":32,"date":"2026-10-28","rating":1606.6,"lo":1600.3,"hi":1613,"votes":21587,"pct":79.5,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":24,"date":"2026-10-19","rating":1293.9,"lo":1287.5,"hi":1300.2,"votes":16254,"pct":86.1,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":35,"date":"2026-11-02","score":-0.0249,"lo":-0.0318,"hi":-0.018,"sessions":95599,"cost_per_task_p50":0.16,"pct":39.3,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1509.2,"rank":17,"pct":96.1,"board_size":414},"math":{"rating":1501.6,"rank":16,"pct":96.3,"board_size":405},"creative_writing":{"rating":1441.5,"rank":43,"pct":89.9,"board_size":417},"instruction_following":{"rating":1480.6,"rank":20,"pct":95.5,"board_size":419},"hard_prompts":{"rating":1492.2,"rank":20,"pct":95.5,"board_size":419},"multi_turn":{"rating":1471.1,"rank":36,"pct":91.6,"board_size":417},"longer_query":{"rating":1483.7,"rank":22,"pct":94.7,"board_size":397},"non_english":{"rating":1463.4,"rank":30,"pct":93.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"z-ai/glm-5.3-flash","input_per_m":0.0313,"output_per_m":0.0846,"blended_per_m":0.0446,"context_length":1048576,"modalities_in":["text","image","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/glm-5-3-flash"},{"slug":"claude-sonnet-5-5-xhigh","name":"Claude Sonnet 5.5 (xHigh)","source_name":"Claude Sonnet 5.5 (xHigh)","base":"Claude Sonnet 5.5","variant":"xHigh","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":95.5,"rank":7,"coverage":0.75,"categories":{"coding":97.8,"reasoning":95.7,"math":96.5,"chat":93.1,"instructions":97.1}},"arena":{"text":{"rank":30,"date":"2026-10-28","rating":1472.9,"lo":1466.1,"hi":1479.6,"votes":10033,"pct":93.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":3,"date":"2026-10-28","rating":1769.7,"lo":1758.5,"hi":1781,"votes":4469,"pct":98.7,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":30,"date":"2026-10-19","rating":1287.2,"lo":1274.7,"hi":1299.7,"votes":2564,"pct":82.5,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1511.9,"rank":14,"pct":96.9,"board_size":414},"math":{"rating":1503.9,"rank":15,"pct":96.5,"board_size":405},"creative_writing":{"rating":1470.4,"rank":19,"pct":95.7,"board_size":417},"instruction_following":{"rating":1491.8,"rank":13,"pct":97.1,"board_size":419},"hard_prompts":{"rating":1493.8,"rank":19,"pct":95.7,"board_size":419},"multi_turn":{"rating":1468.1,"rank":40,"pct":90.6,"board_size":417},"longer_query":{"rating":1494.4,"rank":15,"pct":96.5,"board_size":397},"non_english":{"rating":1456.1,"rank":36,"pct":91.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"anthropic/claude-sonnet-5.5","input_per_m":2,"output_per_m":10,"blended_per_m":4,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-sonnet-5-5-xhigh"},{"slug":"gpt-5-5-high","name":"GPT-5.5 (High)","source_name":"GPT-5.5 (High)","base":"GPT-5.5","variant":"High","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":92.5,"rank":10,"coverage":0.75,"categories":{"coding":92.3,"reasoning":94.7,"math":91.1,"chat":92.8,"instructions":95}},"arena":{"text":{"rank":31,"date":"2026-10-28","rating":1471.6,"lo":1467.9,"hi":1475.3,"votes":69377,"pct":92.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":25,"date":"2026-10-19","rating":1293.1,"lo":1287.3,"hi":1299,"votes":27067,"pct":85.5,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1494.4,"rank":33,"pct":92.3,"board_size":414},"math":{"rating":1478.4,"rank":37,"pct":91.1,"board_size":405},"creative_writing":{"rating":1455.1,"rank":30,"pct":93,"board_size":417},"instruction_following":{"rating":1478.6,"rank":22,"pct":95,"board_size":419},"hard_prompts":{"rating":1488.9,"rank":23,"pct":94.7,"board_size":419},"multi_turn":{"rating":1475.9,"rank":29,"pct":93.3,"board_size":417},"longer_query":{"rating":1484.2,"rank":20,"pct":95.2,"board_size":397},"non_english":{"rating":1467.2,"rank":26,"pct":94,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/gpt-5.5","input_per_m":5,"output_per_m":30,"blended_per_m":11.25,"context_length":1050000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-5-high"},{"slug":"qwen3-5-max-preview","name":"Qwen3.5 Max Preview","source_name":"Qwen3.5-Max-Preview","base":"Qwen3.5 Max Preview","variant":null,"org":"alibaba","open_weights":false,"model_license":"Proprietary","siscope":{"score":90.5,"rank":17,"coverage":0.75,"categories":{"coding":89.6,"reasoning":91.9,"math":89.9,"chat":92.6,"instructions":91.9}},"arena":{"text":{"rank":32,"date":"2026-10-28","rating":1470.4,"lo":1465.5,"hi":1475.2,"votes":22582,"pct":92.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1486.8,"rank":44,"pct":89.6,"board_size":414},"math":{"rating":1474,"rank":42,"pct":89.9,"board_size":405},"creative_writing":{"rating":1463.7,"rank":24,"pct":94.5,"board_size":417},"instruction_following":{"rating":1466.8,"rank":35,"pct":91.9,"board_size":419},"hard_prompts":{"rating":1482.7,"rank":35,"pct":91.9,"board_size":419},"multi_turn":{"rating":1477.8,"rank":26,"pct":94,"board_size":417},"longer_query":{"rating":1476.4,"rank":36,"pct":91.2,"board_size":397},"non_english":{"rating":1465.4,"rank":28,"pct":93.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen3-5-max-preview"},{"slug":"glm-5-2-max","name":"GLM-5.2 (Max)","source_name":"GLM-5.2 (Max)","base":"GLM-5.2","variant":"Max","org":"zai","open_weights":true,"model_license":"MIT","siscope":{"score":74.9,"rank":64,"coverage":1,"categories":{"coding":85.5,"agents":55.4,"reasoning":73.3,"math":75,"chat":92.3,"instructions":91.4}},"arena":{"text":{"rank":33,"date":"2026-10-28","rating":1469.6,"lo":1465.6,"hi":1473.7,"votes":53702,"pct":92.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":33,"date":"2026-10-28","rating":1605.6,"lo":1599.7,"hi":1611.5,"votes":17817,"pct":78.8,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":26,"date":"2026-11-02","score":0.0075,"lo":-0.0002,"hi":0.0151,"sessions":99064,"cost_per_task_p50":1.09,"pct":55.4,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1486.8,"rank":43,"pct":89.6,"board_size":414},"math":{"rating":1483.7,"rank":31,"pct":92.6,"board_size":405},"creative_writing":{"rating":1460.9,"rank":25,"pct":94.2,"board_size":417},"instruction_following":{"rating":1465.6,"rank":37,"pct":91.4,"board_size":419},"hard_prompts":{"rating":1480.6,"rank":39,"pct":90.9,"board_size":419},"multi_turn":{"rating":1469,"rank":39,"pct":90.9,"board_size":417},"longer_query":{"rating":1479,"rank":31,"pct":92.4,"board_size":397},"non_english":{"rating":1458.2,"rank":34,"pct":91.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9186,"stderr":0.0161,"tested_as":"glm-5.2_max","approx":false,"run_date":"2026-06-24","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Fc5kpB4axzmygRywWqBKFmv.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":90.7,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.342,"stderr":0.015,"tested_as":"glm-5.2_max","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FWgjFZzojpiv54XqUhvfuUG.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":38.4,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.8639,"stderr":0.0422,"tested_as":"glm-5.2_max","approx":false,"run_date":"2026-06-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FXjFqou6MyT2XLpkUsCrgxM.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":67,"tested_models":313},{"benchmark":"frontiermath","score":0.5921,"stderr":0.0296,"tested_as":"glm-5.2_max","approx":false,"run_date":"2026-06-19","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":65.3,"tested_models":122},{"benchmark":"swe_bench_verified","score":0.787,"stderr":0.0187,"tested_as":"glm-5.2_max","approx":false,"run_date":"2026-06-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F4AfhcmYVNrw6gM5u8CQsyy.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":88.2,"tested_models":35}],"price":{"openrouter_id":"z-ai/glm-5.2","input_per_m":0.006,"output_per_m":6.8,"blended_per_m":1.7045,"context_length":1048576,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/glm-5-2-max"},{"slug":"gpt-5-4-high","name":"GPT-5.4 (High)","source_name":"GPT-5.4 (High)","base":"GPT-5.4","variant":"High","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":88.3,"rank":23,"coverage":0.75,"categories":{"coding":86.1,"reasoning":88.7,"math":91.1,"chat":92.1,"instructions":92.8}},"arena":{"text":{"rank":34,"date":"2026-10-28","rating":1469.1,"lo":1465.3,"hi":1472.8,"votes":64748,"pct":92.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":18,"date":"2026-10-19","rating":1302.6,"lo":1296.9,"hi":1308.3,"votes":30747,"pct":89.8,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1496.5,"rank":31,"pct":92.7,"board_size":414},"math":{"rating":1487.5,"rank":23,"pct":94.6,"board_size":405},"creative_writing":{"rating":1438.6,"rank":47,"pct":88.9,"board_size":417},"instruction_following":{"rating":1469.3,"rank":31,"pct":92.8,"board_size":419},"hard_prompts":{"rating":1485,"rank":30,"pct":93.1,"board_size":419},"multi_turn":{"rating":1481.8,"rank":22,"pct":95,"board_size":417},"longer_query":{"rating":1473.2,"rank":42,"pct":89.6,"board_size":397},"non_english":{"rating":1465.1,"rank":29,"pct":93.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.899,"stderr":0.0215,"tested_as":"gpt-5.4-2026-03-05_high","approx":false,"run_date":"2026-07-15","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FFbhcT8NnJUntcyNGubJXY6.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":84.3,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.9778,"stderr":0.0222,"tested_as":"gpt-5.4-2026-03-05_high","approx":false,"run_date":"2026-07-15","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FDpPahiEawokzgidE3cNZbS.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":87.5,"tested_models":313},{"benchmark":"swe_bench_verified","score":0.7686,"stderr":0.0192,"tested_as":"gpt-5.4-2026-03-05_high","approx":false,"run_date":"2026-03-06","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Fi9HTMbAxcwsrTf2w2FuJ6N.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":79.4,"tested_models":35}],"price":{"openrouter_id":"openai/gpt-5.4","input_per_m":2.5,"output_per_m":15,"blended_per_m":5.625,"context_length":1050000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-4-high"},{"slug":"ernie-5-1","name":"ERNIE 5.1","source_name":"ERNIE 5.1","base":"ERNIE 5.1","variant":null,"org":"baidu","open_weights":false,"model_license":"Proprietary","siscope":{"score":91,"rank":15,"coverage":0.75,"categories":{"coding":90.6,"reasoning":90.9,"math":92.1,"chat":91.9,"instructions":90.4}},"arena":{"text":{"rank":35,"date":"2026-10-28","rating":1467.8,"lo":1463.3,"hi":1472.3,"votes":39469,"pct":91.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1487.6,"rank":40,"pct":90.6,"board_size":414},"math":{"rating":1481.6,"rank":33,"pct":92.1,"board_size":405},"creative_writing":{"rating":1440.8,"rank":45,"pct":89.4,"board_size":417},"instruction_following":{"rating":1460.3,"rank":41,"pct":90.4,"board_size":419},"hard_prompts":{"rating":1480.6,"rank":38,"pct":90.9,"board_size":419},"multi_turn":{"rating":1470.3,"rank":37,"pct":91.3,"board_size":417},"longer_query":{"rating":1461.7,"rank":50,"pct":87.4,"board_size":397},"non_english":{"rating":1454.2,"rank":37,"pct":91.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/ernie-5-1"},{"slug":"gpt-5-5","name":"GPT-5.5","source_name":"GPT-5.5","base":"GPT-5.5","variant":null,"org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":77.1,"rank":56,"coverage":0.75,"categories":{"coding":87.4,"reasoning":73.4,"math":66.9,"chat":91.6,"instructions":93.5}},"arena":{"text":{"rank":36,"date":"2026-10-28","rating":1466.8,"lo":1463.1,"hi":1470.4,"votes":70949,"pct":91.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":21,"date":"2026-10-19","rating":1297,"lo":1291.2,"hi":1302.7,"votes":28781,"pct":88,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1483,"rank":53,"pct":87.4,"board_size":414},"math":{"rating":1486.9,"rank":24,"pct":94.3,"board_size":405},"creative_writing":{"rating":1452.4,"rank":34,"pct":92.1,"board_size":417},"instruction_following":{"rating":1475.1,"rank":28,"pct":93.5,"board_size":419},"hard_prompts":{"rating":1485.8,"rank":27,"pct":93.8,"board_size":419},"multi_turn":{"rating":1472.3,"rank":34,"pct":92.1,"board_size":417},"longer_query":{"rating":1482.3,"rank":25,"pct":93.9,"board_size":397},"non_english":{"rating":1459.7,"rank":32,"pct":92.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.7727,"stderr":0.0299,"tested_as":"gpt-5.5_none","approx":false,"run_date":"2026-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FKesKa5EXtFG7H4UMBFzgCh.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":53,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.5778,"stderr":0.0745,"tested_as":"gpt-5.5_none","approx":false,"run_date":"2026-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FQuqPmMUTbiEsUvoFYZx5Mk.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":39.4,"tested_models":313}],"price":{"openrouter_id":"openai/gpt-5.5","input_per_m":5,"output_per_m":30,"blended_per_m":11.25,"context_length":1050000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-5"},{"slug":"gemini-3-flash","name":"Gemini 3 Flash","source_name":"Gemini 3 Flash","base":"Gemini 3 Flash","variant":null,"org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":75.8,"rank":61,"coverage":0.75,"categories":{"coding":62.9,"reasoning":88,"math":89.4,"chat":91.4,"instructions":84.7}},"arena":{"text":{"rank":37,"date":"2026-10-28","rating":1465.7,"lo":1461.4,"hi":1470,"votes":31301,"pct":91.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":82,"date":"2026-10-28","rating":1440.1,"lo":1431.5,"hi":1448.7,"votes":10845,"pct":46.4,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":32,"date":"2026-10-19","rating":1284.9,"lo":1279.8,"hi":1290.1,"votes":39131,"pct":81.3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1459.5,"rank":86,"pct":79.4,"board_size":414},"math":{"rating":1472.9,"rank":43,"pct":89.4,"board_size":405},"creative_writing":{"rating":1456.5,"rank":29,"pct":93.3,"board_size":417},"instruction_following":{"rating":1436.5,"rank":65,"pct":84.7,"board_size":419},"hard_prompts":{"rating":1464.4,"rank":51,"pct":88,"board_size":419},"multi_turn":{"rating":1471.1,"rank":35,"pct":91.6,"board_size":417},"longer_query":{"rating":1451.5,"rank":63,"pct":84.3,"board_size":397},"non_english":{"rating":1458.2,"rank":35,"pct":91.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemini-3-flash"},{"slug":"deepseek-v4-1-flash-20260910-max","name":"DeepSeek V4.1 Flash (Max, 2026-09-10)","source_name":"DeepSeek-V4.1-Flash-20260910 (Max)","base":"DeepSeek V4.1 Flash","variant":"Max, 2026-09-10","org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":89.9,"rank":20,"coverage":0.75,"categories":{"coding":88,"reasoning":92.1,"math":91.8,"chat":91.1,"instructions":93.3}},"arena":{"text":{"rank":38,"date":"2026-10-28","rating":1464.5,"lo":1458.4,"hi":1470.6,"votes":13657,"pct":91.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":29,"date":"2026-10-28","rating":1619.2,"lo":1608.2,"hi":1630.1,"votes":3510,"pct":81.5,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":38,"date":"2026-10-19","rating":1277.9,"lo":1267.6,"hi":1288.1,"votes":4100,"pct":77.7,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1501.3,"rank":23,"pct":94.4,"board_size":414},"math":{"rating":1481.4,"rank":34,"pct":91.8,"board_size":405},"creative_writing":{"rating":1437.3,"rank":52,"pct":87.7,"board_size":417},"instruction_following":{"rating":1473.8,"rank":29,"pct":93.3,"board_size":419},"hard_prompts":{"rating":1482.8,"rank":34,"pct":92.1,"board_size":419},"multi_turn":{"rating":1460.3,"rank":48,"pct":88.7,"board_size":417},"longer_query":{"rating":1473.9,"rank":40,"pct":90.2,"board_size":397},"non_english":{"rating":1449.9,"rank":41,"pct":90.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/deepseek-v4-1-flash-20260910-max"},{"slug":"mimo-v2-5-pro","name":"MiMo-V2.5-Pro","source_name":"MiMo-V2.5-Pro","base":"MiMo-V2.5-Pro","variant":null,"org":"xiaomi","open_weights":true,"model_license":"MIT","siscope":{"score":68.2,"rank":92,"coverage":1,"categories":{"coding":73.7,"agents":14.3,"reasoning":93.8,"math":91.3,"chat":90.9,"instructions":93.8}},"arena":{"text":{"rank":39,"date":"2026-10-28","rating":1464.2,"lo":1460.7,"hi":1467.7,"votes":77728,"pct":90.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":72,"date":"2026-10-28","rating":1480.4,"lo":1475.2,"hi":1485.7,"votes":22604,"pct":53,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":49,"date":"2026-11-02","score":-0.0901,"lo":-0.1003,"hi":-0.08,"sessions":49647,"cost_per_task_p50":0.077,"pct":14.3,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1501.3,"rank":24,"pct":94.4,"board_size":414},"math":{"rating":1480.8,"rank":36,"pct":91.3,"board_size":405},"creative_writing":{"rating":1437.8,"rank":51,"pct":88,"board_size":417},"instruction_following":{"rating":1475.4,"rank":27,"pct":93.8,"board_size":419},"hard_prompts":{"rating":1485.8,"rank":26,"pct":93.8,"board_size":419},"multi_turn":{"rating":1475.5,"rank":31,"pct":92.8,"board_size":417},"longer_query":{"rating":1481.1,"rank":28,"pct":93.2,"board_size":397},"non_english":{"rating":1448.4,"rank":43,"pct":90,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"xiaomi/mimo-v2.5-pro","input_per_m":0.48,"output_per_m":1.8,"blended_per_m":0.81,"context_length":1050000,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/mimo-v2-5-pro"},{"slug":"glm-5-1","name":"GLM-5.1","source_name":"GLM-5.1","base":"GLM-5.1","variant":null,"org":"zai","open_weights":true,"model_license":"MIT","siscope":{"score":71.6,"rank":75,"coverage":0.75,"categories":{"coding":67,"reasoning":70.3,"math":70.4,"chat":90.7,"instructions":88}},"arena":{"text":{"rank":40,"date":"2026-10-28","rating":1462.8,"lo":1459.3,"hi":1466.3,"votes":66771,"pct":90.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":63,"date":"2026-10-28","rating":1507.9,"lo":1501.1,"hi":1514.6,"votes":10647,"pct":58.9,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1485.9,"rank":46,"pct":89.1,"board_size":414},"math":{"rating":1472.9,"rank":44,"pct":89.4,"board_size":405},"creative_writing":{"rating":1452.5,"rank":33,"pct":92.3,"board_size":417},"instruction_following":{"rating":1452.5,"rank":51,"pct":88,"board_size":419},"hard_prompts":{"rating":1473,"rank":46,"pct":89.2,"board_size":419},"multi_turn":{"rating":1472.4,"rank":32,"pct":92.3,"board_size":417},"longer_query":{"rating":1467.2,"rank":45,"pct":88.9,"board_size":397},"non_english":{"rating":1448.6,"rank":42,"pct":90.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.899,"stderr":0.0215,"tested_as":"glm-5.1","approx":false,"run_date":"2026-08-10","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FCBbeMKRRSeRsXnvSfn7Png.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":84.3,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.34,"stderr":0.015,"tested_as":"glm-5.1","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FR2fMFAtRXah864hMifdQGV.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":37.4,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9333,"stderr":0.0376,"tested_as":"glm-5.1","approx":false,"run_date":"2026-08-10","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Fb7Lw9ExxAhVY3hdExoh4MP.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":77.2,"tested_models":313},{"benchmark":"frontiermath","score":0.3684,"stderr":0.0286,"tested_as":"glm-5.1","approx":false,"run_date":"2026-08-29","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FMhwme9odWJMzMjoYkW8r6B.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":44.6,"tested_models":122},{"benchmark":"swe_bench_verified","score":0.7417,"stderr":0.0199,"tested_as":"glm-5.1","approx":false,"run_date":"2026-05-15","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":52.9,"tested_models":35}],"price":{"openrouter_id":"z-ai/glm-5.1","input_per_m":1.4,"output_per_m":4.4,"blended_per_m":2.15,"context_length":204800,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/glm-5-1"},{"slug":"claude-opus-4-8-high","name":"Claude Opus 4.8 (High)","source_name":"Claude Opus 4.8 (High)","base":"Claude Opus 4.8","variant":"High","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":86.8,"rank":26,"coverage":0.75,"categories":{"coding":81.5,"reasoning":91.6,"math":93.1,"chat":90.4,"instructions":94.3}},"arena":{"text":{"rank":41,"date":"2026-10-28","rating":1461.3,"lo":1457.4,"hi":1465.2,"votes":63994,"pct":90.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":44,"date":"2026-10-28","rating":1555.8,"lo":1550.1,"hi":1561.6,"votes":18408,"pct":71.5,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":23,"date":"2026-10-19","rating":1294.5,"lo":1288,"hi":1300.9,"votes":18303,"pct":86.7,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1491,"rank":36,"pct":91.5,"board_size":414},"math":{"rating":1485.3,"rank":29,"pct":93.1,"board_size":405},"creative_writing":{"rating":1454.6,"rank":31,"pct":92.8,"board_size":417},"instruction_following":{"rating":1477,"rank":25,"pct":94.3,"board_size":419},"hard_prompts":{"rating":1482.2,"rank":36,"pct":91.6,"board_size":419},"multi_turn":{"rating":1475.7,"rank":30,"pct":93,"board_size":417},"longer_query":{"rating":1484.1,"rank":21,"pct":94.9,"board_size":397},"non_english":{"rating":1450.4,"rank":39,"pct":90.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"anthropic/claude-opus-4.8","input_per_m":5,"output_per_m":25,"blended_per_m":10,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-opus-4-8-high"},{"slug":"claude-sonnet-4-6","name":"Claude Sonnet 4.6","source_name":"Claude Sonnet 4.6","base":"Claude Sonnet 4.6","variant":null,"org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":81.3,"rank":39,"coverage":0.75,"categories":{"coding":72.4,"reasoning":92.6,"math":85.6,"chat":90,"instructions":94}},"arena":{"text":{"rank":42,"date":"2026-10-28","rating":1457.7,"lo":1454.2,"hi":1461.2,"votes":70916,"pct":90,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":56,"date":"2026-10-28","rating":1522.7,"lo":1517.5,"hi":1527.8,"votes":22733,"pct":63.6,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":33,"date":"2026-10-19","rating":1282.8,"lo":1276.7,"hi":1288.9,"votes":27408,"pct":80.7,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1503.2,"rank":21,"pct":94.9,"board_size":414},"math":{"rating":1462.4,"rank":59,"pct":85.6,"board_size":405},"creative_writing":{"rating":1435.4,"rank":56,"pct":86.5,"board_size":417},"instruction_following":{"rating":1475.7,"rank":26,"pct":94,"board_size":419},"hard_prompts":{"rating":1484.3,"rank":32,"pct":92.6,"board_size":419},"multi_turn":{"rating":1463.2,"rank":46,"pct":89.2,"board_size":417},"longer_query":{"rating":1478.7,"rank":33,"pct":91.9,"board_size":397},"non_english":{"rating":1439.8,"rank":52,"pct":87.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"swe_bench_verified","score":0.7521,"stderr":0.0196,"tested_as":"claude-sonnet-4-6","approx":false,"run_date":"2026-02-21","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FKEdgiMmtJKHxgGiS82agYj.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":58.8,"tested_models":35}],"price":{"openrouter_id":"anthropic/claude-sonnet-4.6","input_per_m":3,"output_per_m":15,"blended_per_m":6,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-sonnet-4-6"},{"slug":"gemini-2-5-pro","name":"Gemini 2.5 Pro","source_name":"Gemini 2.5 Pro","base":"Gemini 2.5 Pro","variant":null,"org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":51.8,"rank":170,"coverage":0.75,"categories":{"coding":28.7,"reasoning":76.9,"math":59.3,"chat":90,"instructions":84.9}},"arena":{"text":{"rank":43,"date":"2026-10-28","rating":1457.7,"lo":1455.3,"hi":1460.1,"votes":125307,"pct":90,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":145,"date":"2026-10-28","rating":1226.1,"lo":1210.2,"hi":1242,"votes":2724,"pct":4.6,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":51,"date":"2026-10-19","rating":1263.3,"lo":1258.8,"hi":1267.9,"votes":88755,"pct":69.9,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1451.5,"rank":102,"pct":75.5,"board_size":414},"math":{"rating":1449.7,"rank":72,"pct":82.4,"board_size":405},"creative_writing":{"rating":1453.8,"rank":32,"pct":92.5,"board_size":417},"instruction_following":{"rating":1436.6,"rank":64,"pct":84.9,"board_size":419},"hard_prompts":{"rating":1454.7,"rank":66,"pct":84.4,"board_size":419},"multi_turn":{"rating":1452.5,"rank":64,"pct":84.9,"board_size":417},"longer_query":{"rating":1449.1,"rank":65,"pct":83.8,"board_size":397},"non_english":{"rating":1451.4,"rank":38,"pct":91.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8529,"stderr":0.0212,"tested_as":"gemini-2.5-pro","approx":false,"run_date":"2025-11-16","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FcqUZ6gcq2HBnShFRWvKjGr.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":69.3,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.8472,"stderr":0.0481,"tested_as":"gemini-2.5-pro","approx":false,"run_date":"2025-11-16","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FiJp7PgYZa3PiXAV8UWd7MC.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":65.7,"tested_models":313},{"benchmark":"frontiermath","score":0.2456,"stderr":0.0255,"tested_as":"gemini-2.5-pro","approx":false,"run_date":"2026-06-11","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FFkywQ2KS4AkLPzjSPmhHcS.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":29.8,"tested_models":122},{"benchmark":"swe_bench_verified","score":0.5756,"stderr":0.0225,"tested_as":"gemini-2.5-pro","approx":false,"run_date":"2026-02-13","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FKL724uHFGbiXj4o5PHyLn2.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":5.9,"tested_models":35}],"price":{"openrouter_id":"google/gemini-2.5-pro","input_per_m":1.25,"output_per_m":10,"blended_per_m":3.4375,"context_length":1048576,"modalities_in":["text","image","file","audio","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gemini-2-5-pro"},{"slug":"gpt-5-6-sol-xhigh","name":"GPT-5.6 Sol (xHigh)","source_name":"GPT-5.6 Sol (xHigh)","base":"GPT-5.6 Sol","variant":"xHigh","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":87.9,"rank":25,"coverage":1,"categories":{"coding":92.5,"agents":76.8,"reasoning":92.3,"math":89.1,"chat":89.7,"instructions":95.9}},"arena":{"text":{"rank":44,"date":"2026-10-28","rating":1457.2,"lo":1453,"hi":1461.5,"votes":43796,"pct":89.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":35,"date":"2026-10-19","rating":1280.6,"lo":1273.3,"hi":1287.9,"votes":11439,"pct":79.5,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":14,"date":"2026-11-02","score":0.0456,"lo":0.0352,"hi":0.056,"sessions":45407,"cost_per_task_p50":1.729,"pct":76.8,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1495.2,"rank":32,"pct":92.5,"board_size":414},"math":{"rating":1472.1,"rank":45,"pct":89.1,"board_size":405},"creative_writing":{"rating":1450.3,"rank":35,"pct":91.8,"board_size":417},"instruction_following":{"rating":1482.8,"rank":18,"pct":95.9,"board_size":419},"hard_prompts":{"rating":1483.1,"rank":33,"pct":92.3,"board_size":419},"multi_turn":{"rating":1461.2,"rank":47,"pct":88.9,"board_size":417},"longer_query":{"rating":1480,"rank":30,"pct":92.7,"board_size":397},"non_english":{"rating":1450.4,"rank":40,"pct":90.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/gpt-5.6-sol","input_per_m":4,"output_per_m":20,"blended_per_m":8,"context_length":1050000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-6-sol-xhigh"},{"slug":"kimi-k2-6","name":"Kimi K2.6","source_name":"Kimi K2.6","base":"Kimi K2.6","variant":null,"org":"moonshot","open_weights":true,"model_license":"Modified MIT","siscope":{"score":76.3,"rank":57,"coverage":0.75,"categories":{"coding":73.8,"reasoning":72.7,"math":78.9,"chat":89.5,"instructions":87.8}},"arena":{"text":{"rank":45,"date":"2026-10-28","rating":1455.6,"lo":1451.1,"hi":1460,"votes":39978,"pct":89.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":62,"date":"2026-10-28","rating":1509.2,"lo":1502,"hi":1516.5,"votes":10119,"pct":59.6,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":34,"date":"2026-10-19","rating":1282.1,"lo":1275.3,"hi":1288.9,"votes":16368,"pct":80.1,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1489,"rank":37,"pct":91.3,"board_size":414},"math":{"rating":1474.2,"rank":41,"pct":90.1,"board_size":405},"creative_writing":{"rating":1432.8,"rank":59,"pct":86.1,"board_size":417},"instruction_following":{"rating":1450.9,"rank":52,"pct":87.8,"board_size":419},"hard_prompts":{"rating":1470.5,"rank":47,"pct":89,"board_size":419},"multi_turn":{"rating":1453.2,"rank":62,"pct":85.3,"board_size":417},"longer_query":{"rating":1468.3,"rank":44,"pct":89.1,"board_size":397},"non_english":{"rating":1446.3,"rank":45,"pct":89.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9078,"stderr":0.0172,"tested_as":"kimi-k2.6","approx":false,"run_date":"2026-05-01","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FLjgJoDosTLkiGVT59smA7q.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":87.7,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.349,"stderr":0.0151,"tested_as":"kimi-k2.6","approx":false,"run_date":"2026-08-10","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":41.4,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9611,"stderr":0.0238,"tested_as":"kimi-k2.6","approx":false,"run_date":"2026-05-02","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FBTeRdhgt6TFBj6QkGX2j6P.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":85.3,"tested_models":313},{"benchmark":"frontiermath","score":0.5719,"stderr":0.0294,"tested_as":"kimi-k2.6","approx":false,"run_date":"2026-06-10","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FBxrNfyMffkVUq4n7U5eK3Q.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":61.2,"tested_models":122},{"benchmark":"swe_bench_verified","score":0.7665,"stderr":0.0192,"tested_as":"kimi-k2.6","approx":false,"run_date":"2026-05-08","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FbUPtAK7spEwvmiC8pi6afc.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":70.6,"tested_models":35}],"price":{"openrouter_id":"moonshotai/kimi-k2.6","input_per_m":0.65,"output_per_m":3.41,"blended_per_m":1.34,"context_length":262144,"modalities_in":["text","image"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/kimi-k2-6"},{"slug":"qwen3-7-plus","name":"Qwen3.7-Plus","source_name":"Qwen3.7-Plus","base":"Qwen3.7-Plus","variant":null,"org":"alibaba","open_weights":false,"model_license":"Proprietary","siscope":{"score":66.2,"rank":101,"coverage":1,"categories":{"coding":84.5,"agents":21.4,"reasoning":81.2,"math":68.5,"chat":89.2,"instructions":85.6}},"arena":{"text":{"rank":46,"date":"2026-10-28","rating":1454.6,"lo":1450.2,"hi":1458.9,"votes":42011,"pct":89.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":37,"date":"2026-10-19","rating":1278.1,"lo":1271.5,"hi":1284.8,"votes":14212,"pct":78.3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":45,"date":"2026-11-02","score":-0.0737,"lo":-0.0898,"hi":-0.0575,"sessions":24493,"cost_per_task_p50":0.141,"pct":21.4,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1472.5,"rank":65,"pct":84.5,"board_size":414},"math":{"rating":1467.4,"rank":53,"pct":87.1,"board_size":405},"creative_writing":{"rating":1437.8,"rank":49,"pct":88,"board_size":417},"instruction_following":{"rating":1439.6,"rank":61,"pct":85.6,"board_size":419},"hard_prompts":{"rating":1459.5,"rank":59,"pct":86.1,"board_size":419},"multi_turn":{"rating":1459.3,"rank":50,"pct":88.2,"board_size":417},"longer_query":{"rating":1454,"rank":60,"pct":85.1,"board_size":397},"non_english":{"rating":1444.7,"rank":46,"pct":89.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8788,"stderr":0.0233,"tested_as":"qwen3.7-plus","approx":false,"run_date":"2026-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FURoWjw9Htc6QPwABVcrybw.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":76.2,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.9333,"stderr":0.0376,"tested_as":"qwen3.7-plus","approx":false,"run_date":"2026-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FJvdw6GAXiS6T79bkpbk6Ra.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":77.2,"tested_models":313},{"benchmark":"frontiermath","score":0.3439,"stderr":0.0282,"tested_as":"qwen3.7-plus_none","approx":false,"run_date":"2026-08-29","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FTt8tBXHoCEYqGLePWXkM8u.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":41.3,"tested_models":122}],"price":{"openrouter_id":"qwen/qwen3.7-plus","input_per_m":0.32,"output_per_m":1.28,"blended_per_m":0.56,"context_length":1000000,"modalities_in":["text","image"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/qwen3-7-plus"},{"slug":"claude-opus-4-8","name":"Claude Opus 4.8","source_name":"Claude Opus 4.8","base":"Claude Opus 4.8","variant":null,"org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":79.4,"rank":47,"coverage":0.75,"categories":{"coding":77.9,"reasoning":79.8,"math":76.4,"chat":89,"instructions":90.7}},"arena":{"text":{"rank":47,"date":"2026-10-28","rating":1454,"lo":1450.2,"hi":1457.9,"votes":65121,"pct":89,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":53,"date":"2026-10-28","rating":1536,"lo":1530.3,"hi":1541.7,"votes":17323,"pct":65.6,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":28,"date":"2026-10-19","rating":1288.5,"lo":1282,"hi":1295,"votes":18800,"pct":83.7,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1487.5,"rank":42,"pct":90.1,"board_size":414},"math":{"rating":1470.5,"rank":46,"pct":88.9,"board_size":405},"creative_writing":{"rating":1446.7,"rank":36,"pct":91.6,"board_size":417},"instruction_following":{"rating":1463,"rank":40,"pct":90.7,"board_size":419},"hard_prompts":{"rating":1474.1,"rank":43,"pct":90,"board_size":419},"multi_turn":{"rating":1472.4,"rank":33,"pct":92.3,"board_size":417},"longer_query":{"rating":1480.1,"rank":29,"pct":92.9,"board_size":397},"non_english":{"rating":1444.4,"rank":47,"pct":89,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8535,"stderr":0.0252,"tested_as":"claude-opus-4-8_none","approx":false,"run_date":"2026-08-06","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FckbZdkrXPwbFdjn6bmUQsi.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":69.6,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.8444,"stderr":0.0546,"tested_as":"claude-opus-4-8_none","approx":false,"run_date":"2026-08-06","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FadGE8rXdNuUFs96ioppbc5.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":63.8,"tested_models":313}],"price":{"openrouter_id":"anthropic/claude-opus-4.8","input_per_m":5,"output_per_m":25,"blended_per_m":10,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-opus-4-8"},{"slug":"gpt-5-4","name":"GPT-5.4","source_name":"GPT-5.4","base":"GPT-5.4","variant":null,"org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":66.7,"rank":98,"coverage":0.75,"categories":{"coding":60.9,"reasoning":68.1,"math":61.9,"chat":88.8,"instructions":89}},"arena":{"text":{"rank":48,"date":"2026-10-28","rating":1452.5,"lo":1448.8,"hi":1456.1,"votes":67856,"pct":88.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":98,"date":"2026-10-28","rating":1401.1,"lo":1391.1,"hi":1411,"votes":4499,"pct":35.8,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":27,"date":"2026-10-19","rating":1292,"lo":1285.6,"hi":1298.5,"votes":22804,"pct":84.3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1478.4,"rank":59,"pct":86,"board_size":414},"math":{"rating":1457.8,"rank":64,"pct":84.4,"board_size":405},"creative_writing":{"rating":1427.5,"rank":61,"pct":85.6,"board_size":417},"instruction_following":{"rating":1454.9,"rank":47,"pct":89,"board_size":419},"hard_prompts":{"rating":1468.7,"rank":49,"pct":88.5,"board_size":419},"multi_turn":{"rating":1463.3,"rank":45,"pct":89.4,"board_size":417},"longer_query":{"rating":1464,"rank":46,"pct":88.6,"board_size":397},"non_english":{"rating":1448,"rank":44,"pct":89.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.7475,"stderr":0.031,"tested_as":"gpt-5.4-2026-03-05_none","approx":false,"run_date":"2026-07-15","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FLaBuzZExRqocD4FET6yx26.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":47.6,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.5778,"stderr":0.0745,"tested_as":"gpt-5.4-2026-03-05_none","approx":false,"run_date":"2026-07-15","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Ffjxs2EWts9GjpuBtFD5BN3.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":39.4,"tested_models":313}],"price":{"openrouter_id":"openai/gpt-5.4","input_per_m":2.5,"output_per_m":15,"blended_per_m":5.625,"context_length":1050000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-4"},{"slug":"mimo-v2-6-flash","name":"MiMo-V2.6-Flash","source_name":"MiMo-V2.6-Flash","base":"MiMo-V2.6-Flash","variant":null,"org":"xiaomi","open_weights":true,"model_license":"MIT","siscope":{"score":79.8,"rank":44,"coverage":1,"categories":{"coding":89.9,"agents":51.8,"reasoning":89.7,"math":87.9,"chat":88.5,"instructions":87.6}},"arena":{"text":{"rank":49,"date":"2026-10-28","rating":1451.2,"lo":1445.5,"hi":1457,"votes":15312,"pct":88.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":22,"date":"2026-10-28","rating":1637.2,"lo":1628.7,"hi":1645.6,"votes":7068,"pct":86.1,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":59,"date":"2026-10-19","rating":1255.7,"lo":1244.9,"hi":1266.6,"votes":3618,"pct":65.1,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":28,"date":"2026-11-02","score":0.0043,"lo":-0.0061,"hi":0.0148,"sessions":29722,"cost_per_task_p50":0.071,"pct":51.8,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1498.1,"rank":27,"pct":93.7,"board_size":414},"math":{"rating":1468.5,"rank":50,"pct":87.9,"board_size":405},"creative_writing":{"rating":1404.7,"rank":88,"pct":79.1,"board_size":417},"instruction_following":{"rating":1448.7,"rank":53,"pct":87.6,"board_size":419},"hard_prompts":{"rating":1473.4,"rank":44,"pct":89.7,"board_size":419},"multi_turn":{"rating":1444,"rank":80,"pct":80.8,"board_size":417},"longer_query":{"rating":1459.4,"rank":53,"pct":86.9,"board_size":397},"non_english":{"rating":1431.1,"rank":70,"pct":83.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"xiaomi/mimo-v2.6-flash","input_per_m":0.14,"output_per_m":0.28,"blended_per_m":0.175,"context_length":1050000,"modalities_in":["text","image","video","audio"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/mimo-v2-6-flash"},{"slug":"deepseek-v4-pro","name":"DeepSeek V4 Pro","source_name":"DeepSeek-V4-Pro","base":"DeepSeek V4 Pro","variant":null,"org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":65.1,"rank":110,"coverage":0.75,"categories":{"coding":65.6,"reasoning":65.5,"math":56.2,"chat":88.3,"instructions":86.8}},"arena":{"text":{"rank":50,"date":"2026-10-28","rating":1451.1,"lo":1447.3,"hi":1455,"votes":57572,"pct":88.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":79,"date":"2026-10-28","rating":1447.2,"lo":1440.8,"hi":1453.5,"votes":13931,"pct":48.3,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1469,"rank":72,"pct":82.8,"board_size":414},"math":{"rating":1442.5,"rank":79,"pct":80.7,"board_size":405},"creative_writing":{"rating":1446.3,"rank":38,"pct":91.1,"board_size":417},"instruction_following":{"rating":1445.2,"rank":56,"pct":86.8,"board_size":419},"hard_prompts":{"rating":1461,"rank":58,"pct":86.4,"board_size":419},"multi_turn":{"rating":1467.4,"rank":41,"pct":90.4,"board_size":417},"longer_query":{"rating":1457.4,"rank":55,"pct":86.4,"board_size":397},"non_english":{"rating":1439,"rank":54,"pct":87.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.7323,"stderr":0.0315,"tested_as":"deepseek-v4-pro_none","approx":false,"run_date":"2026-08-06","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FFtGueFbnFnKBAuLmEEufFg.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":44.6,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.4667,"stderr":0.0752,"tested_as":"deepseek-v4-pro_none","approx":false,"run_date":"2026-08-06","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F7bwsMdahVHrkaiN5x49Dk7.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":31.7,"tested_models":313}],"price":null,"url":"https://siscope.app/models/deepseek-v4-pro"},{"slug":"grok-4-20-beta-reasoning-0309","name":"Grok 4.20 Beta (Reasoning, 0309)","source_name":"Grok 4.20 Beta (Reasoning, 0309)","base":"Grok 4.20 Beta","variant":"Reasoning, 0309","org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":68.3,"rank":91,"coverage":0.75,"categories":{"coding":53.1,"reasoning":82.5,"math":83.2,"chat":88,"instructions":79.7}},"arena":{"text":{"rank":51,"date":"2026-10-28","rating":1451,"lo":1447.3,"hi":1454.6,"votes":66422,"pct":88,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":111,"date":"2026-10-28","rating":1375.5,"lo":1369.4,"hi":1381.5,"votes":15404,"pct":27.2,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":55,"date":"2026-10-19","rating":1262.4,"lo":1256.4,"hi":1268.5,"votes":26796,"pct":67.5,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1458.7,"rank":88,"pct":78.9,"board_size":414},"math":{"rating":1455.2,"rank":69,"pct":83.2,"board_size":405},"creative_writing":{"rating":1431.8,"rank":60,"pct":85.8,"board_size":417},"instruction_following":{"rating":1420.5,"rank":86,"pct":79.7,"board_size":419},"hard_prompts":{"rating":1451.5,"rank":74,"pct":82.5,"board_size":419},"multi_turn":{"rating":1455.7,"rank":55,"pct":87,"board_size":417},"longer_query":{"rating":1436.7,"rank":84,"pct":79,"board_size":397},"non_english":{"rating":1440.9,"rank":50,"pct":88.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/grok-4-20-beta-reasoning-0309"},{"slug":"claude-opus-4-5-20251101","name":"Claude Opus 4.5 (2025-11-01)","source_name":"Claude Opus 4.5 (20251101)","base":"Claude Opus 4.5","variant":"2025-11-01","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":70,"rank":84,"coverage":0.75,"categories":{"coding":72.1,"reasoning":74.4,"math":59.2,"chat":87.8,"instructions":93.1}},"arena":{"text":{"rank":52,"date":"2026-10-28","rating":1450.9,"lo":1447.8,"hi":1454,"votes":72825,"pct":87.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":74,"date":"2026-10-28","rating":1469.2,"lo":1462,"hi":1476.4,"votes":13362,"pct":51.7,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1498.2,"rank":26,"pct":93.9,"board_size":414},"math":{"rating":1458.1,"rank":63,"pct":84.7,"board_size":405},"creative_writing":{"rating":1442.7,"rank":40,"pct":90.6,"board_size":417},"instruction_following":{"rating":1472.4,"rank":30,"pct":93.1,"board_size":419},"hard_prompts":{"rating":1476,"rank":41,"pct":90.4,"board_size":419},"multi_turn":{"rating":1466.1,"rank":42,"pct":90.1,"board_size":417},"longer_query":{"rating":1478.9,"rank":32,"pct":92.2,"board_size":397},"non_english":{"rating":1437.5,"rank":56,"pct":86.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8068,"stderr":0.0239,"tested_as":"claude-opus-4-5-20251101","approx":false,"run_date":"2025-11-24","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FmEkZaYpiurQ6TEMAALK3su.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":58.4,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.4806,"stderr":0.0641,"tested_as":"claude-opus-4-5-20251101","approx":false,"run_date":"2025-11-24","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FnSb2focDRMyPJXErk3MV94.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":33.7,"tested_models":313},{"benchmark":"swe_bench_verified","score":0.7665,"stderr":0.0192,"tested_as":"claude-opus-4-5-20251101","approx":false,"run_date":"2026-02-05","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FmKQKxkpGDrFHBPBYR3mBrB.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":70.6,"tested_models":35}],"price":{"openrouter_id":"anthropic/claude-opus-4.5","input_per_m":5,"output_per_m":25,"blended_per_m":10,"context_length":200000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-opus-4-5-20251101"},{"slug":"grok-4-20-multi-agent-beta-0309","name":"Grok 4.20 Multi-Agent Beta (0309)","source_name":"Grok 4.20 Multi-Agent Beta (0309)","base":"Grok 4.20 Multi-Agent Beta","variant":"0309","org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":80.4,"rank":42,"coverage":0.75,"categories":{"coding":78.7,"reasoning":81.8,"math":79.5,"chat":87.6,"instructions":79.4}},"arena":{"text":{"rank":53,"date":"2026-10-28","rating":1450.7,"lo":1447,"hi":1454.3,"votes":64917,"pct":87.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":57,"date":"2026-10-19","rating":1258.8,"lo":1252.7,"hi":1264.9,"votes":24532,"pct":66.3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1457.4,"rank":89,"pct":78.7,"board_size":414},"math":{"rating":1440.6,"rank":84,"pct":79.5,"board_size":405},"creative_writing":{"rating":1436.3,"rank":54,"pct":87.3,"board_size":417},"instruction_following":{"rating":1420.2,"rank":87,"pct":79.4,"board_size":419},"hard_prompts":{"rating":1448.3,"rank":77,"pct":81.8,"board_size":419},"multi_turn":{"rating":1452.1,"rank":65,"pct":84.6,"board_size":417},"longer_query":{"rating":1431,"rank":91,"pct":77.3,"board_size":397},"non_english":{"rating":1440.5,"rank":51,"pct":88,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/grok-4-20-multi-agent-beta-0309"},{"slug":"amazon-nova-experimental-chat-26-02-10","name":"Amazon Nova Experimental Chat (26-02-10)","source_name":"amazon-nova-experimental-chat (26-02-10)","base":"Amazon Nova Experimental Chat","variant":"26-02-10","org":"amazon","open_weights":false,"model_license":"Proprietary","siscope":{"score":83.2,"rank":34,"coverage":0.75,"categories":{"coding":87.7,"reasoning":85.9,"math":78.2,"chat":87.3,"instructions":81.1}},"arena":{"text":{"rank":54,"date":"2026-10-28","rating":1448.7,"lo":1439.1,"hi":1458.3,"votes":3523,"pct":87.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1483.2,"rank":52,"pct":87.7,"board_size":414},"math":{"rating":1437.3,"rank":89,"pct":78.2,"board_size":405},"creative_writing":{"rating":1368.8,"rank":146,"pct":65.1,"board_size":417},"instruction_following":{"rating":1426.9,"rank":80,"pct":81.1,"board_size":419},"hard_prompts":{"rating":1458.7,"rank":60,"pct":85.9,"board_size":419},"multi_turn":{"rating":1441.5,"rank":85,"pct":79.8,"board_size":417},"longer_query":{"rating":1441.3,"rank":77,"pct":80.8,"board_size":397},"non_english":{"rating":1434.6,"rank":63,"pct":85.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/amazon-nova-experimental-chat-26-02-10"},{"slug":"gpt-5-6-terra-xhigh","name":"GPT-5.6 Terra (xHigh)","source_name":"GPT-5.6 Terra (xHigh)","base":"GPT-5.6 Terra","variant":"xHigh","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":77.2,"rank":55,"coverage":1,"categories":{"coding":88.9,"agents":44.6,"reasoning":88.8,"math":86.4,"chat":87.1,"instructions":88.8}},"arena":{"text":{"rank":55,"date":"2026-10-28","rating":1448.3,"lo":1444.2,"hi":1452.4,"votes":48166,"pct":87.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":43,"date":"2026-10-19","rating":1271,"lo":1263.7,"hi":1278.2,"votes":11842,"pct":74.7,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":32,"date":"2026-11-02","score":-0.0151,"lo":-0.0229,"hi":-0.0073,"sessions":44557,"cost_per_task_p50":0.606,"pct":44.6,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1485.5,"rank":47,"pct":88.9,"board_size":414},"math":{"rating":1463.7,"rank":56,"pct":86.4,"board_size":405},"creative_writing":{"rating":1412.7,"rank":79,"pct":81.2,"board_size":417},"instruction_following":{"rating":1454.5,"rank":48,"pct":88.8,"board_size":419},"hard_prompts":{"rating":1469,"rank":48,"pct":88.8,"board_size":419},"multi_turn":{"rating":1454.8,"rank":57,"pct":86.5,"board_size":417},"longer_query":{"rating":1452.9,"rank":61,"pct":84.8,"board_size":397},"non_english":{"rating":1441,"rank":49,"pct":88.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/gpt-5.6-terra","input_per_m":2,"output_per_m":12,"blended_per_m":4.5,"context_length":1050000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-6-terra-xhigh"},{"slug":"claude-opus-4-5-high-32k-20251101","name":"Claude Opus 4.5 (High, 32K, 2025-11-01)","source_name":"Claude Opus 4.5 (High, 32K, 20251101)","base":"Claude Opus 4.5","variant":"High, 32K, 2025-11-01","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":73,"rank":71,"coverage":0.75,"categories":{"coding":76,"reasoning":73.7,"math":64.6,"chat":86.8,"instructions":94.7}},"arena":{"text":{"rank":56,"date":"2026-10-28","rating":1448.2,"lo":1444.4,"hi":1452,"votes":37484,"pct":86.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":66,"date":"2026-10-28","rating":1493.7,"lo":1485.4,"hi":1502,"votes":10981,"pct":57,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1503.2,"rank":22,"pct":94.9,"board_size":414},"math":{"rating":1462.8,"rank":58,"pct":85.9,"board_size":405},"creative_writing":{"rating":1444.9,"rank":39,"pct":90.9,"board_size":417},"instruction_following":{"rating":1478,"rank":23,"pct":94.7,"board_size":419},"hard_prompts":{"rating":1473.3,"rank":45,"pct":89.5,"board_size":419},"multi_turn":{"rating":1460.2,"rank":49,"pct":88.5,"board_size":417},"longer_query":{"rating":1478.2,"rank":34,"pct":91.7,"board_size":397},"non_english":{"rating":1435.3,"rank":60,"pct":85.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8605,"stderr":0.0207,"tested_as":"claude-opus-4-5-20251101_32K","approx":false,"run_date":"2025-11-24","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FKwwo3UFcPDk6iLAeSeeRaa.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":72,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.457,"stderr":0.0158,"tested_as":"claude-opus-4-5-20251101_32K","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FCA5LW4phRnHSsZUGXEm8H6.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":59.6,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.8611,"stderr":0.0426,"tested_as":"claude-opus-4-5-20251101_32K","approx":false,"run_date":"2025-11-24","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FikUWdu6HJ2qRgZynfzDCFe.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":66.7,"tested_models":313},{"benchmark":"frontiermath","score":0.3439,"stderr":0.0282,"tested_as":"claude-opus-4-5-20251101_32K","approx":false,"run_date":"2026-06-11","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FmS5EwCRZVpvUvJEehPUDZu.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":41.3,"tested_models":122}],"price":{"openrouter_id":"anthropic/claude-opus-4.5","input_per_m":5,"output_per_m":25,"blended_per_m":10,"context_length":200000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-opus-4-5-high-32k-20251101"},{"slug":"dola-seed-2-0-pro","name":"Dola Seed 2.0 Pro","source_name":"Dola Seed 2.0 Pro","base":"Dola Seed 2.0 Pro","variant":null,"org":"bytedance","open_weights":false,"model_license":"Proprietary","siscope":{"score":81.1,"rank":41,"coverage":0.75,"categories":{"coding":84,"reasoning":84,"math":78.5,"chat":86.6,"instructions":76.1}},"arena":{"text":{"rank":57,"date":"2026-10-28","rating":1448,"lo":1444.7,"hi":1451.4,"votes":79094,"pct":86.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":40,"date":"2026-10-19","rating":1274.4,"lo":1267.2,"hi":1281.6,"votes":10972,"pct":76.5,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1471.8,"rank":67,"pct":84,"board_size":414},"math":{"rating":1438.8,"rank":88,"pct":78.5,"board_size":405},"creative_writing":{"rating":1406.1,"rank":85,"pct":79.8,"board_size":417},"instruction_following":{"rating":1413.7,"rank":101,"pct":76.1,"board_size":419},"hard_prompts":{"rating":1453.1,"rank":68,"pct":84,"board_size":419},"multi_turn":{"rating":1441,"rank":87,"pct":79.3,"board_size":417},"longer_query":{"rating":1427.3,"rank":98,"pct":75.3,"board_size":397},"non_english":{"rating":1441.3,"rank":48,"pct":88.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/dola-seed-2-0-pro"},{"slug":"grok-4-5","name":"Grok 4.5","source_name":"Grok 4.5","base":"Grok 4.5","variant":null,"org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":81.9,"rank":37,"coverage":0.75,"categories":{"coding":77.6,"reasoning":86.6,"math":85.4,"chat":86.4,"instructions":86.6}},"arena":{"text":{"rank":58,"date":"2026-10-28","rating":1447.6,"lo":1443.3,"hi":1452,"votes":39801,"pct":86.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":46,"date":"2026-10-28","rating":1553,"lo":1546.4,"hi":1559.7,"votes":11018,"pct":70.2,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":31,"date":"2026-10-19","rating":1287.1,"lo":1280.1,"hi":1294.2,"votes":12599,"pct":81.9,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1474,"rank":63,"pct":85,"board_size":414},"math":{"rating":1459,"rank":60,"pct":85.4,"board_size":405},"creative_writing":{"rating":1441.9,"rank":41,"pct":90.4,"board_size":417},"instruction_following":{"rating":1445,"rank":57,"pct":86.6,"board_size":419},"hard_prompts":{"rating":1461.6,"rank":56,"pct":86.6,"board_size":419},"multi_turn":{"rating":1455.8,"rank":54,"pct":87.3,"board_size":417},"longer_query":{"rating":1461.9,"rank":49,"pct":87.9,"board_size":397},"non_english":{"rating":1439.7,"rank":53,"pct":87.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"x-ai/grok-4.5","input_per_m":2,"output_per_m":6,"blended_per_m":3,"context_length":500000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/grok-4-5"},{"slug":"qwen3-6-max-preview","name":"Qwen3.6 Max Preview","source_name":"Qwen3.6-Max-Preview","base":"Qwen3.6 Max Preview","variant":null,"org":"alibaba","open_weights":false,"model_license":"Proprietary","siscope":{"score":75.2,"rank":62,"coverage":0.75,"categories":{"coding":69.2,"reasoning":78.3,"math":80.3,"chat":86.1,"instructions":85.4}},"arena":{"text":{"rank":59,"date":"2026-10-28","rating":1446.7,"lo":1438.6,"hi":1454.9,"votes":5419,"pct":86.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":71,"date":"2026-10-28","rating":1481.8,"lo":1469.3,"hi":1494.3,"votes":2700,"pct":53.6,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1471.1,"rank":69,"pct":83.5,"board_size":414},"math":{"rating":1464.5,"rank":54,"pct":86.9,"board_size":405},"creative_writing":{"rating":1434.7,"rank":58,"pct":86.3,"board_size":417},"instruction_following":{"rating":1439.1,"rank":62,"pct":85.4,"board_size":419},"hard_prompts":{"rating":1456.6,"rank":65,"pct":84.7,"board_size":419},"multi_turn":{"rating":1454.6,"rank":58,"pct":86.3,"board_size":417},"longer_query":{"rating":1457.2,"rank":56,"pct":86.1,"board_size":397},"non_english":{"rating":1436.6,"rank":57,"pct":86.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8737,"stderr":0.0237,"tested_as":"qwen3.6-max-preview","approx":false,"run_date":"2026-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FJv2hJvjpvA8xJW3Bzv7bfw.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":74.4,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.52,"stderr":0.0158,"tested_as":"qwen3.6-max-preview","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FiyPiR8GUuyNNA6Fssziq32.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":75.8,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9111,"stderr":0.0429,"tested_as":"qwen3.6-max-preview","approx":false,"run_date":"2026-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FEfJpx5HztMmL5EQSwsyqMe.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":73.7,"tested_models":313},{"benchmark":"swe_bench_verified","score":0.7665,"stderr":0.0192,"tested_as":"qwen3.6-max-preview","approx":false,"run_date":"2026-05-28","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FFkDMVLdEnJDR5PyUCT6BNQ.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":70.6,"tested_models":35}],"price":null,"url":"https://siscope.app/models/qwen3-6-max-preview"},{"slug":"deepseek-v4-pro-high-20260813","name":"DeepSeek V4 Pro (High, 2026-08-13)","source_name":"DeepSeek-V4-Pro (High, 20260813)","base":"DeepSeek V4 Pro","variant":"High, 2026-08-13","org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":73.3,"rank":70,"coverage":1,"categories":{"coding":78.7,"agents":46.4,"reasoning":85.4,"math":80.2,"chat":85.9,"instructions":87.3}},"arena":{"text":{"rank":60,"date":"2026-10-28","rating":1446,"lo":1439.5,"hi":1452.6,"votes":9787,"pct":85.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":39,"date":"2026-10-28","rating":1581.9,"lo":1572.4,"hi":1591.3,"votes":4676,"pct":74.8,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":31,"date":"2026-11-02","score":-0.003,"lo":-0.02,"hi":0.014,"sessions":7710,"cost_per_task_p50":null,"pct":46.4,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1468.6,"rank":73,"pct":82.6,"board_size":414},"math":{"rating":1441.9,"rank":81,"pct":80.2,"board_size":405},"creative_writing":{"rating":1439.6,"rank":46,"pct":89.2,"board_size":417},"instruction_following":{"rating":1448.6,"rank":54,"pct":87.3,"board_size":419},"hard_prompts":{"rating":1457.9,"rank":62,"pct":85.4,"board_size":419},"multi_turn":{"rating":1454,"rank":60,"pct":85.8,"board_size":417},"longer_query":{"rating":1457.6,"rank":54,"pct":86.6,"board_size":397},"non_english":{"rating":1430.8,"rank":71,"pct":83,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/deepseek-v4-pro-high-20260813"},{"slug":"glm-5","name":"GLM-5","source_name":"GLM-5","base":"GLM-5","variant":null,"org":"zai","open_weights":true,"model_license":"MIT","siscope":{"score":65.2,"rank":109,"coverage":0.75,"categories":{"coding":52.7,"reasoning":79.4,"math":68.8,"chat":85.6,"instructions":81.3}},"arena":{"text":{"rank":61,"date":"2026-10-28","rating":1445.9,"lo":1441.7,"hi":1450.1,"votes":29255,"pct":85.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":87,"date":"2026-10-28","rating":1435.6,"lo":1427.4,"hi":1443.7,"votes":7465,"pct":43,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1460.9,"rank":84,"pct":79.9,"board_size":414},"math":{"rating":1440,"rank":85,"pct":79.2,"board_size":405},"creative_writing":{"rating":1437.8,"rank":50,"pct":88,"board_size":417},"instruction_following":{"rating":1427.8,"rank":79,"pct":81.3,"board_size":419},"hard_prompts":{"rating":1451.6,"rank":73,"pct":82.8,"board_size":419},"multi_turn":{"rating":1456,"rank":53,"pct":87.5,"board_size":417},"longer_query":{"rating":1445.5,"rank":70,"pct":82.6,"board_size":397},"non_english":{"rating":1430.2,"rank":73,"pct":82.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8782,"stderr":0.0234,"tested_as":"glm-5","approx":false,"run_date":"2026-02-12","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Fn4hyz75SVpwPEisKVVjvNg.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":75.9,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.8,"stderr":0.06,"tested_as":"glm-5","approx":false,"run_date":"2026-02-12","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Fccbx7KQY9bTD563vzBXwSg.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":58.3,"tested_models":313},{"benchmark":"swe_bench_verified","score":0.7208,"stderr":0.0209,"tested_as":"glm-5","approx":false,"run_date":"2026-02-15","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FhKkJEu4ueLiNWsTtrJ78PS.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":35.3,"tested_models":35}],"price":{"openrouter_id":"z-ai/glm-5","input_per_m":1,"output_per_m":3.2,"blended_per_m":1.55,"context_length":204800,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/glm-5"},{"slug":"gpt-6-1-sol-max","name":"GPT-6.1 Sol (Max)","source_name":"GPT-6.1 Sol (Max)","base":"GPT-6.1 Sol","variant":"Max","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":92.7,"rank":9,"coverage":1,"categories":{"coding":93.4,"agents":91.1,"reasoning":95,"math":96.3,"chat":85.4,"instructions":92.6}},"arena":{"text":{"rank":62,"date":"2026-10-28","rating":1445.6,"lo":1438.6,"hi":1452.6,"votes":9367,"pct":85.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":5,"date":"2026-10-28","rating":1750.6,"lo":1739.1,"hi":1762,"votes":4092,"pct":97.4,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":29,"date":"2026-10-19","rating":1287.7,"lo":1274.9,"hi":1300.6,"votes":2330,"pct":83.1,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":6,"date":"2026-11-02","score":0.1224,"lo":0.1115,"hi":0.1333,"sessions":29814,"cost_per_task_p50":0.955,"pct":91.1,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1486.2,"rank":45,"pct":89.3,"board_size":414},"math":{"rating":1485.6,"rank":27,"pct":93.6,"board_size":405},"creative_writing":{"rating":1425.2,"rank":65,"pct":84.6,"board_size":417},"instruction_following":{"rating":1467.4,"rank":32,"pct":92.6,"board_size":419},"hard_prompts":{"rating":1467.5,"rank":50,"pct":88.3,"board_size":419},"multi_turn":{"rating":1442,"rank":83,"pct":80.3,"board_size":417},"longer_query":{"rating":1463,"rank":48,"pct":88.1,"board_size":397},"non_english":{"rating":1435.5,"rank":58,"pct":86.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9539,"stderr":0.0138,"tested_as":"gpt-6.1-sol_max","approx":false,"run_date":"2026-09-29","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FLspviLnbeZ82WCngWp6rwR.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":98.8,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.739,"stderr":0.0139,"tested_as":"gpt-6.1-sol_max","approx":false,"run_date":"2026-09-29","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FdfT5VD7cQug8XW6GQHyJUF.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":98,"tested_models":100},{"benchmark":"otis_mock_aime","score":1,"stderr":0,"tested_as":"gpt-6.1-sol_max","approx":false,"run_date":"2026-09-29","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FDi7y6sES4PGQbXNkXYhdqM.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":96.2,"tested_models":313},{"benchmark":"frontiermath","score":0.9368,"stderr":0.0144,"tested_as":"gpt-6.1-sol_max","approx":false,"run_date":"2026-09-29","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":99.2,"tested_models":122}],"price":{"openrouter_id":"openai/gpt-6.1-sol","input_per_m":2,"output_per_m":10,"blended_per_m":4,"context_length":1050000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-6-1-sol-max"},{"slug":"nvidia-nemotron-3-ultra-550b-a55b-nvfp4","name":"Nemotron 3 Ultra 550B A55B (NVFP4)","source_name":"NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)","base":"Nemotron 3 Ultra 550B A55B","variant":"NVFP4","org":"nvidia","open_weights":true,"model_license":"OpenMDW-1.1","siscope":{"score":81.9,"rank":36,"coverage":0.75,"categories":{"coding":82.3,"reasoning":83.7,"math":84.2,"chat":85.2,"instructions":78.2}},"arena":{"text":{"rank":63,"date":"2026-10-28","rating":1445.2,"lo":1438.3,"hi":1452,"votes":11563,"pct":85.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1467.9,"rank":74,"pct":82.3,"board_size":414},"math":{"rating":1457.5,"rank":65,"pct":84.2,"board_size":405},"creative_writing":{"rating":1398.1,"rank":106,"pct":74.8,"board_size":417},"instruction_following":{"rating":1418.2,"rank":92,"pct":78.2,"board_size":419},"hard_prompts":{"rating":1452.4,"rank":69,"pct":83.7,"board_size":419},"multi_turn":{"rating":1411,"rank":136,"pct":67.5,"board_size":417},"longer_query":{"rating":1437.5,"rank":83,"pct":79.3,"board_size":397},"non_english":{"rating":1427.3,"rank":79,"pct":81.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/nvidia-nemotron-3-ultra-550b-a55b-nvfp4"},{"slug":"deepseek-v4-pro-preview-high","name":"DeepSeek-V4-Pro Preview (High)","source_name":"DeepSeek-V4-Pro Preview (High)","base":"DeepSeek-V4-Pro Preview","variant":"High","org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":73.5,"rank":68,"coverage":0.75,"categories":{"coding":63.5,"reasoning":83.3,"math":82.9,"chat":84.7,"instructions":84.4}},"arena":{"text":{"rank":64,"date":"2026-10-28","rating":1444.9,"lo":1441,"hi":1448.9,"votes":54870,"pct":84.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":75,"date":"2026-10-28","rating":1464.2,"lo":1457.9,"hi":1470.5,"votes":13087,"pct":51,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1453.1,"rank":100,"pct":76,"board_size":414},"math":{"rating":1454,"rank":70,"pct":82.9,"board_size":405},"creative_writing":{"rating":1440.9,"rank":44,"pct":89.7,"board_size":417},"instruction_following":{"rating":1435.7,"rank":66,"pct":84.4,"board_size":419},"hard_prompts":{"rating":1452.1,"rank":71,"pct":83.3,"board_size":419},"multi_turn":{"rating":1445.5,"rank":74,"pct":82.5,"board_size":417},"longer_query":{"rating":1445.9,"rank":68,"pct":83.1,"board_size":397},"non_english":{"rating":1431.2,"rank":68,"pct":84,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/deepseek-v4-pro-preview-high"},{"slug":"kimi-k2-5-thinking","name":"Kimi K2.5 (Thinking)","source_name":"Kimi K2.5 (Thinking)","base":"Kimi K2.5","variant":"Thinking","org":"moonshot","open_weights":true,"model_license":"Modified MIT","siscope":{"score":75,"rank":63,"coverage":0.75,"categories":{"coding":64.6,"reasoning":84,"math":88.6,"chat":84.7,"instructions":82.3}},"arena":{"text":{"rank":65,"date":"2026-10-28","rating":1444.9,"lo":1441.6,"hi":1448.2,"votes":74682,"pct":84.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":85,"date":"2026-10-28","rating":1436.2,"lo":1431,"hi":1441.5,"votes":20008,"pct":44.4,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":46,"date":"2026-10-19","rating":1269,"lo":1263.4,"hi":1274.7,"votes":28249,"pct":72.9,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1473.7,"rank":64,"pct":84.7,"board_size":414},"math":{"rating":1470.1,"rank":47,"pct":88.6,"board_size":405},"creative_writing":{"rating":1421.9,"rank":68,"pct":83.9,"board_size":417},"instruction_following":{"rating":1430.8,"rank":75,"pct":82.3,"board_size":419},"hard_prompts":{"rating":1453.1,"rank":67,"pct":84,"board_size":419},"multi_turn":{"rating":1444.2,"rank":79,"pct":81.2,"board_size":417},"longer_query":{"rating":1444.3,"rank":72,"pct":82.1,"board_size":397},"non_english":{"rating":1432.4,"rank":65,"pct":84.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"moonshotai/kimi-k2.5","input_per_m":0.5,"output_per_m":2.5,"blended_per_m":1,"context_length":262144,"modalities_in":["text","image"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/kimi-k2-5-thinking"},{"slug":"ernie-5-0-0110","name":"ERNIE 5.0 (0110)","source_name":"ERNIE 5.0 (0110)","base":"ERNIE 5.0","variant":"0110","org":"baidu","open_weights":false,"model_license":"Proprietary","siscope":{"score":78.3,"rank":52,"coverage":0.75,"categories":{"coding":78,"reasoning":80.1,"math":77.7,"chat":84.2,"instructions":75.8}},"arena":{"text":{"rank":66,"date":"2026-10-28","rating":1444.5,"lo":1440.7,"hi":1448.4,"votes":36475,"pct":84.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1454.7,"rank":92,"pct":78,"board_size":414},"math":{"rating":1436,"rank":91,"pct":77.7,"board_size":405},"creative_writing":{"rating":1426.2,"rank":64,"pct":84.9,"board_size":417},"instruction_following":{"rating":1413.1,"rank":102,"pct":75.8,"board_size":419},"hard_prompts":{"rating":1445.1,"rank":84,"pct":80.1,"board_size":419},"multi_turn":{"rating":1433.3,"rank":98,"pct":76.7,"board_size":417},"longer_query":{"rating":1421.7,"rank":109,"pct":72.7,"board_size":397},"non_english":{"rating":1435.4,"rank":59,"pct":86.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/ernie-5-0-0110"},{"slug":"grok-4-20-beta-1","name":"Grok 4.20 Beta 1","source_name":"Grok 4.20 Beta 1","base":"Grok 4.20 Beta 1","variant":null,"org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":76,"rank":60,"coverage":0.75,"categories":{"coding":73.8,"reasoning":77.3,"math":75.7,"chat":84.2,"instructions":77}},"arena":{"text":{"rank":67,"date":"2026-10-28","rating":1444.5,"lo":1440,"hi":1449,"votes":27889,"pct":84.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1446.6,"rank":109,"pct":73.8,"board_size":414},"math":{"rating":1432.3,"rank":99,"pct":75.7,"board_size":405},"creative_writing":{"rating":1438.1,"rank":48,"pct":88.7,"board_size":417},"instruction_following":{"rating":1415.2,"rank":97,"pct":77,"board_size":419},"hard_prompts":{"rating":1440.8,"rank":96,"pct":77.3,"board_size":419},"multi_turn":{"rating":1450.9,"rank":67,"pct":84.1,"board_size":417},"longer_query":{"rating":1426.7,"rank":101,"pct":74.7,"board_size":397},"non_english":{"rating":1432.9,"rank":64,"pct":84.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/grok-4-20-beta-1"},{"slug":"gemma-4-31b","name":"Gemma 4 31B","source_name":"Gemma 4 31B","base":"Gemma 4 31B","variant":null,"org":"google","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":67.9,"rank":95,"coverage":0.75,"categories":{"coding":52.2,"reasoning":81.1,"math":86.6,"chat":84,"instructions":83.5}},"arena":{"text":{"rank":68,"date":"2026-10-28","rating":1443,"lo":1435.6,"hi":1450.4,"votes":6138,"pct":84,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":114,"date":"2026-10-28","rating":1368.7,"lo":1362.5,"hi":1374.8,"votes":15489,"pct":25.2,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":39,"date":"2026-10-19","rating":1276.5,"lo":1270.8,"hi":1282.1,"votes":40219,"pct":77.1,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1459.1,"rank":87,"pct":79.2,"board_size":414},"math":{"rating":1464.2,"rank":55,"pct":86.6,"board_size":405},"creative_writing":{"rating":1416.2,"rank":74,"pct":82.2,"board_size":417},"instruction_following":{"rating":1433.6,"rank":70,"pct":83.5,"board_size":419},"hard_prompts":{"rating":1447.7,"rank":80,"pct":81.1,"board_size":419},"multi_turn":{"rating":1451.9,"rank":66,"pct":84.4,"board_size":417},"longer_query":{"rating":1445.8,"rank":69,"pct":82.8,"board_size":397},"non_english":{"rating":1430.8,"rank":72,"pct":83,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"google/gemma-4-31b-it","input_per_m":0.2,"output_per_m":0.4,"blended_per_m":0.25,"context_length":262144,"modalities_in":["image","text","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gemma-4-31b"},{"slug":"step-5-preview","name":"Step 5 Preview","source_name":"Step 5 Preview","base":"Step 5 Preview","variant":null,"org":"stepfun","open_weights":false,"model_license":"Proprietary","siscope":{"score":73.9,"rank":66,"coverage":1,"categories":{"coding":87.2,"agents":37.5,"reasoning":87.8,"math":83.9,"chat":83,"instructions":85.9}},"arena":{"text":{"rank":69,"date":"2026-10-28","rating":1442.7,"lo":1436.4,"hi":1449,"votes":11355,"pct":83,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":49,"date":"2026-10-19","rating":1264.6,"lo":1249.5,"hi":1279.6,"votes":1649,"pct":71.1,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":36,"date":"2026-11-02","score":-0.0253,"lo":-0.0393,"hi":-0.0113,"sessions":16859,"cost_per_task_p50":0.631,"pct":37.5,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1482.2,"rank":54,"pct":87.2,"board_size":414},"math":{"rating":1457,"rank":66,"pct":83.9,"board_size":405},"creative_writing":{"rating":1413,"rank":78,"pct":81.5,"board_size":417},"instruction_following":{"rating":1440.8,"rank":60,"pct":85.9,"board_size":419},"hard_prompts":{"rating":1462.6,"rank":52,"pct":87.8,"board_size":419},"multi_turn":{"rating":1436.8,"rank":93,"pct":77.9,"board_size":417},"longer_query":{"rating":1452.1,"rank":62,"pct":84.6,"board_size":397},"non_english":{"rating":1428.9,"rank":76,"pct":82.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"stepfun/step-5-preview","input_per_m":1,"output_per_m":2.7,"blended_per_m":1.425,"context_length":1048576,"modalities_in":["text","image","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/step-5-preview"},{"slug":"gpt-5-1-high","name":"GPT-5.1 (High)","source_name":"GPT-5.1 (High)","base":"GPT-5.1","variant":"High","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":64.1,"rank":120,"coverage":0.75,"categories":{"coding":50,"reasoning":75.7,"math":75.9,"chat":83,"instructions":86.4}},"arena":{"text":{"rank":70,"date":"2026-10-28","rating":1442.7,"lo":1439,"hi":1446.4,"votes":41639,"pct":83,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":64,"date":"2026-10-19","rating":1249.5,"lo":1241.7,"hi":1257.3,"votes":9848,"pct":62,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1453.3,"rank":98,"pct":76.5,"board_size":414},"math":{"rating":1446.1,"rank":78,"pct":80.9,"board_size":405},"creative_writing":{"rating":1427.1,"rank":62,"pct":85.3,"board_size":417},"instruction_following":{"rating":1442.6,"rank":58,"pct":86.4,"board_size":419},"hard_prompts":{"rating":1456.9,"rank":64,"pct":84.9,"board_size":419},"multi_turn":{"rating":1449.5,"rank":68,"pct":83.9,"board_size":417},"longer_query":{"rating":1447.5,"rank":67,"pct":83.3,"board_size":397},"non_english":{"rating":1431.3,"rank":67,"pct":84.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8763,"stderr":0.0188,"tested_as":"gpt-5.1-2025-11-13_high","approx":false,"run_date":"2025-11-13","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FCSVtMksEVjBNsGJGjW4GcQ.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":75.6,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.48,"stderr":0.0158,"tested_as":"gpt-5.1-2025-11-13_high","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FQCLnRy69NBH9ip3VYtQneh.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":66.7,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.8861,"stderr":0.0405,"tested_as":"gpt-5.1-2025-11-13_high","approx":false,"run_date":"2025-11-13","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FmYKKTdV27TRJv9FpUg7rkn.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":70.8,"tested_models":313},{"benchmark":"swe_bench_verified","score":0.6798,"stderr":0.0212,"tested_as":"gpt-5.1-2025-11-13_high","approx":false,"run_date":"2026-02-18","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FYoHtZpMNdsRE6qdj2K4Ucj.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":23.5,"tested_models":35}],"price":{"openrouter_id":"openai/gpt-5.1","input_per_m":1.25,"output_per_m":10,"blended_per_m":3.4375,"context_length":400000,"modalities_in":["image","text","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-1-high"},{"slug":"claude-sonnet-5-high","name":"Claude Sonnet 5 (High)","source_name":"Claude Sonnet 5 (High)","base":"Claude Sonnet 5","variant":"High","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":81.6,"rank":38,"coverage":1,"categories":{"coding":78,"agents":75,"reasoning":87.1,"math":88.1,"chat":83,"instructions":88.3}},"arena":{"text":{"rank":71,"date":"2026-10-28","rating":1442.7,"lo":1438.7,"hi":1446.7,"votes":52952,"pct":83,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":50,"date":"2026-10-28","rating":1540.1,"lo":1534.3,"hi":1545.9,"votes":16832,"pct":67.5,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":41,"date":"2026-10-19","rating":1272.5,"lo":1265.7,"hi":1279.4,"votes":14034,"pct":75.9,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":15,"date":"2026-11-02","score":0.0284,"lo":0.0165,"hi":0.0403,"sessions":41722,"cost_per_task_p50":1.113,"pct":75,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1483.7,"rank":49,"pct":88.4,"board_size":414},"math":{"rating":1468.8,"rank":49,"pct":88.1,"board_size":405},"creative_writing":{"rating":1416.2,"rank":75,"pct":82.2,"board_size":417},"instruction_following":{"rating":1452.7,"rank":50,"pct":88.3,"board_size":419},"hard_prompts":{"rating":1461.8,"rank":54,"pct":87.1,"board_size":419},"multi_turn":{"rating":1452.6,"rank":63,"pct":85.1,"board_size":417},"longer_query":{"rating":1463.1,"rank":47,"pct":88.4,"board_size":397},"non_english":{"rating":1431.1,"rank":69,"pct":83.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"anthropic/claude-sonnet-5","input_per_m":2,"output_per_m":10,"blended_per_m":4,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-sonnet-5-high"},{"slug":"inkling","name":"Inkling","source_name":"Inkling","base":"Inkling","variant":null,"org":"thinky","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":58.6,"rank":142,"coverage":1,"categories":{"coding":59.7,"agents":3.6,"reasoning":83.3,"math":91.6,"chat":83,"instructions":80.9}},"arena":{"text":{"rank":72,"date":"2026-10-28","rating":1442.7,"lo":1438.5,"hi":1446.9,"votes":45472,"pct":83,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":94,"date":"2026-10-28","rating":1415.2,"lo":1409.2,"hi":1421.2,"votes":17073,"pct":38.4,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":55,"date":"2026-11-02","score":-0.1608,"lo":-0.1757,"hi":-0.146,"sessions":44251,"cost_per_task_p50":0.332,"pct":3.6,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1466.1,"rank":80,"pct":80.9,"board_size":414},"math":{"rating":1481,"rank":35,"pct":91.6,"board_size":405},"creative_writing":{"rating":1392.1,"rank":114,"pct":72.8,"board_size":417},"instruction_following":{"rating":1426.1,"rank":81,"pct":80.9,"board_size":419},"hard_prompts":{"rating":1452.1,"rank":70,"pct":83.3,"board_size":419},"multi_turn":{"rating":1439.1,"rank":88,"pct":79.1,"board_size":417},"longer_query":{"rating":1435.6,"rank":86,"pct":78.5,"board_size":397},"non_english":{"rating":1435.1,"rank":61,"pct":85.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"thinkingmachines/inkling","input_per_m":1,"output_per_m":4.05,"blended_per_m":1.7625,"context_length":524288,"modalities_in":["text","image","audio"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/inkling"},{"slug":"gemini-3-flash-minimal","name":"Gemini 3 Flash (Minimal)","source_name":"Gemini 3 Flash (Minimal)","base":"Gemini 3 Flash","variant":"Minimal","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":63.9,"rank":121,"coverage":0.75,"categories":{"coding":48.8,"reasoning":76.1,"math":81.4,"chat":82.8,"instructions":76.3}},"arena":{"text":{"rank":73,"date":"2026-10-28","rating":1442.4,"lo":1439.4,"hi":1445.5,"votes":90997,"pct":82.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":109,"date":"2026-10-28","rating":1384.5,"lo":1379.3,"hi":1389.7,"votes":22080,"pct":28.5,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":48,"date":"2026-10-19","rating":1265.7,"lo":1260.4,"hi":1271,"votes":37173,"pct":71.7,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1435.8,"rank":129,"pct":69,"board_size":414},"math":{"rating":1447.5,"rank":76,"pct":81.4,"board_size":405},"creative_writing":{"rating":1435.4,"rank":57,"pct":86.5,"board_size":417},"instruction_following":{"rating":1414.3,"rank":100,"pct":76.3,"board_size":419},"hard_prompts":{"rating":1437.7,"rank":101,"pct":76.1,"board_size":419},"multi_turn":{"rating":1455.1,"rank":56,"pct":86.8,"board_size":417},"longer_query":{"rating":1428.7,"rank":94,"pct":76.5,"board_size":397},"non_english":{"rating":1437.9,"rank":55,"pct":87.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemini-3-flash-minimal"},{"slug":"ernie-5-0-preview-1203","name":"ERNIE-5.0-Preview (1203)","source_name":"ERNIE-5.0-Preview (1203)","base":"ERNIE-5.0-Preview","variant":"1203","org":"baidu","open_weights":false,"model_license":"Proprietary","siscope":{"score":69.1,"rank":87,"coverage":0.75,"categories":{"coding":65.4,"reasoning":76.3,"math":64.4,"chat":82.5,"instructions":69.9}},"arena":{"text":{"rank":74,"date":"2026-10-28","rating":1442.3,"lo":1435.8,"hi":1448.8,"votes":9802,"pct":82.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1425.5,"rank":144,"pct":65.4,"board_size":414},"math":{"rating":1410.1,"rank":145,"pct":64.4,"board_size":405},"creative_writing":{"rating":1422.1,"rank":67,"pct":84.1,"board_size":417},"instruction_following":{"rating":1401.3,"rank":127,"pct":69.9,"board_size":419},"hard_prompts":{"rating":1438,"rank":100,"pct":76.3,"board_size":419},"multi_turn":{"rating":1408.6,"rank":142,"pct":66.1,"board_size":417},"longer_query":{"rating":1409.2,"rank":133,"pct":66.7,"board_size":397},"non_english":{"rating":1435,"rank":62,"pct":85.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/ernie-5-0-preview-1203"},{"slug":"gpt-6-astra-max","name":"GPT-6 Astra (Max)","source_name":"GPT-6 Astra (Max)","base":"GPT-6 Astra","variant":"Max","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":93.3,"rank":8,"coverage":1,"categories":{"coding":95.1,"agents":94.6,"reasoning":95.4,"math":94.3,"chat":82.3,"instructions":88.5}},"arena":{"text":{"rank":75,"date":"2026-10-28","rating":1441.2,"lo":1435.2,"hi":1447.1,"votes":15038,"pct":82.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":2,"date":"2026-10-28","rating":1773.4,"lo":1763.8,"hi":1782.9,"votes":7210,"pct":99.3,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":36,"date":"2026-10-19","rating":1279.9,"lo":1269.6,"hi":1290.2,"votes":4012,"pct":78.9,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":4,"date":"2026-11-02","score":0.1368,"lo":0.1167,"hi":0.1569,"sessions":15315,"cost_per_task_p50":6.094,"pct":94.6,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1488,"rank":39,"pct":90.8,"board_size":414},"math":{"rating":1467.9,"rank":51,"pct":87.6,"board_size":405},"creative_writing":{"rating":1420.2,"rank":70,"pct":83.4,"board_size":417},"instruction_following":{"rating":1454.1,"rank":49,"pct":88.5,"board_size":419},"hard_prompts":{"rating":1462.1,"rank":53,"pct":87.6,"board_size":419},"multi_turn":{"rating":1448.4,"rank":70,"pct":83.4,"board_size":417},"longer_query":{"rating":1460.9,"rank":52,"pct":87.1,"board_size":397},"non_english":{"rating":1431.6,"rank":66,"pct":84.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9577,"stderr":0.0137,"tested_as":"gpt-6-astra_max","approx":false,"run_date":"2026-08-30","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F3h8STJpG2VzY9LiBUzwotv.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":99.7,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.756,"stderr":0.0136,"tested_as":"gpt-6-astra_max","approx":false,"run_date":"2026-08-30","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FPppwnX7EjXx2SeTcFN8Ujn.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":99,"tested_models":100},{"benchmark":"otis_mock_aime","score":1,"stderr":0,"tested_as":"gpt-6-astra_max","approx":false,"run_date":"2026-08-30","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FL7kW8yxFKCjVXhxNnt3VTq.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":96.2,"tested_models":313},{"benchmark":"frontiermath","score":0.9368,"stderr":0.0144,"tested_as":"gpt-6-astra_max","approx":false,"run_date":"2026-08-30","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":99.2,"tested_models":122}],"price":{"openrouter_id":"openai/gpt-6-astra","input_per_m":10,"output_per_m":50,"blended_per_m":20,"context_length":1050000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-6-astra-max"},{"slug":"glm-4-6","name":"GLM-4.6","source_name":"GLM-4.6","base":"GLM-4.6","variant":null,"org":"zai","open_weights":true,"model_license":"MIT","siscope":{"score":61.9,"rank":127,"coverage":0.75,"categories":{"coding":46.6,"reasoning":77,"math":75.5,"chat":82.1,"instructions":74.6}},"arena":{"text":{"rank":76,"date":"2026-10-28","rating":1440.1,"lo":1436.2,"hi":1443.9,"votes":35810,"pct":82.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":124,"date":"2026-10-28","rating":1341.2,"lo":1330.3,"hi":1352,"votes":6755,"pct":18.5,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1448.7,"rank":106,"pct":74.6,"board_size":414},"math":{"rating":1431.8,"rank":100,"pct":75.5,"board_size":405},"creative_writing":{"rating":1411.9,"rank":80,"pct":81,"board_size":417},"instruction_following":{"rating":1410.2,"rank":107,"pct":74.6,"board_size":419},"hard_prompts":{"rating":1440.3,"rank":97,"pct":77,"board_size":419},"multi_turn":{"rating":1427,"rank":108,"pct":74.3,"board_size":417},"longer_query":{"rating":1422.4,"rank":106,"pct":73.5,"board_size":397},"non_english":{"rating":1426.3,"rank":82,"pct":80.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"z-ai/glm-4.6","input_per_m":0.5,"output_per_m":2,"blended_per_m":0.875,"context_length":204800,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/glm-4-6"},{"slug":"hy3","name":"Hy3","source_name":"Hy3","base":"Hy3","variant":null,"org":"tencent","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":64.5,"rank":118,"coverage":1,"categories":{"coding":69.9,"agents":19.6,"reasoning":81.3,"math":90.6,"chat":81.8,"instructions":81.6}},"arena":{"text":{"rank":77,"date":"2026-10-28","rating":1439.1,"lo":1433.2,"hi":1444.9,"votes":13840,"pct":81.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":64,"date":"2026-10-28","rating":1505.4,"lo":1497.3,"hi":1513.5,"votes":6844,"pct":58.3,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":46,"date":"2026-11-02","score":-0.0753,"lo":-0.0897,"hi":-0.061,"sessions":32673,"cost_per_task_p50":0.073,"pct":19.6,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1466.4,"rank":77,"pct":81.6,"board_size":414},"math":{"rating":1476.7,"rank":39,"pct":90.6,"board_size":405},"creative_writing":{"rating":1407,"rank":84,"pct":80,"board_size":417},"instruction_following":{"rating":1428.7,"rank":78,"pct":81.6,"board_size":419},"hard_prompts":{"rating":1448,"rank":79,"pct":81.3,"board_size":419},"multi_turn":{"rating":1435.1,"rank":94,"pct":77.6,"board_size":417},"longer_query":{"rating":1443.7,"rank":74,"pct":81.6,"board_size":397},"non_english":{"rating":1427.7,"rank":77,"pct":81.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"tencent/hy3","input_per_m":0.132,"output_per_m":0.528,"blended_per_m":0.231,"context_length":262144,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/hy3"},{"slug":"qwen3-max-preview","name":"Qwen3 Max Preview","source_name":"Qwen3-Max-Preview","base":"Qwen3 Max Preview","variant":null,"org":"alibaba","open_weights":false,"model_license":"Proprietary","siscope":{"score":79.7,"rank":45,"coverage":0.75,"categories":{"coding":78.2,"reasoning":81.6,"math":81.2,"chat":81.6,"instructions":78.7}},"arena":{"text":{"rank":78,"date":"2026-10-28","rating":1438.9,"lo":1434.4,"hi":1443.4,"votes":27368,"pct":81.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1455.6,"rank":91,"pct":78.2,"board_size":414},"math":{"rating":1446.7,"rank":77,"pct":81.2,"board_size":405},"creative_writing":{"rating":1401.1,"rank":98,"pct":76.7,"board_size":417},"instruction_following":{"rating":1419.5,"rank":90,"pct":78.7,"board_size":419},"hard_prompts":{"rating":1448.1,"rank":78,"pct":81.6,"board_size":419},"multi_turn":{"rating":1446.1,"rank":72,"pct":82.9,"board_size":417},"longer_query":{"rating":1438.1,"rank":82,"pct":79.5,"board_size":397},"non_english":{"rating":1429.1,"rank":75,"pct":82.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen3-max-preview"},{"slug":"claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5 (2025-09-29)","source_name":"Claude Sonnet 4.5 (20250929)","base":"Claude Sonnet 4.5","variant":"2025-09-29","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":54.3,"rank":163,"coverage":0.75,"categories":{"coding":49,"reasoning":50.7,"math":48.3,"chat":81.1,"instructions":90}},"arena":{"text":{"rank":79,"date":"2026-10-28","rating":1438.5,"lo":1435.7,"hi":1441.4,"votes":82621,"pct":81.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":108,"date":"2026-10-28","rating":1384.9,"lo":1377.6,"hi":1392.2,"votes":15679,"pct":29.1,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1484.7,"rank":48,"pct":88.6,"board_size":414},"math":{"rating":1422.2,"rank":120,"pct":70.5,"board_size":405},"creative_writing":{"rating":1441.8,"rank":42,"pct":90.1,"board_size":417},"instruction_following":{"rating":1459.2,"rank":43,"pct":90,"board_size":419},"hard_prompts":{"rating":1461.8,"rank":55,"pct":87.1,"board_size":419},"multi_turn":{"rating":1464.6,"rank":44,"pct":89.7,"board_size":417},"longer_query":{"rating":1475.2,"rank":37,"pct":90.9,"board_size":397},"non_english":{"rating":1424.9,"rank":85,"pct":79.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.7374,"stderr":0.0314,"tested_as":"claude-sonnet-4-5-20250929","approx":false,"run_date":"2025-09-29","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FfsZmzw8jjyUgMQGwxodBwN.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":45.8,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.237,"stderr":0.0135,"tested_as":"claude-sonnet-4-5-20250929","approx":false,"run_date":"2026-08-10","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":19.2,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.3556,"stderr":0.0722,"tested_as":"claude-sonnet-4-5-20250929","approx":false,"run_date":"2025-09-29","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FdEVgttSw8u6Tt2RsPWTc3C.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":26,"tested_models":313},{"benchmark":"swe_bench_verified","score":0.7128,"stderr":0.0206,"tested_as":"claude-sonnet-4-5-20250929","approx":false,"run_date":"2026-02-05","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FLti64yMEsBWSzgEMFCSVhp.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":29.4,"tested_models":35}],"price":{"openrouter_id":"anthropic/claude-sonnet-4.5","input_per_m":3,"output_per_m":15,"blended_per_m":6,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-sonnet-4-5-20250929"},{"slug":"gpt-5-2-chat-20260210","name":"GPT-5.2 Chat (2026-02-10)","source_name":"GPT-5.2 Chat (20260210)","base":"GPT-5.2 Chat","variant":"2026-02-10","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":76.3,"rank":58,"coverage":0.75,"categories":{"coding":73.6,"reasoning":79.9,"math":76.7,"chat":81.1,"instructions":77.5}},"arena":{"text":{"rank":80,"date":"2026-10-28","rating":1438.5,"lo":1434.5,"hi":1442.5,"votes":35974,"pct":81.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":47,"date":"2026-10-19","rating":1267.8,"lo":1261.4,"hi":1274.3,"votes":16465,"pct":72.3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1446.4,"rank":110,"pct":73.6,"board_size":414},"math":{"rating":1434.7,"rank":95,"pct":76.7,"board_size":405},"creative_writing":{"rating":1400.9,"rank":99,"pct":76.4,"board_size":417},"instruction_following":{"rating":1416.8,"rank":95,"pct":77.5,"board_size":419},"hard_prompts":{"rating":1445,"rank":85,"pct":79.9,"board_size":419},"multi_turn":{"rating":1457.8,"rank":51,"pct":88,"board_size":417},"longer_query":{"rating":1427.5,"rank":97,"pct":75.8,"board_size":397},"non_english":{"rating":1425,"rank":84,"pct":80.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/gpt-5.2-chat","input_per_m":1.75,"output_per_m":14,"blended_per_m":4.8125,"context_length":128000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-2-chat-20260210"},{"slug":"qwen3-8-27b","name":"Qwen3.8-27B","source_name":"Qwen3.8-27B","base":"Qwen3.8-27B","variant":null,"org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":71.1,"rank":77,"coverage":1,"categories":{"coding":82.5,"agents":33.9,"reasoning":85.6,"math":83.7,"chat":80.9,"instructions":84}},"arena":{"text":{"rank":81,"date":"2026-10-28","rating":1438.4,"lo":1433.6,"hi":1443.3,"votes":27779,"pct":80.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":34,"date":"2026-10-28","rating":1589.8,"lo":1583.5,"hi":1596,"votes":18752,"pct":78.1,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":44,"date":"2026-10-19","rating":1269.5,"lo":1261.3,"hi":1277.6,"votes":7614,"pct":74.1,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":38,"date":"2026-11-02","score":-0.043,"lo":-0.0514,"hi":-0.0346,"sessions":64176,"cost_per_task_p50":0.43,"pct":33.9,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1481.4,"rank":55,"pct":86.9,"board_size":414},"math":{"rating":1455.9,"rank":67,"pct":83.7,"board_size":405},"creative_writing":{"rating":1379.1,"rank":133,"pct":68.3,"board_size":417},"instruction_following":{"rating":1434.7,"rank":68,"pct":84,"board_size":419},"hard_prompts":{"rating":1458.1,"rank":61,"pct":85.6,"board_size":419},"multi_turn":{"rating":1438.2,"rank":89,"pct":78.8,"board_size":417},"longer_query":{"rating":1447.7,"rank":66,"pct":83.6,"board_size":397},"non_english":{"rating":1426.4,"rank":81,"pct":80.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"qwen/qwen3.8-27b","input_per_m":0.15,"output_per_m":1.875,"blended_per_m":0.5813,"context_length":1024000,"modalities_in":["text","image","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/qwen3-8-27b"},{"slug":"glm-5v-turbo","name":"GLM-5V-Turbo","source_name":"GLM-5V-Turbo","base":"GLM-5V-Turbo","variant":null,"org":"zai","open_weights":false,"model_license":"Proprietary","siscope":{"score":69,"rank":88,"coverage":0.75,"categories":{"coding":58,"reasoning":79.2,"math":80.4,"chat":80.6,"instructions":80.1}},"arena":{"text":{"rank":82,"date":"2026-10-28","rating":1437.7,"lo":1431.3,"hi":1444.1,"votes":10476,"pct":80.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":99,"date":"2026-10-28","rating":1401,"lo":1387.7,"hi":1414.2,"votes":2394,"pct":35.1,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":50,"date":"2026-10-19","rating":1263.9,"lo":1258.5,"hi":1269.3,"votes":42757,"pct":70.5,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1466.1,"rank":79,"pct":80.9,"board_size":414},"math":{"rating":1442,"rank":80,"pct":80.4,"board_size":405},"creative_writing":{"rating":1416.4,"rank":73,"pct":82.7,"board_size":417},"instruction_following":{"rating":1423,"rank":84,"pct":80.1,"board_size":419},"hard_prompts":{"rating":1443.7,"rank":87,"pct":79.2,"board_size":419},"multi_turn":{"rating":1432.1,"rank":101,"pct":76,"board_size":417},"longer_query":{"rating":1438.6,"rank":81,"pct":79.8,"board_size":397},"non_english":{"rating":1420.6,"rank":89,"pct":78.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"z-ai/glm-5v-turbo","input_per_m":1.2,"output_per_m":4,"blended_per_m":1.9,"context_length":202752,"modalities_in":["image","text","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/glm-5v-turbo"},{"slug":"qwen3-5-397b-a17b","name":"Qwen3.5 397B A17B","source_name":"Qwen3.5-397B-A17B","base":"Qwen3.5 397B A17B","variant":null,"org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":65.3,"rank":106,"coverage":0.75,"categories":{"coding":57.3,"reasoning":75.9,"math":63.1,"chat":80.4,"instructions":80.4}},"arena":{"text":{"rank":83,"date":"2026-10-28","rating":1437.6,"lo":1434.5,"hi":1440.6,"votes":97675,"pct":80.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":100,"date":"2026-10-28","rating":1400.2,"lo":1395.1,"hi":1405.4,"votes":21096,"pct":34.4,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":54,"date":"2026-10-19","rating":1262.5,"lo":1257.2,"hi":1267.7,"votes":32657,"pct":68.1,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1463.9,"rank":83,"pct":80.1,"board_size":414},"math":{"rating":1453.7,"rank":71,"pct":82.7,"board_size":405},"creative_writing":{"rating":1402.2,"rank":95,"pct":77.4,"board_size":417},"instruction_following":{"rating":1423.3,"rank":83,"pct":80.4,"board_size":419},"hard_prompts":{"rating":1447.6,"rank":81,"pct":80.9,"board_size":419},"multi_turn":{"rating":1446.3,"rank":71,"pct":83.2,"board_size":417},"longer_query":{"rating":1441.1,"rank":78,"pct":80.6,"board_size":397},"non_english":{"rating":1429.6,"rank":74,"pct":82.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8586,"stderr":0.0248,"tested_as":"qwen3.5-397b-a17b","approx":false,"run_date":"2026-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FgZMFRbVKnBmcnZU4YqqKMN.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":70.8,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.8889,"stderr":0.0474,"tested_as":"qwen3.5-397b-a17b","approx":false,"run_date":"2026-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FJYuFdyZZSiMvmSZNzMTywb.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":71.2,"tested_models":313},{"benchmark":"frontiermath","score":0.2947,"stderr":0.0271,"tested_as":"qwen3.5-397b-a17b","approx":false,"run_date":"2026-08-28","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FEzMaDdXs4YQTMLgppBGxAb.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":35.5,"tested_models":122}],"price":{"openrouter_id":"qwen/qwen3.5-397b-a17b","input_per_m":0.5,"output_per_m":3.6,"blended_per_m":1.275,"context_length":262144,"modalities_in":["text","image","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/qwen3-5-397b-a17b"},{"slug":"grok-4-1-thinking","name":"Grok 4.1 (Thinking)","source_name":"Grok 4.1 (Thinking)","base":"Grok 4.1","variant":"Thinking","org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":56,"rank":156,"coverage":0.75,"categories":{"coding":38.6,"reasoning":74.4,"math":70.3,"chat":80.1,"instructions":66.7}},"arena":{"text":{"rank":84,"date":"2026-10-28","rating":1436.4,"lo":1433.3,"hi":1439.6,"votes":66470,"pct":80.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":146,"date":"2026-10-28","rating":1214.5,"lo":1189.6,"hi":1239.4,"votes":961,"pct":4,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1445.1,"rank":112,"pct":73.1,"board_size":414},"math":{"rating":1421.9,"rank":121,"pct":70.3,"board_size":405},"creative_writing":{"rating":1403.4,"rank":89,"pct":78.8,"board_size":417},"instruction_following":{"rating":1394.8,"rank":140,"pct":66.7,"board_size":419},"hard_prompts":{"rating":1432.9,"rank":108,"pct":74.4,"board_size":419},"multi_turn":{"rating":1430.2,"rank":103,"pct":75.5,"board_size":417},"longer_query":{"rating":1406.6,"rank":137,"pct":65.4,"board_size":397},"non_english":{"rating":1425.2,"rank":83,"pct":80.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/grok-4-1-thinking"},{"slug":"qwen3-6-plus","name":"Qwen3.6-Plus","source_name":"Qwen3.6-Plus","base":"Qwen3.6-Plus","variant":null,"org":"alibaba","open_weights":false,"model_license":"Proprietary","siscope":{"score":60.2,"rank":136,"coverage":0.75,"categories":{"coding":46.9,"reasoning":72.5,"math":68.6,"chat":79.9,"instructions":80.6}},"arena":{"text":{"rank":85,"date":"2026-10-28","rating":1436.3,"lo":1432.2,"hi":1440.4,"votes":48126,"pct":79.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":77,"date":"2026-10-28","rating":1461.6,"lo":1456,"hi":1467.2,"votes":18511,"pct":49.7,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1466.9,"rank":75,"pct":82.1,"board_size":414},"math":{"rating":1449.4,"rank":73,"pct":82.2,"board_size":405},"creative_writing":{"rating":1403.1,"rank":93,"pct":77.9,"board_size":417},"instruction_following":{"rating":1424.3,"rank":82,"pct":80.6,"board_size":419},"hard_prompts":{"rating":1448.3,"rank":76,"pct":81.8,"board_size":419},"multi_turn":{"rating":1438.1,"rank":90,"pct":78.6,"board_size":417},"longer_query":{"rating":1439,"rank":79,"pct":80.3,"board_size":397},"non_english":{"rating":1423.8,"rank":86,"pct":79.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8838,"stderr":0.0228,"tested_as":"qwen3.6-plus","approx":false,"run_date":"2026-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Ff6ZdMtRpdfskGbrBCzrKSn.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":79.2,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.4414,"stderr":0.0157,"tested_as":"qwen3.6-plus","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F4LWNorP8Fy8V8doxirNFcH.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":56.6,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9333,"stderr":0.0376,"tested_as":"qwen3.6-plus","approx":false,"run_date":"2026-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FjYiGAFfUQKJuRStPzU3PX3.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":77.2,"tested_models":313},{"benchmark":"frontiermath","score":0.3825,"stderr":0.0288,"tested_as":"qwen3.6-plus","approx":false,"run_date":"2026-08-30","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FjbyVWnEvvFVNNc8AEF6WcQ.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":46.3,"tested_models":122},{"benchmark":"swe_bench_verified","score":0.5785,"stderr":0.0225,"tested_as":"qwen3.6-plus","approx":false,"run_date":"2026-05-14","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F8HV4HP9EM5KuLSwzifuLye.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":8.8,"tested_models":35}],"price":{"openrouter_id":"qwen/qwen3.6-plus","input_per_m":0.325,"output_per_m":1.95,"blended_per_m":0.7312,"context_length":1000000,"modalities_in":["text","image","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/qwen3-6-plus"},{"slug":"mimo-v2-pro","name":"MiMo-V2-Pro","source_name":"MiMo-V2-Pro","base":"MiMo-V2-Pro","variant":null,"org":"xiaomi","open_weights":false,"model_license":"Proprietary","siscope":{"score":73.4,"rank":69,"coverage":0.75,"categories":{"coding":63.6,"reasoning":85.2,"math":81.7,"chat":79.7,"instructions":87.1}},"arena":{"text":{"rank":86,"date":"2026-10-28","rating":1436.1,"lo":1431.4,"hi":1440.7,"votes":25421,"pct":79.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":89,"date":"2026-10-28","rating":1434.2,"lo":1426,"hi":1442.3,"votes":7225,"pct":41.7,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1475.9,"rank":61,"pct":85.5,"board_size":414},"math":{"rating":1447.6,"rank":75,"pct":81.7,"board_size":405},"creative_writing":{"rating":1414.7,"rank":76,"pct":82,"board_size":417},"instruction_following":{"rating":1445.4,"rank":55,"pct":87.1,"board_size":419},"hard_prompts":{"rating":1457.4,"rank":63,"pct":85.2,"board_size":419},"multi_turn":{"rating":1456.3,"rank":52,"pct":87.7,"board_size":417},"longer_query":{"rating":1455.3,"rank":58,"pct":85.6,"board_size":397},"non_english":{"rating":1416.3,"rank":100,"pct":76.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/mimo-v2-pro"},{"slug":"grok-4-1","name":"Grok 4.1","source_name":"Grok 4.1","base":"Grok 4.1","variant":null,"org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":71.7,"rank":74,"coverage":0.75,"categories":{"coding":72.6,"reasoning":75.6,"math":67.6,"chat":79.4,"instructions":68.4}},"arena":{"text":{"rank":87,"date":"2026-10-28","rating":1436,"lo":1432.8,"hi":1439.1,"votes":68599,"pct":79.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1443.7,"rank":114,"pct":72.6,"board_size":414},"math":{"rating":1416.2,"rank":132,"pct":67.6,"board_size":405},"creative_writing":{"rating":1411,"rank":82,"pct":80.5,"board_size":417},"instruction_following":{"rating":1399.7,"rank":133,"pct":68.4,"board_size":419},"hard_prompts":{"rating":1435.3,"rank":103,"pct":75.6,"board_size":419},"multi_turn":{"rating":1437.5,"rank":92,"pct":78.1,"board_size":417},"longer_query":{"rating":1415.9,"rank":116,"pct":71,"board_size":397},"non_english":{"rating":1421.8,"rank":87,"pct":79.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/grok-4-1"},{"slug":"gemini-3-5-flash-lite","name":"Gemini 3.5 Flash-Lite","source_name":"Gemini 3.5 Flash-Lite","base":"Gemini 3.5 Flash-Lite","variant":null,"org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":68.2,"rank":93,"coverage":0.75,"categories":{"coding":58.5,"reasoning":77.5,"math":77.5,"chat":79.2,"instructions":78.9}},"arena":{"text":{"rank":88,"date":"2026-10-28","rating":1435.5,"lo":1431,"hi":1439.9,"votes":35740,"pct":79.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":90,"date":"2026-10-28","rating":1434.1,"lo":1393.1,"hi":1475.1,"votes":236,"pct":41.1,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":45,"date":"2026-10-19","rating":1269.1,"lo":1261.2,"hi":1276.9,"votes":9238,"pct":73.5,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1453,"rank":101,"pct":75.8,"board_size":414},"math":{"rating":1435.8,"rank":92,"pct":77.5,"board_size":405},"creative_writing":{"rating":1421.2,"rank":69,"pct":83.7,"board_size":417},"instruction_following":{"rating":1419.9,"rank":89,"pct":78.9,"board_size":419},"hard_prompts":{"rating":1441.2,"rank":95,"pct":77.5,"board_size":419},"multi_turn":{"rating":1445.3,"rank":75,"pct":82.2,"board_size":417},"longer_query":{"rating":1435.1,"rank":88,"pct":78,"board_size":397},"non_english":{"rating":1427.5,"rank":78,"pct":81.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"google/gemini-3.5-flash-lite","input_per_m":0.3,"output_per_m":2.5,"blended_per_m":0.85,"context_length":1048576,"modalities_in":["text","image","video","file","audio"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gemini-3-5-flash-lite"},{"slug":"glm-4-7","name":"GLM-4.7","source_name":"GLM-4.7","base":"GLM-4.7","variant":null,"org":"zai","open_weights":true,"model_license":"MIT","siscope":{"score":62.4,"rank":125,"coverage":0.75,"categories":{"coding":60,"reasoning":57.1,"math":67.1,"chat":78.9,"instructions":75.4}},"arena":{"text":{"rank":89,"date":"2026-10-28","rating":1435.4,"lo":1429.4,"hi":1441.5,"votes":12239,"pct":78.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":88,"date":"2026-10-28","rating":1435.2,"lo":1423.1,"hi":1447.3,"votes":3948,"pct":42.4,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1454.2,"rank":94,"pct":77.5,"board_size":414},"math":{"rating":1424,"rank":117,"pct":71.3,"board_size":405},"creative_writing":{"rating":1401.3,"rank":97,"pct":76.9,"board_size":417},"instruction_following":{"rating":1412.3,"rank":104,"pct":75.4,"board_size":419},"hard_prompts":{"rating":1443,"rank":91,"pct":78.5,"board_size":419},"multi_turn":{"rating":1445.8,"rank":73,"pct":82.7,"board_size":417},"longer_query":{"rating":1432.4,"rank":90,"pct":77.5,"board_size":397},"non_english":{"rating":1417.1,"rank":97,"pct":77,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8333,"stderr":0.0237,"tested_as":"glm-4.7","approx":false,"run_date":"2026-01-29","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F6phXzd4aCbnBUSQmBsaywa.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":63.6,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.322,"stderr":0.0148,"tested_as":"glm-4.7","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FaYau6EG7CCaWVSyVq3vvQc.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":29.3,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.8333,"stderr":0.0477,"tested_as":"glm-4.7","approx":false,"run_date":"2026-01-29","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FGYzmrzMfeSjNjm2J6L9PeT.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":62.8,"tested_models":313}],"price":{"openrouter_id":"z-ai/glm-4.7","input_per_m":0.6,"output_per_m":2.2,"blended_per_m":1,"context_length":204800,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/glm-4-7"},{"slug":"claude-sonnet-4-5-high-32k-20250929","name":"Claude Sonnet 4.5 (High, 32K, 2025-09-29)","source_name":"Claude Sonnet 4.5 (High, 32K, 20250929)","base":"Claude Sonnet 4.5","variant":"High, 32K, 2025-09-29","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":64.6,"rank":115,"coverage":0.75,"categories":{"coding":61.1,"reasoning":73.3,"math":55.7,"chat":78.7,"instructions":89.7}},"arena":{"text":{"rank":90,"date":"2026-10-28","rating":1434.5,"lo":1431.7,"hi":1437.3,"votes":83892,"pct":78.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":105,"date":"2026-10-28","rating":1393.5,"lo":1385.8,"hi":1401.3,"votes":13213,"pct":31.1,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1488.2,"rank":38,"pct":91,"board_size":414},"math":{"rating":1448.6,"rank":74,"pct":81.9,"board_size":405},"creative_writing":{"rating":1424.5,"rank":66,"pct":84.4,"board_size":417},"instruction_following":{"rating":1458,"rank":44,"pct":89.7,"board_size":419},"hard_prompts":{"rating":1461.6,"rank":57,"pct":86.6,"board_size":419},"multi_turn":{"rating":1453.4,"rank":61,"pct":85.6,"board_size":417},"longer_query":{"rating":1475,"rank":38,"pct":90.7,"board_size":397},"non_english":{"rating":1417.8,"rank":95,"pct":77.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8173,"stderr":0.0276,"tested_as":"claude-sonnet-4-5-20250929_32K","approx":false,"run_date":"2025-10-21","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Fii6JE9j57eSbuswEsJArTa.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":59.9,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.7778,"stderr":0.0627,"tested_as":"claude-sonnet-4-5-20250929_32K","approx":false,"run_date":"2025-10-21","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FkqTyhmHyT9irTAWk3xBt2x.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":56.4,"tested_models":313},{"benchmark":"frontiermath","score":0.2386,"stderr":0.0253,"tested_as":"claude-sonnet-4-5-20250929_32K","approx":false,"run_date":"2026-06-11","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F7oUkeLfwMK3MtkSNHX6QPu.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":28.9,"tested_models":122}],"price":{"openrouter_id":"anthropic/claude-sonnet-4.5","input_per_m":3,"output_per_m":15,"blended_per_m":6,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-sonnet-4-5-high-32k-20250929"},{"slug":"gemma-4-26b-a4b","name":"Gemma 4 26B A4B","source_name":"Gemma 4 26B A4B","base":"Gemma 4 26B A4B","variant":null,"org":"google","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":64.5,"rank":116,"coverage":0.75,"categories":{"coding":48.3,"reasoning":76.6,"math":88.4,"chat":78.5,"instructions":79.2}},"arena":{"text":{"rank":91,"date":"2026-10-28","rating":1434.2,"lo":1426.7,"hi":1441.6,"votes":6090,"pct":78.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":117,"date":"2026-10-28","rating":1358.8,"lo":1341.8,"hi":1375.7,"votes":1494,"pct":23.2,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":56,"date":"2026-10-19","rating":1259.6,"lo":1253.1,"hi":1266,"votes":23922,"pct":66.9,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1446.3,"rank":111,"pct":73.4,"board_size":414},"math":{"rating":1469.7,"rank":48,"pct":88.4,"board_size":405},"creative_writing":{"rating":1401.5,"rank":96,"pct":77.2,"board_size":417},"instruction_following":{"rating":1420,"rank":88,"pct":79.2,"board_size":419},"hard_prompts":{"rating":1438.5,"rank":99,"pct":76.6,"board_size":419},"multi_turn":{"rating":1441.6,"rank":84,"pct":80,"board_size":417},"longer_query":{"rating":1427.3,"rank":99,"pct":75.3,"board_size":397},"non_english":{"rating":1421.7,"rank":88,"pct":79.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"google/gemma-4-26b-a4b-it","input_per_m":0.06,"output_per_m":0.18,"blended_per_m":0.09,"context_length":262144,"modalities_in":["image","text","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gemma-4-26b-a4b"},{"slug":"deepseek-v4-flash","name":"DeepSeek V4 Flash","source_name":"DeepSeek-V4-Flash","base":"DeepSeek V4 Flash","variant":null,"org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":76.1,"rank":59,"coverage":0.75,"categories":{"coding":78.5,"reasoning":78.9,"math":72.3,"chat":78.2,"instructions":79.9}},"arena":{"text":{"rank":92,"date":"2026-10-28","rating":1431.8,"lo":1427.8,"hi":1435.9,"votes":51944,"pct":78.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1456.4,"rank":90,"pct":78.5,"board_size":414},"math":{"rating":1425.8,"rank":113,"pct":72.3,"board_size":405},"creative_writing":{"rating":1402.6,"rank":94,"pct":77.6,"board_size":417},"instruction_following":{"rating":1420.9,"rank":85,"pct":79.9,"board_size":419},"hard_prompts":{"rating":1443.5,"rank":89,"pct":78.9,"board_size":419},"multi_turn":{"rating":1448.6,"rank":69,"pct":83.7,"board_size":417},"longer_query":{"rating":1433.9,"rank":89,"pct":77.8,"board_size":397},"non_english":{"rating":1419.1,"rank":91,"pct":78.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/deepseek-v4-flash"},{"slug":"minimax-m3","name":"MiniMax-M3","source_name":"MiniMax-M3","base":"MiniMax-M3","variant":null,"org":"minimax","open_weights":true,"model_license":"MiniMax Community License","siscope":{"score":58.1,"rank":145,"coverage":1,"categories":{"coding":69.2,"agents":10.7,"reasoning":84.2,"math":62.5,"chat":78,"instructions":83}},"arena":{"text":{"rank":93,"date":"2026-10-28","rating":1431.3,"lo":1427.5,"hi":1435,"votes":68611,"pct":78,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":69,"date":"2026-10-28","rating":1483.3,"lo":1477.9,"hi":1488.7,"votes":21032,"pct":55,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":62,"date":"2026-10-19","rating":1251.1,"lo":1244.7,"hi":1257.4,"votes":19844,"pct":63.3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":51,"date":"2026-11-02","score":-0.1042,"lo":-0.1159,"hi":-0.0924,"sessions":44359,"cost_per_task_p50":0.235,"pct":10.7,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1469.5,"rank":70,"pct":83.3,"board_size":414},"math":{"rating":1427.5,"rank":109,"pct":73.3,"board_size":405},"creative_writing":{"rating":1400.5,"rank":102,"pct":75.7,"board_size":417},"instruction_following":{"rating":1431,"rank":72,"pct":83,"board_size":419},"hard_prompts":{"rating":1446,"rank":83,"pct":80.4,"board_size":419},"multi_turn":{"rating":1441.4,"rank":86,"pct":79.6,"board_size":417},"longer_query":{"rating":1443.5,"rank":75,"pct":81.3,"board_size":397},"non_english":{"rating":1418.3,"rank":94,"pct":77.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9091,"stderr":0.0205,"tested_as":"MiniMax-M3","approx":false,"run_date":"2026-08-10","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FhDESmyGFrbZDomjff3rqzD.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":88,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.7111,"stderr":0.0683,"tested_as":"MiniMax-M3","approx":false,"run_date":"2026-08-10","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F79ZP6iwoBaF5t9a5VRqPnw.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":51.6,"tested_models":313}],"price":{"openrouter_id":"minimax/minimax-m3","input_per_m":0.3,"output_per_m":1.2,"blended_per_m":0.525,"context_length":1048576,"modalities_in":["text","image","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/minimax-m3"},{"slug":"gpt-5-6-luna-xhigh","name":"GPT-5.6 Luna (xHigh)","source_name":"GPT-5.6 Luna (xHigh)","base":"GPT-5.6 Luna","variant":"xHigh","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":81.2,"rank":40,"coverage":0.75,"categories":{"coding":81.6,"reasoning":82.8,"math":85.1,"chat":77.8,"instructions":85.2}},"arena":{"text":{"rank":94,"date":"2026-10-28","rating":1431,"lo":1426.8,"hi":1435.3,"votes":41317,"pct":77.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":58,"date":"2026-10-19","rating":1257.1,"lo":1249.7,"hi":1264.5,"votes":11055,"pct":65.7,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1466.4,"rank":76,"pct":81.6,"board_size":414},"math":{"rating":1458.7,"rank":61,"pct":85.1,"board_size":405},"creative_writing":{"rating":1396,"rank":108,"pct":74.3,"board_size":417},"instruction_following":{"rating":1437.8,"rank":63,"pct":85.2,"board_size":419},"hard_prompts":{"rating":1451.6,"rank":72,"pct":82.8,"board_size":419},"multi_turn":{"rating":1434.5,"rank":96,"pct":77.2,"board_size":417},"longer_query":{"rating":1436.3,"rank":85,"pct":78.8,"board_size":397},"non_english":{"rating":1417.1,"rank":96,"pct":77,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/gpt-5.6-luna","input_per_m":0.2,"output_per_m":1.2,"blended_per_m":0.45,"context_length":1050000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-6-luna-xhigh"},{"slug":"mistral-large-4","name":"Mistral Large 4","source_name":"Mistral Large 4","base":"Mistral Large 4","variant":null,"org":"mistral","open_weights":false,"model_license":"Proprietary","siscope":{"score":66.2,"rank":100,"coverage":1,"categories":{"coding":77.3,"agents":25,"reasoning":79.2,"math":87.4,"chat":77.5,"instructions":78.5}},"arena":{"text":{"rank":95,"date":"2026-10-28","rating":1430.1,"lo":1423.9,"hi":1436.3,"votes":12066,"pct":77.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":48,"date":"2026-10-28","rating":1544.3,"lo":1533.8,"hi":1554.9,"votes":4068,"pct":68.9,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":42,"date":"2026-10-19","rating":1272.2,"lo":1252.9,"hi":1291.4,"votes":1008,"pct":75.3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":43,"date":"2026-11-02","score":-0.0641,"lo":-0.0852,"hi":-0.043,"sessions":14173,"cost_per_task_p50":0.446,"pct":25,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1478.3,"rank":60,"pct":85.7,"board_size":414},"math":{"rating":1467.7,"rank":52,"pct":87.4,"board_size":405},"creative_writing":{"rating":1360.8,"rank":157,"pct":62.5,"board_size":417},"instruction_following":{"rating":1418.7,"rank":91,"pct":78.5,"board_size":419},"hard_prompts":{"rating":1443.7,"rank":88,"pct":79.2,"board_size":419},"multi_turn":{"rating":1437.5,"rank":91,"pct":78.1,"board_size":417},"longer_query":{"rating":1428.1,"rank":95,"pct":76.3,"board_size":397},"non_english":{"rating":1420.2,"rank":90,"pct":78.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"mistralai/mistral-large-4-0","input_per_m":0.7,"output_per_m":2.1,"blended_per_m":1.05,"context_length":1048576,"modalities_in":["text","image"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/mistral-large-4"},{"slug":"glm-4-5","name":"GLM-4.5","source_name":"GLM-4.5","base":"GLM-4.5","variant":null,"org":"zai","open_weights":true,"model_license":"MIT","siscope":{"score":71,"rank":78,"coverage":0.75,"categories":{"coding":68.3,"reasoning":73.2,"math":73,"chat":77.3,"instructions":71.1}},"arena":{"text":{"rank":96,"date":"2026-10-28","rating":1430,"lo":1425.1,"hi":1434.9,"votes":23797,"pct":77.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1433.9,"rank":132,"pct":68.3,"board_size":414},"math":{"rating":1427.2,"rank":110,"pct":73,"board_size":405},"creative_writing":{"rating":1395,"rank":109,"pct":74,"board_size":417},"instruction_following":{"rating":1404.1,"rank":122,"pct":71.1,"board_size":419},"hard_prompts":{"rating":1429.2,"rank":113,"pct":73.2,"board_size":419},"multi_turn":{"rating":1414.9,"rank":128,"pct":69.5,"board_size":417},"longer_query":{"rating":1412.5,"rank":126,"pct":68.4,"board_size":397},"non_english":{"rating":1417,"rank":98,"pct":76.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"z-ai/glm-4.5","input_per_m":0.6,"output_per_m":2.2,"blended_per_m":1,"context_length":131072,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/glm-4-5"},{"slug":"ernie-5-0-preview-1022","name":"ERNIE-5.0-Preview (1022)","source_name":"ERNIE-5.0-Preview (1022)","base":"ERNIE-5.0-Preview","variant":"1022","org":"baidu","open_weights":false,"model_license":"Proprietary","siscope":{"score":64.3,"rank":119,"coverage":0.75,"categories":{"coding":61,"reasoning":67.9,"math":61.6,"chat":77,"instructions":65.8}},"arena":{"text":{"rank":97,"date":"2026-10-28","rating":1429.8,"lo":1421,"hi":1438.5,"votes":4755,"pct":77,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1412.3,"rank":162,"pct":61,"board_size":414},"math":{"rating":1405.1,"rank":156,"pct":61.6,"board_size":405},"creative_writing":{"rating":1416.8,"rank":72,"pct":82.9,"board_size":417},"instruction_following":{"rating":1392.5,"rank":144,"pct":65.8,"board_size":419},"hard_prompts":{"rating":1420.4,"rank":135,"pct":67.9,"board_size":419},"multi_turn":{"rating":1418.4,"rank":118,"pct":71.6,"board_size":417},"longer_query":{"rating":1406,"rank":139,"pct":65.2,"board_size":397},"non_english":{"rating":1426.6,"rank":80,"pct":81.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/ernie-5-0-preview-1022"},{"slug":"grok-4-6-high","name":"Grok 4.6 (High)","source_name":"Grok 4.6 (High)","base":"Grok 4.6","variant":"High","org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":79.2,"rank":48,"coverage":0.75,"categories":{"coding":80.6,"reasoning":82.5,"math":77.1,"chat":76.8,"instructions":82.8}},"arena":{"text":{"rank":98,"date":"2026-10-28","rating":1428.5,"lo":1423.9,"hi":1433.2,"votes":33824,"pct":76.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":30,"date":"2026-10-28","rating":1616.4,"lo":1609.4,"hi":1623.4,"votes":11966,"pct":80.8,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":52,"date":"2026-10-19","rating":1263,"lo":1254.7,"hi":1271.3,"votes":7261,"pct":69.3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1464.3,"rank":82,"pct":80.4,"board_size":414},"math":{"rating":1414.9,"rank":136,"pct":66.6,"board_size":405},"creative_writing":{"rating":1426.4,"rank":63,"pct":85.1,"board_size":417},"instruction_following":{"rating":1430.9,"rank":73,"pct":82.8,"board_size":419},"hard_prompts":{"rating":1447.4,"rank":82,"pct":80.6,"board_size":419},"multi_turn":{"rating":1425.3,"rank":111,"pct":73.6,"board_size":417},"longer_query":{"rating":1456,"rank":57,"pct":85.9,"board_size":397},"non_english":{"rating":1418.7,"rank":93,"pct":78,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.94,"stderr":0.0145,"tested_as":"grok-4.6_high","approx":false,"run_date":"2026-08-12","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FhnP6Z88x8bPEBRZ2PW6kps.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":96.1,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.493,"stderr":0.0158,"tested_as":"grok-4.6_high","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FTpHYtuPG6kYZFvMK7Z6Hqj.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":70.7,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9778,"stderr":0.01,"tested_as":"grok-4.6_high","approx":false,"run_date":"2026-08-12","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FjtfdCURnwfZzak4BSiBKzx.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":87.5,"tested_models":313}],"price":{"openrouter_id":"x-ai/grok-4.6","input_per_m":2,"output_per_m":6,"blended_per_m":3,"context_length":500000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/grok-4-6-high"},{"slug":"chatgpt-4o-latest-20250326","name":"ChatGPT-4o Latest (2025-03-26)","source_name":"ChatGPT-4o Latest (20250326)","base":"ChatGPT-4o Latest","variant":"2025-03-26","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":65.1,"rank":111,"coverage":0.75,"categories":{"coding":61.3,"reasoning":69.9,"math":62.1,"chat":76.6,"instructions":70.3}},"arena":{"text":{"rank":99,"date":"2026-10-28","rating":1428.4,"lo":1425.7,"hi":1431.2,"votes":81893,"pct":76.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":71,"date":"2026-10-19","rating":1243.3,"lo":1237.8,"hi":1248.8,"votes":23400,"pct":57.8,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1412.8,"rank":161,"pct":61.3,"board_size":414},"math":{"rating":1406.9,"rank":154,"pct":62.1,"board_size":405},"creative_writing":{"rating":1405,"rank":87,"pct":79.3,"board_size":417},"instruction_following":{"rating":1403.1,"rank":125,"pct":70.3,"board_size":419},"hard_prompts":{"rating":1424.1,"rank":127,"pct":69.9,"board_size":419},"multi_turn":{"rating":1454.2,"rank":59,"pct":86.1,"board_size":417},"longer_query":{"rating":1412.3,"rank":127,"pct":68.2,"board_size":397},"non_english":{"rating":1418.8,"rank":92,"pct":78.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/chatgpt-4o-latest-20250326"},{"slug":"mistral-large-3","name":"Mistral Large 3","source_name":"Mistral Large 3","base":"Mistral Large 3","variant":null,"org":"mistral","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":55.8,"rank":157,"coverage":0.75,"categories":{"coding":39.9,"reasoning":73.4,"math":66.6,"chat":76.3,"instructions":71.3}},"arena":{"text":{"rank":100,"date":"2026-10-28","rating":1428.3,"lo":1425.5,"hi":1431.1,"votes":88325,"pct":76.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":144,"date":"2026-10-28","rating":1232.6,"lo":1207.1,"hi":1258.1,"votes":838,"pct":5.3,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":84,"date":"2026-10-19","rating":1219.9,"lo":1212.2,"hi":1227.7,"votes":9254,"pct":50,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1448.7,"rank":105,"pct":74.6,"board_size":414},"math":{"rating":1414.9,"rank":135,"pct":66.6,"board_size":405},"creative_writing":{"rating":1386.5,"rank":124,"pct":70.4,"board_size":417},"instruction_following":{"rating":1404.2,"rank":121,"pct":71.3,"board_size":419},"hard_prompts":{"rating":1430.2,"rank":112,"pct":73.4,"board_size":419},"multi_turn":{"rating":1430.1,"rank":104,"pct":75.2,"board_size":417},"longer_query":{"rating":1414.4,"rank":122,"pct":69.4,"board_size":397},"non_english":{"rating":1413.8,"rank":101,"pct":76.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/mistral-large-3"},{"slug":"mimo-v2-5","name":"MiMo-V2.5","source_name":"MiMo-V2.5","base":"MiMo-V2.5","variant":null,"org":"xiaomi","open_weights":true,"model_license":"MIT","siscope":{"score":71.9,"rank":73,"coverage":0.75,"categories":{"coding":63.9,"reasoning":82.3,"math":78,"chat":76.1,"instructions":83.7}},"arena":{"text":{"rank":101,"date":"2026-10-28","rating":1427.8,"lo":1423.6,"hi":1432,"votes":47327,"pct":76.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":84,"date":"2026-10-28","rating":1438.3,"lo":1432.2,"hi":1444.3,"votes":14837,"pct":45,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":66,"date":"2026-10-19","rating":1247,"lo":1241.2,"hi":1252.9,"votes":29381,"pct":60.2,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1469,"rank":71,"pct":82.8,"board_size":414},"math":{"rating":1436.6,"rank":90,"pct":78,"board_size":405},"creative_writing":{"rating":1392.5,"rank":113,"pct":73.1,"board_size":417},"instruction_following":{"rating":1434.6,"rank":69,"pct":83.7,"board_size":419},"hard_prompts":{"rating":1450.1,"rank":75,"pct":82.3,"board_size":419},"multi_turn":{"rating":1445.2,"rank":76,"pct":82,"board_size":417},"longer_query":{"rating":1444.7,"rank":71,"pct":82.3,"board_size":397},"non_english":{"rating":1404.7,"rank":121,"pct":71.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"xiaomi/mimo-v2.5","input_per_m":0.4,"output_per_m":2,"blended_per_m":0.8,"context_length":1050000,"modalities_in":["text","audio","image","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/mimo-v2-5"},{"slug":"deepseek-r1-0528","name":"DeepSeek-R1 (0528)","source_name":"DeepSeek-R1 (0528)","base":"DeepSeek-R1","variant":"0528","org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":64.5,"rank":117,"coverage":0.75,"categories":{"coding":65.9,"reasoning":66.3,"math":60.1,"chat":75.8,"instructions":62.9}},"arena":{"text":{"rank":102,"date":"2026-10-28","rating":1427.7,"lo":1422.1,"hi":1433.4,"votes":18165,"pct":75.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1426.8,"rank":142,"pct":65.9,"board_size":414},"math":{"rating":1400,"rank":162,"pct":60.1,"board_size":405},"creative_writing":{"rating":1405.2,"rank":86,"pct":79.6,"board_size":417},"instruction_following":{"rating":1381.5,"rank":156,"pct":62.9,"board_size":419},"hard_prompts":{"rating":1415.3,"rank":142,"pct":66.3,"board_size":419},"multi_turn":{"rating":1404.4,"rank":149,"pct":64.4,"board_size":417},"longer_query":{"rating":1391.1,"rank":163,"pct":59.1,"board_size":397},"non_english":{"rating":1411.7,"rank":105,"pct":75.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/deepseek-r1-0528"},{"slug":"longcat-flash-chat-exp-2602","name":"LongCat-Flash-Chat Exp (2602)","source_name":"LongCat-Flash-Chat Exp (2602)","base":"LongCat-Flash-Chat Exp","variant":"2602","org":"meituan","open_weights":false,"model_license":"Proprietary","siscope":{"score":77.8,"rank":53,"coverage":0.75,"categories":{"coding":83.8,"reasoning":76.8,"math":75.7,"chat":75.6,"instructions":75.1}},"arena":{"text":{"rank":103,"date":"2026-10-28","rating":1426.7,"lo":1422.2,"hi":1431.2,"votes":29244,"pct":75.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1471.2,"rank":68,"pct":83.8,"board_size":414},"math":{"rating":1432.3,"rank":97,"pct":75.7,"board_size":405},"creative_writing":{"rating":1387.9,"rank":121,"pct":71.2,"board_size":417},"instruction_following":{"rating":1411.2,"rank":105,"pct":75.1,"board_size":419},"hard_prompts":{"rating":1439.7,"rank":98,"pct":76.8,"board_size":419},"multi_turn":{"rating":1417.6,"rank":121,"pct":71.2,"board_size":417},"longer_query":{"rating":1425.1,"rank":104,"pct":74,"board_size":397},"non_english":{"rating":1399.6,"rank":136,"pct":67.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/longcat-flash-chat-exp-2602"},{"slug":"grok-3-preview-02-24","name":"Grok 3 Preview (02-24)","source_name":"Grok 3 Preview (02-24)","base":"Grok 3 Preview","variant":"02-24","org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":65.5,"rank":104,"coverage":0.75,"categories":{"coding":67.1,"reasoning":74.9,"math":56.2,"chat":75.1,"instructions":74.2}},"arena":{"text":{"rank":104,"date":"2026-10-28","rating":1425.4,"lo":1421.1,"hi":1429.7,"votes":32496,"pct":75.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1432,"rank":136,"pct":67.1,"board_size":414},"math":{"rating":1390.6,"rank":178,"pct":56.2,"board_size":405},"creative_writing":{"rating":1413.9,"rank":77,"pct":81.7,"board_size":417},"instruction_following":{"rating":1408.6,"rank":109,"pct":74.2,"board_size":419},"hard_prompts":{"rating":1433.4,"rank":106,"pct":74.9,"board_size":419},"multi_turn":{"rating":1424.1,"rank":112,"pct":73.1,"board_size":417},"longer_query":{"rating":1438.8,"rank":80,"pct":80.1,"board_size":397},"non_english":{"rating":1410.3,"rank":107,"pct":74.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/grok-3-preview-02-24"},{"slug":"beam-1-0-501b-a23b","name":"Beam 1.0 501B A23B","source_name":"Beam 1.0 501B A23B","base":"Beam 1.0 501B A23B","variant":null,"org":"reflection","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":63.4,"rank":122,"coverage":1,"categories":{"coding":64.5,"agents":28.6,"reasoning":77.8,"math":86.1,"chat":75.1,"instructions":82.3}},"arena":{"text":{"rank":105,"date":"2026-10-28","rating":1425.4,"lo":1416.1,"hi":1434.7,"votes":4233,"pct":75.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":86,"date":"2026-10-28","rating":1436,"lo":1423.3,"hi":1448.8,"votes":2932,"pct":43.7,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":41,"date":"2026-11-02","score":-0.047,"lo":-0.0726,"hi":-0.0213,"sessions":12384,"cost_per_task_p50":null,"pct":28.6,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1474.1,"rank":62,"pct":85.2,"board_size":414},"math":{"rating":1463,"rank":57,"pct":86.1,"board_size":405},"creative_writing":{"rating":1390.5,"rank":118,"pct":71.9,"board_size":417},"instruction_following":{"rating":1430.8,"rank":74,"pct":82.3,"board_size":419},"hard_prompts":{"rating":1441.9,"rank":94,"pct":77.8,"board_size":419},"multi_turn":{"rating":1417,"rank":122,"pct":70.9,"board_size":417},"longer_query":{"rating":1429.6,"rank":93,"pct":76.8,"board_size":397},"non_english":{"rating":1412.2,"rank":104,"pct":75.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"reflection/beam-1.0-501b-a23b","input_per_m":0.25,"output_per_m":1,"blended_per_m":0.4375,"context_length":1048576,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/beam-1-0-501b-a23b"},{"slug":"deepseek-v3-2-exp-thinking","name":"DeepSeek V3.2 Exp (Thinking)","source_name":"DeepSeek-V3.2-Exp (Thinking)","base":"DeepSeek V3.2 Exp","variant":"Thinking","org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":70.7,"rank":80,"coverage":0.75,"categories":{"coding":71.2,"reasoning":71.3,"math":70,"chat":74.9,"instructions":68.9}},"arena":{"text":{"rank":106,"date":"2026-10-28","rating":1425,"lo":1418.4,"hi":1431.5,"votes":8991,"pct":74.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1438.8,"rank":120,"pct":71.2,"board_size":414},"math":{"rating":1421.8,"rank":122,"pct":70,"board_size":405},"creative_writing":{"rating":1387.8,"rank":122,"pct":70.9,"board_size":417},"instruction_following":{"rating":1400.3,"rank":131,"pct":68.9,"board_size":419},"hard_prompts":{"rating":1426.7,"rank":121,"pct":71.3,"board_size":419},"multi_turn":{"rating":1412.9,"rank":132,"pct":68.5,"board_size":417},"longer_query":{"rating":1410.6,"rank":129,"pct":67.7,"board_size":397},"non_english":{"rating":1404.5,"rank":125,"pct":70.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"deepseek/deepseek-v3.2-exp","input_per_m":0.27,"output_per_m":0.41,"blended_per_m":0.305,"context_length":163840,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/deepseek-v3-2-exp-thinking"},{"slug":"deepseek-v3-2","name":"DeepSeek-V3.2","source_name":"DeepSeek-V3.2","base":"DeepSeek-V3.2","variant":null,"org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":60.4,"rank":135,"coverage":0.75,"categories":{"coding":45.2,"reasoning":75.1,"math":77,"chat":74.6,"instructions":75.6}},"arena":{"text":{"rank":107,"date":"2026-10-28","rating":1424.4,"lo":1421,"hi":1427.9,"votes":48095,"pct":74.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":129,"date":"2026-10-28","rating":1325.8,"lo":1317.8,"hi":1333.7,"votes":9327,"pct":15.2,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1448.8,"rank":104,"pct":75.1,"board_size":414},"math":{"rating":1435.1,"rank":94,"pct":77,"board_size":405},"creative_writing":{"rating":1399.6,"rank":104,"pct":75.2,"board_size":417},"instruction_following":{"rating":1412.7,"rank":103,"pct":75.6,"board_size":419},"hard_prompts":{"rating":1433.5,"rank":105,"pct":75.1,"board_size":419},"multi_turn":{"rating":1426.9,"rank":109,"pct":74,"board_size":417},"longer_query":{"rating":1427.8,"rank":96,"pct":76,"board_size":397},"non_english":{"rating":1408.8,"rank":111,"pct":73.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"deepseek/deepseek-v3.2","input_per_m":0.26,"output_per_m":0.38,"blended_per_m":0.29,"context_length":163840,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/deepseek-v3-2"},{"slug":"deepseek-v4-flash-preview-high","name":"DeepSeek-V4-Flash Preview (High)","source_name":"DeepSeek-V4-Flash Preview (High)","base":"DeepSeek-V4-Flash Preview","variant":"High","org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":64.9,"rank":113,"coverage":0.75,"categories":{"coding":55.9,"reasoning":73.9,"math":72,"chat":74.4,"instructions":77.8}},"arena":{"text":{"rank":108,"date":"2026-10-28","rating":1424.3,"lo":1420.2,"hi":1428.4,"votes":51763,"pct":74.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":91,"date":"2026-10-28","rating":1430.5,"lo":1423.5,"hi":1437.4,"votes":10074,"pct":40.4,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1440.2,"rank":119,"pct":71.4,"board_size":414},"math":{"rating":1425.4,"rank":114,"pct":72,"board_size":405},"creative_writing":{"rating":1398.5,"rank":105,"pct":75,"board_size":417},"instruction_following":{"rating":1417.1,"rank":94,"pct":77.8,"board_size":419},"hard_prompts":{"rating":1431.5,"rank":110,"pct":73.9,"board_size":419},"multi_turn":{"rating":1431.6,"rank":102,"pct":75.7,"board_size":417},"longer_query":{"rating":1423.9,"rank":105,"pct":73.7,"board_size":397},"non_english":{"rating":1409.5,"rank":108,"pct":74.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/deepseek-v4-flash-preview-high"},{"slug":"mistral-medium-3-1-2508","name":"Mistral Medium 3.1 (2508)","source_name":"Mistral Medium 3.1 (2508)","base":"Mistral Medium 3.1","variant":"2508","org":"mistral","open_weights":false,"model_license":"Proprietary","siscope":{"score":67.2,"rank":97,"coverage":0.75,"categories":{"coding":67.8,"reasoning":70.6,"math":63.4,"chat":74.2,"instructions":67.2}},"arena":{"text":{"rank":109,"date":"2026-10-28","rating":1424.2,"lo":1421.7,"hi":1426.8,"votes":95269,"pct":74.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":109,"date":"2026-10-19","rating":1172.2,"lo":1166.1,"hi":1178.4,"votes":41611,"pct":34.9,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1433.2,"rank":134,"pct":67.8,"board_size":414},"math":{"rating":1408.5,"rank":149,"pct":63.4,"board_size":405},"creative_writing":{"rating":1390.6,"rank":117,"pct":72.1,"board_size":417},"instruction_following":{"rating":1397.6,"rank":138,"pct":67.2,"board_size":419},"hard_prompts":{"rating":1425.6,"rank":124,"pct":70.6,"board_size":419},"multi_turn":{"rating":1418,"rank":120,"pct":71.4,"board_size":417},"longer_query":{"rating":1405.6,"rank":140,"pct":64.9,"board_size":397},"non_english":{"rating":1407.7,"rank":112,"pct":73.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"mistralai/mistral-medium-3.1","input_per_m":0.4,"output_per_m":2,"blended_per_m":0.8,"context_length":131072,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/mistral-medium-3-1-2508"},{"slug":"mimo-v2-omni","name":"MiMo-V2-Omni","source_name":"MiMo-V2-Omni","base":"MiMo-V2-Omni","variant":null,"org":"xiaomi","open_weights":false,"model_license":"Proprietary","siscope":{"score":77.4,"rank":54,"coverage":0.75,"categories":{"coding":81.4,"reasoning":79.7,"math":74.3,"chat":73.9,"instructions":81.6}},"arena":{"text":{"rank":110,"date":"2026-10-28","rating":1423.1,"lo":1417.6,"hi":1428.6,"votes":20615,"pct":73.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":82,"date":"2026-10-19","rating":1227.6,"lo":1220.3,"hi":1235,"votes":10650,"pct":51.2,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1466.2,"rank":78,"pct":81.4,"board_size":414},"math":{"rating":1430.7,"rank":105,"pct":74.3,"board_size":405},"creative_writing":{"rating":1391.8,"rank":115,"pct":72.6,"board_size":417},"instruction_following":{"rating":1428.7,"rank":77,"pct":81.6,"board_size":419},"hard_prompts":{"rating":1444.9,"rank":86,"pct":79.7,"board_size":419},"multi_turn":{"rating":1444.9,"rank":77,"pct":81.7,"board_size":417},"longer_query":{"rating":1441.4,"rank":76,"pct":81.1,"board_size":397},"non_english":{"rating":1403.5,"rank":129,"pct":69.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/mimo-v2-omni"},{"slug":"longcat-flash-chat","name":"LongCat-Flash-Chat","source_name":"LongCat-Flash-Chat","base":"LongCat-Flash-Chat","variant":null,"org":"meituan","open_weights":true,"model_license":"MIT","siscope":{"score":74.5,"rank":65,"coverage":0.75,"categories":{"coding":80.6,"reasoning":74.2,"math":79.7,"chat":73.7,"instructions":67.2}},"arena":{"text":{"rank":111,"date":"2026-10-28","rating":1422.7,"lo":1416.3,"hi":1429.1,"votes":11167,"pct":73.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1465.8,"rank":81,"pct":80.6,"board_size":414},"math":{"rating":1441.4,"rank":83,"pct":79.7,"board_size":405},"creative_writing":{"rating":1346.1,"rank":173,"pct":58.7,"board_size":417},"instruction_following":{"rating":1397.6,"rank":137,"pct":67.2,"board_size":419},"hard_prompts":{"rating":1432.8,"rank":109,"pct":74.2,"board_size":419},"multi_turn":{"rating":1402.6,"rank":152,"pct":63.7,"board_size":417},"longer_query":{"rating":1390.9,"rank":164,"pct":58.8,"board_size":397},"non_english":{"rating":1403.7,"rank":127,"pct":69.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/longcat-flash-chat"},{"slug":"gpt-5-1","name":"GPT-5.1","source_name":"GPT-5.1","base":"GPT-5.1","variant":null,"org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":51.7,"rank":172,"coverage":0.75,"categories":{"coding":44.7,"reasoning":56.6,"math":45.3,"chat":73.2,"instructions":78}},"arena":{"text":{"rank":112,"date":"2026-10-28","rating":1422.2,"lo":1418.6,"hi":1425.7,"votes":44413,"pct":73.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":123,"date":"2026-10-28","rating":1341.3,"lo":1332.9,"hi":1349.8,"votes":10675,"pct":19.2,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":77,"date":"2026-10-19","rating":1234.9,"lo":1227.4,"hi":1242.4,"votes":10801,"pct":54.2,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1437.5,"rank":124,"pct":70.2,"board_size":414},"math":{"rating":1409.5,"rank":148,"pct":63.6,"board_size":405},"creative_writing":{"rating":1403.3,"rank":91,"pct":78.4,"board_size":417},"instruction_following":{"rating":1418.1,"rank":93,"pct":78,"board_size":419},"hard_prompts":{"rating":1434.5,"rank":104,"pct":75.4,"board_size":419},"multi_turn":{"rating":1432.9,"rank":99,"pct":76.4,"board_size":417},"longer_query":{"rating":1429.6,"rank":92,"pct":76.8,"board_size":397},"non_english":{"rating":1412.8,"rank":102,"pct":75.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.6667,"stderr":0.0336,"tested_as":"gpt-5.1-2025-11-13_none","approx":false,"run_date":"2026-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FUT5fVL4EGvSTZBKMTPy9YN.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":37.7,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.3778,"stderr":0.0731,"tested_as":"gpt-5.1-2025-11-13_none","approx":false,"run_date":"2026-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FH5NgPXUD57sbusTLp3yKQE.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":26.9,"tested_models":313}],"price":{"openrouter_id":"openai/gpt-5.1","input_per_m":1.25,"output_per_m":10,"blended_per_m":3.4375,"context_length":400000,"modalities_in":["image","text","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-1"},{"slug":"deepseek-v3-2-exp","name":"DeepSeek V3.2 Exp","source_name":"DeepSeek-V3.2-Exp","base":"DeepSeek V3.2 Exp","variant":null,"org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":55.6,"rank":158,"coverage":0.75,"categories":{"coding":39.9,"reasoning":73,"math":68.3,"chat":73.2,"instructions":69.4}},"arena":{"text":{"rank":113,"date":"2026-10-28","rating":1422.2,"lo":1415.8,"hi":1428.5,"votes":11996,"pct":73.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":135,"date":"2026-10-28","rating":1271.4,"lo":1257.9,"hi":1285,"votes":3968,"pct":11.3,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1435,"rank":131,"pct":68.5,"board_size":414},"math":{"rating":1418.3,"rank":129,"pct":68.3,"board_size":405},"creative_writing":{"rating":1403.2,"rank":92,"pct":78.1,"board_size":417},"instruction_following":{"rating":1400.7,"rank":129,"pct":69.4,"board_size":419},"hard_prompts":{"rating":1428.9,"rank":114,"pct":73,"board_size":419},"multi_turn":{"rating":1421.4,"rank":116,"pct":72.4,"board_size":417},"longer_query":{"rating":1417.5,"rank":115,"pct":71.2,"board_size":397},"non_english":{"rating":1404.2,"rank":126,"pct":70.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"deepseek/deepseek-v3.2-exp","input_per_m":0.27,"output_per_m":0.41,"blended_per_m":0.305,"context_length":163840,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/deepseek-v3-2-exp"},{"slug":"mistral-medium-3-5","name":"Mistral Medium 3.5","source_name":"Mistral Medium 3.5","base":"Mistral Medium 3.5","variant":null,"org":"mistral","open_weights":true,"model_license":"Modified MIT","siscope":{"score":51.2,"rank":179,"coverage":1,"categories":{"coding":45.2,"agents":8.9,"reasoning":75.8,"math":75.7,"chat":73,"instructions":76.8}},"arena":{"text":{"rank":114,"date":"2026-10-28","rating":1420.8,"lo":1414.4,"hi":1427.1,"votes":11791,"pct":73,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":136,"date":"2026-10-28","rating":1264,"lo":1249.2,"hi":1278.8,"votes":2299,"pct":10.6,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":83,"date":"2026-10-19","rating":1222.5,"lo":1213,"hi":1231.9,"votes":5375,"pct":50.6,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":52,"date":"2026-11-02","score":-0.1322,"lo":-0.1491,"hi":-0.1152,"sessions":14001,"cost_per_task_p50":0.47,"pct":8.9,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1460.1,"rank":85,"pct":79.7,"board_size":414},"math":{"rating":1432.3,"rank":98,"pct":75.7,"board_size":405},"creative_writing":{"rating":1373.8,"rank":142,"pct":66.1,"board_size":417},"instruction_following":{"rating":1415,"rank":98,"pct":76.8,"board_size":419},"hard_prompts":{"rating":1436.5,"rank":102,"pct":75.8,"board_size":419},"multi_turn":{"rating":1423.3,"rank":114,"pct":72.8,"board_size":417},"longer_query":{"rating":1415,"rank":120,"pct":69.9,"board_size":397},"non_english":{"rating":1404.6,"rank":122,"pct":71.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"mistralai/mistral-medium-3-5","input_per_m":1.5,"output_per_m":7.5,"blended_per_m":3,"context_length":262144,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/mistral-medium-3-5"},{"slug":"kimi-k2-5-instant","name":"Kimi K2.5 (Instant)","source_name":"Kimi K2.5 (Instant)","base":"Kimi K2.5","variant":"Instant","org":"moonshot","open_weights":true,"model_license":"Modified MIT","siscope":{"score":70.2,"rank":81,"coverage":0.75,"categories":{"coding":62.2,"reasoning":78.7,"math":80,"chat":72.7,"instructions":82.1}},"arena":{"text":{"rank":115,"date":"2026-10-28","rating":1420.1,"lo":1413.7,"hi":1426.6,"votes":8371,"pct":72.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":97,"date":"2026-10-28","rating":1405.6,"lo":1393.5,"hi":1417.6,"votes":3246,"pct":36.4,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":60,"date":"2026-10-19","rating":1253.7,"lo":1243.1,"hi":1264.4,"votes":4111,"pct":64.5,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1483.5,"rank":51,"pct":87.9,"board_size":414},"math":{"rating":1441.8,"rank":82,"pct":80,"board_size":405},"creative_writing":{"rating":1382,"rank":129,"pct":69.2,"board_size":417},"instruction_following":{"rating":1429.8,"rank":76,"pct":82.1,"board_size":419},"hard_prompts":{"rating":1443.1,"rank":90,"pct":78.7,"board_size":419},"multi_turn":{"rating":1427.4,"rank":107,"pct":74.5,"board_size":417},"longer_query":{"rating":1435.5,"rank":87,"pct":78.3,"board_size":397},"non_english":{"rating":1406.3,"rank":115,"pct":72.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"moonshotai/kimi-k2.5","input_per_m":0.5,"output_per_m":2.5,"blended_per_m":1,"context_length":262144,"modalities_in":["text","image"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/kimi-k2-5-instant"},{"slug":"qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","source_name":"Qwen3-VL-235B-A22B-Instruct","base":"Qwen3 VL 235B A22B Instruct","variant":null,"org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":71.4,"rank":76,"coverage":0.75,"categories":{"coding":70.5,"reasoning":72.7,"math":71.8,"chat":72.5,"instructions":72.7}},"arena":{"text":{"rank":116,"date":"2026-10-28","rating":1420,"lo":1413.5,"hi":1426.5,"votes":11314,"pct":72.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":67,"date":"2026-10-19","rating":1247,"lo":1240.1,"hi":1253.9,"votes":12724,"pct":60.2,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1438.2,"rank":123,"pct":70.5,"board_size":414},"math":{"rating":1425.3,"rank":115,"pct":71.8,"board_size":405},"creative_writing":{"rating":1365.6,"rank":149,"pct":64.4,"board_size":417},"instruction_following":{"rating":1406.2,"rank":114,"pct":72.7,"board_size":419},"hard_prompts":{"rating":1428.2,"rank":115,"pct":72.7,"board_size":419},"multi_turn":{"rating":1428,"rank":106,"pct":74.8,"board_size":417},"longer_query":{"rating":1419.6,"rank":112,"pct":72,"board_size":397},"non_english":{"rating":1404.5,"rank":123,"pct":70.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"qwen/qwen3-vl-235b-a22b-instruct","input_per_m":0.21,"output_per_m":1.9,"blended_per_m":0.6325,"context_length":262144,"modalities_in":["text","image"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/qwen3-vl-235b-a22b-instruct"},{"slug":"deepseek-v3-2-thinking","name":"DeepSeek-V3.2 (Thinking)","source_name":"DeepSeek-V3.2 (Thinking)","base":"DeepSeek-V3.2","variant":"Thinking","org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":61.5,"rank":131,"coverage":0.75,"categories":{"coding":50.4,"reasoning":73.7,"math":70.8,"chat":72.2,"instructions":73.9}},"arena":{"text":{"rank":117,"date":"2026-10-28","rating":1419.8,"lo":1416.2,"hi":1423.3,"votes":42033,"pct":72.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":115,"date":"2026-10-28","rating":1362.5,"lo":1353.4,"hi":1371.6,"votes":6860,"pct":24.5,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1453.2,"rank":99,"pct":76.3,"board_size":414},"math":{"rating":1422.3,"rank":119,"pct":70.8,"board_size":405},"creative_writing":{"rating":1389,"rank":120,"pct":71.4,"board_size":417},"instruction_following":{"rating":1408.4,"rank":110,"pct":73.9,"board_size":419},"hard_prompts":{"rating":1430.5,"rank":111,"pct":73.7,"board_size":419},"multi_turn":{"rating":1424.1,"rank":113,"pct":73.1,"board_size":417},"longer_query":{"rating":1425.8,"rank":103,"pct":74.2,"board_size":397},"non_english":{"rating":1398.7,"rank":138,"pct":67.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"deepseek/deepseek-v3.2","input_per_m":0.26,"output_per_m":0.38,"blended_per_m":0.29,"context_length":163840,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/deepseek-v3-2-thinking"},{"slug":"deepseek-v3-1","name":"DeepSeek-V3.1","source_name":"DeepSeek-V3.1","base":"DeepSeek-V3.1","variant":null,"org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":64.8,"rank":114,"coverage":0.75,"categories":{"coding":61.7,"reasoning":65.6,"math":69.3,"chat":71.8,"instructions":65.1}},"arena":{"text":{"rank":118,"date":"2026-10-28","rating":1419.5,"lo":1413.5,"hi":1425.6,"votes":14606,"pct":71.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1413.5,"rank":159,"pct":61.7,"board_size":414},"math":{"rating":1419.7,"rank":125,"pct":69.3,"board_size":405},"creative_writing":{"rating":1387.6,"rank":123,"pct":70.7,"board_size":417},"instruction_following":{"rating":1388.2,"rank":147,"pct":65.1,"board_size":419},"hard_prompts":{"rating":1414.2,"rank":145,"pct":65.6,"board_size":419},"multi_turn":{"rating":1399.9,"rank":154,"pct":63.2,"board_size":417},"longer_query":{"rating":1399.3,"rank":152,"pct":61.6,"board_size":397},"non_english":{"rating":1399.5,"rank":137,"pct":67.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"deepseek/deepseek-chat-v3.1","input_per_m":0.25,"output_per_m":0.95,"blended_per_m":0.425,"context_length":163840,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/deepseek-v3-1"},{"slug":"amazon-nova-experimental-chat-12-10","name":"Amazon Nova Experimental Chat (12-10)","source_name":"amazon-nova-experimental-chat (12-10)","base":"Amazon Nova Experimental Chat","variant":"12-10","org":"amazon","open_weights":false,"model_license":"Proprietary","siscope":{"score":67.8,"rank":96,"coverage":0.75,"categories":{"coding":66.8,"reasoning":71.8,"math":68.8,"chat":71.8,"instructions":64.1}},"arena":{"text":{"rank":119,"date":"2026-10-28","rating":1419.5,"lo":1410.1,"hi":1428.9,"votes":3734,"pct":71.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1430.2,"rank":138,"pct":66.8,"board_size":414},"math":{"rating":1419.2,"rank":127,"pct":68.8,"board_size":405},"creative_writing":{"rating":1349.8,"rank":166,"pct":60.3,"board_size":417},"instruction_following":{"rating":1386.2,"rank":151,"pct":64.1,"board_size":419},"hard_prompts":{"rating":1427.2,"rank":119,"pct":71.8,"board_size":419},"multi_turn":{"rating":1408.8,"rank":141,"pct":66.3,"board_size":417},"longer_query":{"rating":1390.2,"rank":166,"pct":58.3,"board_size":397},"non_english":{"rating":1398.1,"rank":139,"pct":67,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/amazon-nova-experimental-chat-12-10"},{"slug":"claude-opus-4-1-thinking-16k-20250805","name":"Claude Opus 4.1 (Thinking 16K, 2025-08-05)","source_name":"Claude Opus 4.1 (Thinking 16K, 20250805)","base":"Claude Opus 4.1","variant":"Thinking 16K, 2025-08-05","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":69.9,"rank":85,"coverage":0.75,"categories":{"coding":86.2,"reasoning":65.6,"math":59.9,"chat":71.1,"instructions":84.2}},"arena":{"text":{"rank":120,"date":"2026-10-28","rating":1419.2,"lo":1415.8,"hi":1422.7,"votes":49535,"pct":71.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1478.8,"rank":58,"pct":86.2,"board_size":414},"math":{"rating":1431,"rank":103,"pct":74.8,"board_size":405},"creative_writing":{"rating":1411.8,"rank":81,"pct":80.8,"board_size":417},"instruction_following":{"rating":1435.5,"rank":67,"pct":84.2,"board_size":419},"hard_prompts":{"rating":1442.4,"rank":92,"pct":78.2,"board_size":419},"multi_turn":{"rating":1444.3,"rank":78,"pct":81.5,"board_size":417},"longer_query":{"rating":1454.8,"rank":59,"pct":85.4,"board_size":397},"non_english":{"rating":1403.7,"rank":128,"pct":69.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.7727,"stderr":0.0299,"tested_as":"claude-opus-4-1-20250805_16K","approx":false,"run_date":"2025-08-05","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FerLgyKQs2mg2memE9SJvK5.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":53,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.6444,"stderr":0.0722,"tested_as":"claude-opus-4-1-20250805_16K","approx":false,"run_date":"2025-08-05","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Fkf9vy9sMjMBBswrX6NMzce.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":44.9,"tested_models":313}],"price":{"openrouter_id":"anthropic/claude-opus-4.1","input_per_m":15,"output_per_m":75,"blended_per_m":30,"context_length":200000,"modalities_in":["image","text","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-opus-4-1-thinking-16k-20250805"},{"slug":"gpt-5-5-instant","name":"GPT-5.5 Instant","source_name":"GPT-5.5 Instant","base":"GPT-5.5 Instant","variant":null,"org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":61.1,"rank":134,"coverage":0.75,"categories":{"coding":68,"reasoning":66.7,"math":50.1,"chat":71.1,"instructions":72.7}},"arena":{"text":{"rank":121,"date":"2026-10-28","rating":1419.2,"lo":1414.3,"hi":1424.1,"votes":27128,"pct":71.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":63,"date":"2026-10-19","rating":1249.8,"lo":1241.2,"hi":1258.4,"votes":7590,"pct":62.7,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1433.3,"rank":133,"pct":68,"board_size":414},"math":{"rating":1419.6,"rank":126,"pct":69.1,"board_size":405},"creative_writing":{"rating":1417.6,"rank":71,"pct":83.2,"board_size":417},"instruction_following":{"rating":1406.2,"rank":115,"pct":72.7,"board_size":419},"hard_prompts":{"rating":1426.1,"rank":122,"pct":71.1,"board_size":419},"multi_turn":{"rating":1433.5,"rank":97,"pct":76.9,"board_size":417},"longer_query":{"rating":1421.9,"rank":108,"pct":73,"board_size":397},"non_english":{"rating":1416.9,"rank":99,"pct":76.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8251,"stderr":0.0225,"tested_as":"gpt-5.5-instant","approx":false,"run_date":"2026-08-02","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FWPVhgi8NT9grAT7kfipT9G.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":62.3,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.6806,"stderr":0.0621,"tested_as":"gpt-5.5-instant","approx":false,"run_date":"2026-08-02","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FhGzLQWbxPdgQiiMbaDqF8k.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":48.1,"tested_models":313},{"benchmark":"frontiermath","score":0.2632,"stderr":0.0261,"tested_as":"gpt-5.5-instant","approx":false,"run_date":"2026-08-02","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FgGcHjE6ppy54ahN2pfxsGH.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":33.1,"tested_models":122}],"price":null,"url":"https://siscope.app/models/gpt-5-5-instant"},{"slug":"qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct (2507)","source_name":"Qwen3-235B-A22B-Instruct (2507)","base":"Qwen3 235B A22B Instruct","variant":"2507","org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":73,"rank":72,"coverage":0.75,"categories":{"coding":72.9,"reasoning":74.6,"math":75,"chat":71.1,"instructions":73.7}},"arena":{"text":{"rank":122,"date":"2026-10-28","rating":1419.2,"lo":1416.6,"hi":1421.7,"votes":98081,"pct":71.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1444.5,"rank":113,"pct":72.9,"board_size":414},"math":{"rating":1431.6,"rank":101,"pct":75,"board_size":405},"creative_writing":{"rating":1374.8,"rank":140,"pct":66.6,"board_size":417},"instruction_following":{"rating":1407.8,"rank":111,"pct":73.7,"board_size":419},"hard_prompts":{"rating":1433.3,"rank":107,"pct":74.6,"board_size":419},"multi_turn":{"rating":1432.1,"rank":100,"pct":76,"board_size":417},"longer_query":{"rating":1425.9,"rank":102,"pct":74.5,"board_size":397},"non_english":{"rating":1409.3,"rank":109,"pct":74.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen3-235b-a22b-instruct-2507"},{"slug":"deepseek-v3-1-terminus-thinking","name":"DeepSeek V3.1 Terminus (Thinking)","source_name":"DeepSeek-V3.1-Terminus (Thinking)","base":"DeepSeek V3.1 Terminus","variant":"Thinking","org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"coding":65.1,"reasoning":70.8,"chat":70.8,"instructions":71.5}},"arena":{"text":{"rank":123,"date":"2026-10-28","rating":1419.1,"lo":1409,"hi":1429.2,"votes":3379,"pct":70.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1425.3,"rank":145,"pct":65.1,"board_size":414},"creative_writing":{"rating":1390.7,"rank":116,"pct":72.4,"board_size":417},"instruction_following":{"rating":1404.7,"rank":120,"pct":71.5,"board_size":419},"hard_prompts":{"rating":1426,"rank":123,"pct":70.8,"board_size":419},"multi_turn":{"rating":1410.8,"rank":137,"pct":67.3,"board_size":417},"longer_query":{"rating":1421.4,"rank":111,"pct":72.2,"board_size":397},"non_english":{"rating":1405.2,"rank":118,"pct":72,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"deepseek/deepseek-v3.1-terminus","input_per_m":0.27,"output_per_m":1,"blended_per_m":0.4525,"context_length":163840,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/deepseek-v3-1-terminus-thinking"},{"slug":"claude-opus-4-1-20250805","name":"Claude Opus 4.1 (2025-08-05)","source_name":"Claude Opus 4.1 (20250805)","base":"Claude Opus 4.1","variant":"2025-08-05","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":56.1,"rank":155,"coverage":0.75,"categories":{"coding":52,"reasoning":61.3,"math":49.2,"chat":70.6,"instructions":83.3}},"arena":{"text":{"rank":124,"date":"2026-10-28","rating":1418.6,"lo":1415.6,"hi":1421.5,"votes":77213,"pct":70.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":106,"date":"2026-10-28","rating":1390.2,"lo":1379.4,"hi":1400.9,"votes":6904,"pct":30.5,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1472.4,"rank":66,"pct":84.3,"board_size":414},"math":{"rating":1421.5,"rank":123,"pct":69.8,"board_size":405},"creative_writing":{"rating":1410.3,"rank":83,"pct":80.3,"board_size":417},"instruction_following":{"rating":1433.5,"rank":71,"pct":83.3,"board_size":419},"hard_prompts":{"rating":1442.1,"rank":93,"pct":78,"board_size":419},"multi_turn":{"rating":1443.2,"rank":82,"pct":80.5,"board_size":417},"longer_query":{"rating":1444.2,"rank":73,"pct":81.8,"board_size":397},"non_english":{"rating":1405.3,"rank":116,"pct":72.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.7323,"stderr":0.0315,"tested_as":"claude-opus-4-1-20250805","approx":false,"run_date":"2025-08-05","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Fj62bkFDjBSeFyVpnGzuzg4.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":44.6,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.4,"stderr":0.0739,"tested_as":"claude-opus-4-1-20250805","approx":false,"run_date":"2025-08-05","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FRaiKuDSzUJYDVMxn4jfzNC.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":28.5,"tested_models":313},{"benchmark":"swe_bench_verified","score":0.7335,"stderr":0.0201,"tested_as":"claude-opus-4-1-20250805","approx":false,"run_date":"2026-02-11","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FcA6Mq67yaynLhY8F5kes3c.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":41.2,"tested_models":35}],"price":{"openrouter_id":"anthropic/claude-opus-4.1","input_per_m":15,"output_per_m":75,"blended_per_m":30,"context_length":200000,"modalities_in":["image","text","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-opus-4-1-20250805"},{"slug":"qwen3-5-122b-a10b","name":"Qwen3.5 122B A10B","source_name":"Qwen3.5-122B-A10B","base":"Qwen3.5 122B A10B","variant":null,"org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":58.6,"rank":141,"coverage":0.75,"categories":{"coding":46.3,"reasoning":68.7,"math":75,"chat":70.3,"instructions":68.2}},"arena":{"text":{"rank":125,"date":"2026-10-28","rating":1417.5,"lo":1413.3,"hi":1421.8,"votes":29712,"pct":70.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":116,"date":"2026-10-28","rating":1360.4,"lo":1352.7,"hi":1368,"votes":8210,"pct":23.8,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":70,"date":"2026-10-19","rating":1244.5,"lo":1237.7,"hi":1251.3,"votes":13236,"pct":58.4,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1435.6,"rank":130,"pct":68.8,"board_size":414},"math":{"rating":1431.6,"rank":102,"pct":75,"board_size":405},"creative_writing":{"rating":1368.7,"rank":147,"pct":64.9,"board_size":417},"instruction_following":{"rating":1399.5,"rank":134,"pct":68.2,"board_size":419},"hard_prompts":{"rating":1421.3,"rank":132,"pct":68.7,"board_size":419},"multi_turn":{"rating":1416.7,"rank":124,"pct":70.4,"board_size":417},"longer_query":{"rating":1410.5,"rank":130,"pct":67.4,"board_size":397},"non_english":{"rating":1400.6,"rank":133,"pct":68.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"qwen/qwen3.5-122b-a10b","input_per_m":0.26,"output_per_m":2.08,"blended_per_m":0.715,"context_length":262144,"modalities_in":["text","image","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/qwen3-5-122b-a10b"},{"slug":"gpt-4-5-preview-2025-02-27","name":"GPT-4.5 Preview (2025-02-27)","source_name":"GPT-4.5 Preview (2025-02-27)","base":"GPT-4.5 Preview","variant":"2025-02-27","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":53.1,"rank":167,"coverage":0.75,"categories":{"coding":56.4,"reasoning":50.7,"math":45.9,"chat":70.1,"instructions":70.8}},"arena":{"text":{"rank":126,"date":"2026-10-28","rating":1417.3,"lo":1411.7,"hi":1423,"votes":14547,"pct":70.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":97,"date":"2026-10-19","rating":1194.9,"lo":1183.2,"hi":1206.6,"votes":2925,"pct":42.2,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1396.3,"rank":181,"pct":56.4,"board_size":414},"math":{"rating":1412,"rank":143,"pct":64.9,"board_size":405},"creative_writing":{"rating":1393.5,"rank":111,"pct":73.3,"board_size":417},"instruction_following":{"rating":1403.7,"rank":123,"pct":70.8,"board_size":419},"hard_prompts":{"rating":1403.4,"rank":163,"pct":61.2,"board_size":419},"multi_turn":{"rating":1444,"rank":81,"pct":80.8,"board_size":417},"longer_query":{"rating":1405.5,"rank":141,"pct":64.6,"board_size":397},"non_english":{"rating":1412.8,"rank":103,"pct":75.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.6869,"stderr":0.033,"tested_as":"gpt-4.5-preview-2025-02-27","approx":false,"run_date":"2025-02-28","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FdodibSv7pk8GtqeMy4YLQg.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":40.1,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.3778,"stderr":0.0731,"tested_as":"gpt-4.5-preview-2025-02-27","approx":false,"run_date":"2025-02-28","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F9DCJMt7YsTMDenTdX4Db6V.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":26.9,"tested_models":313}],"price":null,"url":"https://siscope.app/models/gpt-4-5-preview-2025-02-27"},{"slug":"deepseek-v3-1-terminus","name":"DeepSeek V3.1 Terminus","source_name":"DeepSeek-V3.1-Terminus","base":"DeepSeek V3.1 Terminus","variant":null,"org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":61.2,"rank":133,"coverage":0.75,"categories":{"coding":59.1,"reasoning":62.4,"math":60.4,"chat":69.9,"instructions":62.4}},"arena":{"text":{"rank":127,"date":"2026-10-28","rating":1417.1,"lo":1407.4,"hi":1426.8,"votes":3609,"pct":69.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1406.7,"rank":170,"pct":59.1,"board_size":414},"math":{"rating":1401.7,"rank":161,"pct":60.4,"board_size":405},"creative_writing":{"rating":1403.3,"rank":90,"pct":78.4,"board_size":417},"instruction_following":{"rating":1380.7,"rank":158,"pct":62.4,"board_size":419},"hard_prompts":{"rating":1406.1,"rank":158,"pct":62.4,"board_size":419},"multi_turn":{"rating":1387.9,"rank":171,"pct":59.1,"board_size":417},"longer_query":{"rating":1395.9,"rank":156,"pct":60.9,"board_size":397},"non_english":{"rating":1407.5,"rank":113,"pct":73.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"deepseek/deepseek-v3.1-terminus","input_per_m":0.27,"output_per_m":1,"blended_per_m":0.4525,"context_length":163840,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/deepseek-v3-1-terminus"},{"slug":"qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","source_name":"Qwen3-Next-80B-A3B-Instruct","base":"Qwen3 Next 80B A3B Instruct","variant":null,"org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":70.8,"rank":79,"coverage":0.75,"categories":{"coding":71.7,"reasoning":72,"math":78.7,"chat":69.6,"instructions":65.6}},"arena":{"text":{"rank":128,"date":"2026-10-28","rating":1417,"lo":1412.3,"hi":1421.7,"votes":22753,"pct":69.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1440.5,"rank":118,"pct":71.7,"board_size":414},"math":{"rating":1439.9,"rank":87,"pct":78.7,"board_size":405},"creative_writing":{"rating":1333.4,"rank":189,"pct":54.8,"board_size":417},"instruction_following":{"rating":1388.4,"rank":145,"pct":65.6,"board_size":419},"hard_prompts":{"rating":1427.5,"rank":118,"pct":72,"board_size":419},"multi_turn":{"rating":1415.6,"rank":127,"pct":69.7,"board_size":417},"longer_query":{"rating":1402.4,"rank":145,"pct":63.6,"board_size":397},"non_english":{"rating":1406.9,"rank":114,"pct":73,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"qwen/qwen3-next-80b-a3b-instruct","input_per_m":0.1,"output_per_m":1.1,"blended_per_m":0.35,"context_length":262144,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/qwen3-next-80b-a3b-instruct"},{"slug":"gemini-2-5-flash","name":"Gemini 2.5 Flash","source_name":"Gemini 2.5 Flash","base":"Gemini 2.5 Flash","variant":null,"org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":66.2,"rank":99,"coverage":0.75,"categories":{"coding":64.4,"reasoning":69.1,"math":64.6,"chat":69.4,"instructions":71.8}},"arena":{"text":{"rank":129,"date":"2026-10-28","rating":1416.9,"lo":1414.5,"hi":1419.3,"votes":125457,"pct":69.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":76,"date":"2026-10-19","rating":1235.5,"lo":1230.9,"hi":1240,"votes":60087,"pct":54.8,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1423.4,"rank":148,"pct":64.4,"board_size":414},"math":{"rating":1410.7,"rank":144,"pct":64.6,"board_size":405},"creative_writing":{"rating":1399.9,"rank":103,"pct":75.5,"board_size":417},"instruction_following":{"rating":1404.9,"rank":119,"pct":71.8,"board_size":419},"hard_prompts":{"rating":1422,"rank":130,"pct":69.1,"board_size":419},"multi_turn":{"rating":1407.9,"rank":143,"pct":65.9,"board_size":417},"longer_query":{"rating":1418.8,"rank":113,"pct":71.7,"board_size":397},"non_english":{"rating":1409.2,"rank":110,"pct":73.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"google/gemini-2.5-flash","input_per_m":0.3,"output_per_m":2.5,"blended_per_m":0.85,"context_length":1048576,"modalities_in":["file","image","text","audio","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gemini-2-5-flash"},{"slug":"deepseek-v3-1-thinking","name":"DeepSeek-V3.1 (Thinking)","source_name":"DeepSeek-V3.1 (Thinking)","base":"DeepSeek-V3.1","variant":"Thinking","org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":65.2,"rank":108,"coverage":0.75,"categories":{"coding":63,"reasoning":67,"math":66.3,"chat":69.1,"instructions":69.1}},"arena":{"text":{"rank":130,"date":"2026-10-28","rating":1416.6,"lo":1410,"hi":1423.2,"votes":11458,"pct":69.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1416.8,"rank":154,"pct":63,"board_size":414},"math":{"rating":1414.8,"rank":137,"pct":66.3,"board_size":405},"creative_writing":{"rating":1400.8,"rank":100,"pct":76,"board_size":417},"instruction_following":{"rating":1400.4,"rank":130,"pct":69.1,"board_size":419},"hard_prompts":{"rating":1416.8,"rank":139,"pct":67,"board_size":419},"multi_turn":{"rating":1407.6,"rank":144,"pct":65.6,"board_size":417},"longer_query":{"rating":1421.6,"rank":110,"pct":72.5,"board_size":397},"non_english":{"rating":1399.9,"rank":135,"pct":67.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"deepseek/deepseek-chat-v3.1","input_per_m":0.25,"output_per_m":0.95,"blended_per_m":0.425,"context_length":163840,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/deepseek-v3-1-thinking"},{"slug":"gpt-5-2-high","name":"GPT-5.2 (High)","source_name":"GPT-5.2 (High)","base":"GPT-5.2","variant":"High","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":65.3,"rank":105,"coverage":0.75,"categories":{"coding":59.5,"reasoning":63.4,"math":82,"chat":68.9,"instructions":74.4}},"arena":{"text":{"rank":131,"date":"2026-10-28","rating":1416.3,"lo":1412.7,"hi":1419.8,"votes":49628,"pct":68.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":68,"date":"2026-10-19","rating":1245.8,"lo":1239.7,"hi":1251.8,"votes":19022,"pct":59.6,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1441.6,"rank":117,"pct":71.9,"board_size":414},"math":{"rating":1439.9,"rank":86,"pct":78.7,"board_size":405},"creative_writing":{"rating":1375.9,"rank":137,"pct":67.1,"board_size":417},"instruction_following":{"rating":1409.3,"rank":108,"pct":74.4,"board_size":419},"hard_prompts":{"rating":1428.1,"rank":116,"pct":72.5,"board_size":419},"multi_turn":{"rating":1419.2,"rank":117,"pct":72.1,"board_size":417},"longer_query":{"rating":1408.5,"rank":134,"pct":66.4,"board_size":397},"non_english":{"rating":1404.8,"rank":120,"pct":71.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8819,"stderr":0.0191,"tested_as":"gpt-5.2-2025-12-11_high","approx":false,"run_date":"2025-12-11","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F3Q6osT8EYezayG7yfxkSpr.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":78.3,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.343,"stderr":0.015,"tested_as":"gpt-5.2-2025-12-11_high","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FXp4qkZ32zjDeSYii2eQpnm.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":39.4,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9611,"stderr":0.026,"tested_as":"gpt-5.2-2025-12-11_high","approx":false,"run_date":"2025-12-11","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FLiUMZyNSM8q93KDubWgYCh.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":85.3,"tested_models":313},{"benchmark":"swe_bench_verified","score":0.7376,"stderr":0.02,"tested_as":"gpt-5.2-2025-12-11_high","approx":false,"run_date":"2026-02-12","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F9owdbpnWJ5pkQQC3GWKP5L.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":47.1,"tested_models":35}],"price":{"openrouter_id":"openai/gpt-5.2","input_per_m":1.75,"output_per_m":14,"blended_per_m":4.8125,"context_length":400000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-2-high"},{"slug":"gemini-3-1-flash-lite-preview","name":"Gemini 3.1 Flash-Lite Preview","source_name":"Gemini 3.1 Flash-Lite Preview","base":"Gemini 3.1 Flash-Lite Preview","variant":null,"org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":50.4,"rank":182,"coverage":0.75,"categories":{"coding":33.8,"reasoning":62.9,"math":73.5,"chat":68.7,"instructions":61.5}},"arena":{"text":{"rank":132,"date":"2026-10-28","rating":1415.8,"lo":1412.2,"hi":1419.4,"votes":64196,"pct":68.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":137,"date":"2026-10-28","rating":1256.3,"lo":1249.4,"hi":1263.1,"votes":14350,"pct":9.9,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":73,"date":"2026-10-19","rating":1240.2,"lo":1234.4,"hi":1245.9,"votes":27657,"pct":56.6,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1400.1,"rank":176,"pct":57.6,"board_size":414},"math":{"rating":1427.8,"rank":108,"pct":73.5,"board_size":405},"creative_writing":{"rating":1400.8,"rank":101,"pct":76,"board_size":417},"instruction_following":{"rating":1377.2,"rank":162,"pct":61.5,"board_size":419},"hard_prompts":{"rating":1407.3,"rank":155,"pct":62.9,"board_size":419},"multi_turn":{"rating":1416.9,"rank":123,"pct":70.7,"board_size":417},"longer_query":{"rating":1394.2,"rank":159,"pct":60.1,"board_size":397},"non_english":{"rating":1410.4,"rank":106,"pct":74.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"google/gemini-3.1-flash-lite-preview","input_per_m":0.25,"output_per_m":1.5,"blended_per_m":0.5625,"context_length":1048576,"modalities_in":["text","image","video","file","audio"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gemini-3-1-flash-lite-preview"},{"slug":"qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22B Thinking (2507)","source_name":"Qwen3-235B-A22B-Thinking (2507)","base":"Qwen3 235B A22B Thinking","variant":"2507","org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":65.3,"rank":107,"coverage":0.75,"categories":{"coding":64.6,"reasoning":66.7,"math":65.1,"chat":68.4,"instructions":63.9}},"arena":{"text":{"rank":133,"date":"2026-10-28","rating":1415.3,"lo":1408.8,"hi":1421.8,"votes":8822,"pct":68.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1424.2,"rank":147,"pct":64.6,"board_size":414},"math":{"rating":1412.2,"rank":142,"pct":65.1,"board_size":405},"creative_writing":{"rating":1383.5,"rank":128,"pct":69.5,"board_size":417},"instruction_following":{"rating":1385.9,"rank":152,"pct":63.9,"board_size":419},"hard_prompts":{"rating":1416,"rank":140,"pct":66.7,"board_size":419},"multi_turn":{"rating":1406.4,"rank":145,"pct":65.4,"board_size":417},"longer_query":{"rating":1399.3,"rank":153,"pct":61.6,"board_size":397},"non_english":{"rating":1397.3,"rank":141,"pct":66.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen3-235b-a22b-thinking-2507"},{"slug":"amazon-nova-experimental-chat-11-10","name":"Amazon Nova Experimental Chat (11-10)","source_name":"amazon-nova-experimental-chat (11-10)","base":"Amazon Nova Experimental Chat","variant":"11-10","org":"amazon","open_weights":false,"model_license":"Proprietary","siscope":{"score":68,"rank":94,"coverage":0.75,"categories":{"coding":67.6,"reasoning":68.9,"math":74.5,"chat":68.2,"instructions":64.4}},"arena":{"text":{"rank":134,"date":"2026-10-28","rating":1415,"lo":1410.8,"hi":1419.2,"votes":26026,"pct":68.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1433.1,"rank":135,"pct":67.6,"board_size":414},"math":{"rating":1430.9,"rank":104,"pct":74.5,"board_size":405},"creative_writing":{"rating":1349.3,"rank":168,"pct":59.9,"board_size":417},"instruction_following":{"rating":1386.6,"rank":150,"pct":64.4,"board_size":419},"hard_prompts":{"rating":1421.8,"rank":131,"pct":68.9,"board_size":419},"multi_turn":{"rating":1379.9,"rank":178,"pct":57.5,"board_size":417},"longer_query":{"rating":1394.9,"rank":158,"pct":60.4,"board_size":397},"non_english":{"rating":1404.5,"rank":124,"pct":70.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/amazon-nova-experimental-chat-11-10"},{"slug":"kimi-k2-thinking-turbo","name":"Kimi K2 Thinking Turbo","source_name":"Kimi K2 Thinking Turbo","base":"Kimi K2 Thinking Turbo","variant":null,"org":"moonshot","open_weights":true,"model_license":"Modified MIT","siscope":{"score":57.3,"rank":148,"coverage":0.75,"categories":{"coding":45.7,"reasoning":69.6,"math":68.2,"chat":67.9,"instructions":70.3}},"arena":{"text":{"rank":135,"date":"2026-10-28","rating":1414.4,"lo":1411.3,"hi":1417.4,"votes":63310,"pct":67.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":130,"date":"2026-10-28","rating":1321.9,"lo":1314.5,"hi":1329.4,"votes":13045,"pct":14.6,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1453.5,"rank":97,"pct":76.8,"board_size":414},"math":{"rating":1429,"rank":107,"pct":73.8,"board_size":405},"creative_writing":{"rating":1373.3,"rank":143,"pct":65.9,"board_size":417},"instruction_following":{"rating":1403.1,"rank":124,"pct":70.3,"board_size":419},"hard_prompts":{"rating":1427.8,"rank":117,"pct":72.2,"board_size":419},"multi_turn":{"rating":1414.1,"rank":129,"pct":69.2,"board_size":417},"longer_query":{"rating":1415,"rank":119,"pct":69.9,"board_size":397},"non_english":{"rating":1397.5,"rank":140,"pct":66.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8422,"stderr":0.0209,"tested_as":"kimi-k2-thinking-turbo","approx":false,"run_date":"2025-11-11","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FmuGecFpAg9wHd6gexWJ99L.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":66.9,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.8306,"stderr":0.0482,"tested_as":"kimi-k2-thinking-turbo","approx":false,"run_date":"2025-11-13","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F8BM7dCHaUZgcYJwZWiBhiQ.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":62.5,"tested_models":313}],"price":null,"url":"https://siscope.app/models/kimi-k2-thinking-turbo"},{"slug":"inkling-small","name":"Inkling Small","source_name":"Inkling-Small","base":"Inkling Small","variant":null,"org":"thinky","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":51.6,"rank":173,"coverage":1,"categories":{"coding":56.5,"agents":1.8,"reasoning":70.1,"math":84.9,"chat":67.7,"instructions":69.6}},"arena":{"text":{"rank":136,"date":"2026-10-28","rating":1414.3,"lo":1409.8,"hi":1418.8,"votes":36999,"pct":67.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":95,"date":"2026-10-28","rating":1409.1,"lo":1400,"hi":1418.2,"votes":5295,"pct":37.7,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":75,"date":"2026-10-19","rating":1236.8,"lo":1228.7,"hi":1244.9,"votes":8074,"pct":55.4,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":56,"date":"2026-11-02","score":-0.1689,"lo":-0.1876,"hi":-0.1503,"sessions":14746,"cost_per_task_p50":0.188,"pct":1.8,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1450.9,"rank":103,"pct":75.3,"board_size":414},"math":{"rating":1458.3,"rank":62,"pct":84.9,"board_size":405},"creative_writing":{"rating":1335.7,"rank":187,"pct":55.3,"board_size":417},"instruction_following":{"rating":1400.9,"rank":128,"pct":69.6,"board_size":419},"hard_prompts":{"rating":1424.2,"rank":126,"pct":70.1,"board_size":419},"multi_turn":{"rating":1415.9,"rank":126,"pct":70,"board_size":417},"longer_query":{"rating":1403.9,"rank":144,"pct":63.9,"board_size":397},"non_english":{"rating":1402.6,"rank":130,"pct":69.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"thinkingmachines/inkling-small","input_per_m":0.45,"output_per_m":1.2,"blended_per_m":0.6375,"context_length":524288,"modalities_in":["text","image","audio"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/inkling-small"},{"slug":"qwen3-max-2025-09-23","name":"Qwen3-Max (2025-09-23)","source_name":"Qwen3-Max (2025-09-23)","base":"Qwen3-Max","variant":"2025-09-23","org":"alibaba","open_weights":false,"model_license":"Proprietary","siscope":{"score":60.2,"rank":137,"coverage":0.75,"categories":{"coding":70.9,"reasoning":60.9,"math":50.5,"chat":67.5,"instructions":67.7}},"arena":{"text":{"rank":137,"date":"2026-10-28","rating":1413,"lo":1406.5,"hi":1419.4,"votes":9026,"pct":67.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1438.6,"rank":121,"pct":70.9,"board_size":414},"math":{"rating":1435.5,"rank":93,"pct":77.2,"board_size":405},"creative_writing":{"rating":1380.8,"rank":131,"pct":68.8,"board_size":417},"instruction_following":{"rating":1397.9,"rank":136,"pct":67.7,"board_size":419},"hard_prompts":{"rating":1423.4,"rank":128,"pct":69.6,"board_size":419},"multi_turn":{"rating":1434.5,"rank":95,"pct":77.2,"board_size":417},"longer_query":{"rating":1410.3,"rank":131,"pct":67.2,"board_size":397},"non_english":{"rating":1400.1,"rank":134,"pct":68.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.726,"stderr":0.0273,"tested_as":"qwen3-max-2025-09-23","approx":false,"run_date":"2025-10-06","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F46RCssznDADYeg8MuSgvsj.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":44.3,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.4875,"stderr":0.0158,"tested_as":"qwen3-max-2025-09-23","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FfXG2GPt5F25tHRTPhAoZ4K.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":68.7,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.7333,"stderr":0.0591,"tested_as":"qwen3-max-2025-09-23","approx":false,"run_date":"2025-10-06","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FULeuPtwp3ZoyuXQYuuQ82i.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":53.5,"tested_models":313},{"benchmark":"frontiermath","score":0.1895,"stderr":0.0233,"tested_as":"qwen3-max-2025-09-23","approx":false,"run_date":"2026-08-30","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FNrTH3EYHjp4hPdxgpCPGTX.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":20.7,"tested_models":122}],"price":null,"url":"https://siscope.app/models/qwen3-max-2025-09-23"},{"slug":"gpt-5-2","name":"GPT-5.2","source_name":"GPT-5.2","base":"GPT-5.2","variant":null,"org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":56.7,"rank":152,"coverage":0.75,"categories":{"coding":53.1,"reasoning":58.1,"math":55.4,"chat":67.2,"instructions":70.1}},"arena":{"text":{"rank":138,"date":"2026-10-28","rating":1412.3,"lo":1409.1,"hi":1415.4,"votes":83793,"pct":67.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":93,"date":"2026-10-28","rating":1416.4,"lo":1393.8,"hi":1439,"votes":1082,"pct":39.1,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":81,"date":"2026-10-19","rating":1228.6,"lo":1222.6,"hi":1234.6,"votes":20100,"pct":51.8,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1432,"rank":137,"pct":67.1,"board_size":414},"math":{"rating":1417.6,"rank":131,"pct":67.8,"board_size":405},"creative_writing":{"rating":1375.5,"rank":139,"pct":66.8,"board_size":417},"instruction_following":{"rating":1402.9,"rank":126,"pct":70.1,"board_size":419},"hard_prompts":{"rating":1426.9,"rank":120,"pct":71.5,"board_size":419},"multi_turn":{"rating":1418.4,"rank":119,"pct":71.6,"board_size":417},"longer_query":{"rating":1412.7,"rank":125,"pct":68.7,"board_size":397},"non_english":{"rating":1405.3,"rank":117,"pct":72.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.7323,"stderr":0.0315,"tested_as":"gpt-5.2-2025-12-11_none","approx":false,"run_date":"2026-07-13","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F4sPs53wmM9bvN8JXzsiNCk.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":44.6,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.6222,"stderr":0.0731,"tested_as":"gpt-5.2-2025-12-11_none","approx":false,"run_date":"2026-07-13","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FUBKiF8QVUmHwqgx4rF7CDA.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":42.9,"tested_models":313}],"price":{"openrouter_id":"openai/gpt-5.2","input_per_m":1.75,"output_per_m":14,"blended_per_m":4.8125,"context_length":400000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-2"},{"slug":"gpt-5-4-mini-high","name":"GPT-5.4 mini (High)","source_name":"GPT-5.4 mini (High)","base":"GPT-5.4 mini","variant":"High","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":57,"rank":149,"coverage":0.75,"categories":{"coding":51.6,"reasoning":53.1,"math":68.9,"chat":67,"instructions":72}},"arena":{"text":{"rank":139,"date":"2026-10-28","rating":1411.6,"lo":1407.9,"hi":1415.3,"votes":63432,"pct":67,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":103,"date":"2026-10-28","rating":1397.3,"lo":1390.8,"hi":1403.8,"votes":11893,"pct":32.5,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":69,"date":"2026-10-19","rating":1244.8,"lo":1238.6,"hi":1251,"votes":25734,"pct":59,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1438.3,"rank":122,"pct":70.7,"board_size":414},"math":{"rating":1418.2,"rank":130,"pct":68.1,"board_size":405},"creative_writing":{"rating":1370.4,"rank":145,"pct":65.4,"board_size":417},"instruction_following":{"rating":1405.1,"rank":118,"pct":72,"board_size":419},"hard_prompts":{"rating":1424.2,"rank":125,"pct":70.1,"board_size":419},"multi_turn":{"rating":1429.1,"rank":105,"pct":75,"board_size":417},"longer_query":{"rating":1407.5,"rank":136,"pct":65.9,"board_size":397},"non_english":{"rating":1404.9,"rank":119,"pct":71.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8359,"stderr":0.0223,"tested_as":"gpt-5.4-mini-2026-03-17_high","approx":false,"run_date":"2026-04-15","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FAQF46S9hBhosKPEMy3fyB9.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":66,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.294,"stderr":0.0144,"tested_as":"gpt-5.4-mini-2026-03-17_high","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FZ3pjKgAULY9j9wmzQpdqZG.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":23.2,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.8722,"stderr":0.0425,"tested_as":"gpt-5.4-mini-2026-03-17_high","approx":false,"run_date":"2026-04-15","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FZ5Sp2AKYzTBNdMEyTfTRuN.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":69.6,"tested_models":313}],"price":{"openrouter_id":"openai/gpt-5.4-mini","input_per_m":0.75,"output_per_m":4.5,"blended_per_m":1.6875,"context_length":400000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-4-mini-high"},{"slug":"grok-4-0709","name":"Grok 4 (0709)","source_name":"Grok 4 (0709)","base":"Grok 4","variant":"0709","org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":63.2,"rank":123,"coverage":0.75,"categories":{"coding":59.8,"reasoning":63.6,"math":71,"chat":66.7,"instructions":64.6}},"arena":{"text":{"rank":140,"date":"2026-10-28","rating":1411.4,"lo":1407.5,"hi":1415.4,"votes":39678,"pct":66.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":89,"date":"2026-10-19","rating":1210.2,"lo":1202.9,"hi":1217.5,"votes":30173,"pct":47,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1408.3,"rank":167,"pct":59.8,"board_size":414},"math":{"rating":1422.5,"rank":118,"pct":71,"board_size":405},"creative_writing":{"rating":1396.3,"rank":107,"pct":74.5,"board_size":417},"instruction_following":{"rating":1386.9,"rank":149,"pct":64.6,"board_size":419},"hard_prompts":{"rating":1408.7,"rank":153,"pct":63.6,"board_size":419},"multi_turn":{"rating":1416.4,"rank":125,"pct":70.2,"board_size":417},"longer_query":{"rating":1408.2,"rank":135,"pct":66.2,"board_size":397},"non_english":{"rating":1402.5,"rank":131,"pct":68.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/grok-4-0709"},{"slug":"mimo-v2-flash-non-thinking","name":"MiMo-V2-Flash (Non-Thinking)","source_name":"MiMo-V2-Flash (Non-Thinking)","base":"MiMo-V2-Flash","variant":"Non-Thinking","org":"xiaomi","open_weights":true,"model_license":"MIT","siscope":{"score":54.4,"rank":162,"coverage":0.75,"categories":{"coding":44.5,"reasoning":67.5,"math":57.9,"chat":66.5,"instructions":66}},"arena":{"text":{"rank":141,"date":"2026-10-28","rating":1410.9,"lo":1407.5,"hi":1414.4,"votes":48060,"pct":66.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":127,"date":"2026-10-28","rating":1330.6,"lo":1320.9,"hi":1340.4,"votes":5645,"pct":16.6,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1442.5,"rank":115,"pct":72.4,"board_size":414},"math":{"rating":1395.6,"rank":171,"pct":57.9,"board_size":405},"creative_writing":{"rating":1375.9,"rank":138,"pct":67.1,"board_size":417},"instruction_following":{"rating":1392.6,"rank":143,"pct":66,"board_size":419},"hard_prompts":{"rating":1419.8,"rank":136,"pct":67.5,"board_size":419},"multi_turn":{"rating":1403.8,"rank":151,"pct":63.9,"board_size":417},"longer_query":{"rating":1409.2,"rank":132,"pct":66.7,"board_size":397},"non_english":{"rating":1391.5,"rank":147,"pct":65.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/mimo-v2-flash-non-thinking"},{"slug":"o3-2025-04-16","name":"o3 (2025-04-16)","source_name":"o3 (2025-04-16)","base":"o3","variant":"2025-04-16","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":62.3,"rank":126,"coverage":0.75,"categories":{"coding":59.3,"reasoning":61,"math":72.8,"chat":66.3,"instructions":59.1}},"arena":{"text":{"rank":142,"date":"2026-10-28","rating":1409.8,"lo":1406.2,"hi":1413.4,"votes":58901,"pct":66.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":86,"date":"2026-10-19","rating":1214.3,"lo":1207.8,"hi":1220.8,"votes":45567,"pct":48.8,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1407.4,"rank":169,"pct":59.3,"board_size":414},"math":{"rating":1426.3,"rank":111,"pct":72.8,"board_size":405},"creative_writing":{"rating":1358.4,"rank":158,"pct":62,"board_size":417},"instruction_following":{"rating":1367.8,"rank":172,"pct":59.1,"board_size":419},"hard_prompts":{"rating":1402.1,"rank":164,"pct":61,"board_size":419},"multi_turn":{"rating":1404.7,"rank":147,"pct":64.7,"board_size":417},"longer_query":{"rating":1371.5,"rank":183,"pct":54,"board_size":397},"non_english":{"rating":1401.2,"rank":132,"pct":68.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/o3","input_per_m":2,"output_per_m":8,"blended_per_m":3.5,"context_length":200000,"modalities_in":["image","text","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/o3-2025-04-16"},{"slug":"qwen3-5-27b","name":"Qwen3.5-27B","source_name":"Qwen3.5-27B","base":"Qwen3.5-27B","variant":null,"org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":56.2,"rank":154,"coverage":0.75,"categories":{"coding":44.1,"reasoning":65.8,"math":73.8,"chat":66,"instructions":66.3}},"arena":{"text":{"rank":143,"date":"2026-10-28","rating":1409,"lo":1404.7,"hi":1413.3,"votes":28647,"pct":66,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":118,"date":"2026-10-28","rating":1358.3,"lo":1350.3,"hi":1366.4,"votes":7767,"pct":22.5,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":72,"date":"2026-10-19","rating":1241,"lo":1235.5,"hi":1246.5,"votes":30272,"pct":57.2,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1426.4,"rank":143,"pct":65.6,"board_size":414},"math":{"rating":1429,"rank":106,"pct":73.8,"board_size":405},"creative_writing":{"rating":1362.4,"rank":154,"pct":63.2,"board_size":417},"instruction_following":{"rating":1393,"rank":142,"pct":66.3,"board_size":419},"hard_prompts":{"rating":1414.4,"rank":144,"pct":65.8,"board_size":419},"multi_turn":{"rating":1410.1,"rank":139,"pct":66.8,"board_size":417},"longer_query":{"rating":1412.9,"rank":124,"pct":68.9,"board_size":397},"non_english":{"rating":1389.8,"rank":149,"pct":64.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"qwen/qwen3.5-27b","input_per_m":0.26,"output_per_m":2.6,"blended_per_m":0.845,"context_length":262144,"modalities_in":["text","image","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/qwen3-5-27b"},{"slug":"grok-4-1-fast-reasoning","name":"Grok 4.1 Fast (Reasoning)","source_name":"Grok 4.1 Fast (Reasoning)","base":"Grok 4.1 Fast","variant":"Reasoning","org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":48.4,"rank":197,"coverage":0.75,"categories":{"coding":33.4,"reasoning":62.9,"math":62.9,"chat":65.8,"instructions":61.2}},"arena":{"text":{"rank":144,"date":"2026-10-28","rating":1407.9,"lo":1404.7,"hi":1411.1,"votes":57500,"pct":65.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":142,"date":"2026-10-28","rating":1242.1,"lo":1231,"hi":1253.2,"votes":5473,"pct":6.6,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":94,"date":"2026-10-19","rating":1201.2,"lo":1194.3,"hi":1208.1,"votes":13368,"pct":44,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1411.4,"rank":165,"pct":60.3,"board_size":414},"math":{"rating":1407.8,"rank":151,"pct":62.9,"board_size":405},"creative_writing":{"rating":1394.2,"rank":110,"pct":73.8,"board_size":417},"instruction_following":{"rating":1376.1,"rank":163,"pct":61.2,"board_size":419},"hard_prompts":{"rating":1407.3,"rank":156,"pct":62.9,"board_size":419},"multi_turn":{"rating":1389.1,"rank":168,"pct":59.9,"board_size":417},"longer_query":{"rating":1389.8,"rank":167,"pct":58.1,"board_size":397},"non_english":{"rating":1391.3,"rank":148,"pct":64.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/grok-4-1-fast-reasoning"},{"slug":"grok-4-fast-non-reasoning","name":"Grok 4 Fast (Non-Reasoning)","source_name":"Grok 4 Fast (Non-Reasoning)","base":"Grok 4 Fast","variant":"Non-Reasoning","org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":65.8,"rank":102,"coverage":0.75,"categories":{"coding":66.6,"reasoning":64.6,"math":68.6,"chat":65.6,"instructions":64.6}},"arena":{"text":{"rank":145,"date":"2026-10-28","rating":1406.8,"lo":1399,"hi":1414.5,"votes":6336,"pct":65.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1427.9,"rank":139,"pct":66.6,"board_size":414},"math":{"rating":1418.5,"rank":128,"pct":68.6,"board_size":405},"creative_writing":{"rating":1386.3,"rank":126,"pct":70,"board_size":417},"instruction_following":{"rating":1386.9,"rank":148,"pct":64.6,"board_size":419},"hard_prompts":{"rating":1411.9,"rank":149,"pct":64.6,"board_size":419},"multi_turn":{"rating":1413.8,"rank":130,"pct":69,"board_size":417},"longer_query":{"rating":1414.2,"rank":123,"pct":69.2,"board_size":397},"non_english":{"rating":1395.4,"rank":144,"pct":65.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/grok-4-fast-non-reasoning"},{"slug":"gemini-2-5-flash-preview-09-2025","name":"Gemini 2.5 Flash Preview (09-2025)","source_name":"Gemini 2.5 Flash Preview (09-2025)","base":"Gemini 2.5 Flash Preview","variant":"09-2025","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":61.7,"rank":130,"coverage":0.75,"categories":{"coding":57.9,"reasoning":63.9,"math":67.3,"chat":65.3,"instructions":66.5}},"arena":{"text":{"rank":146,"date":"2026-10-28","rating":1406.5,"lo":1402.5,"hi":1410.5,"votes":32996,"pct":65.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":61,"date":"2026-10-19","rating":1253.5,"lo":1243.8,"hi":1263.3,"votes":4792,"pct":63.9,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1400.3,"rank":175,"pct":57.9,"board_size":414},"math":{"rating":1415.4,"rank":133,"pct":67.3,"board_size":405},"creative_writing":{"rating":1386.3,"rank":125,"pct":70,"board_size":417},"instruction_following":{"rating":1393.7,"rank":141,"pct":66.5,"board_size":419},"hard_prompts":{"rating":1408.8,"rank":152,"pct":63.9,"board_size":419},"multi_turn":{"rating":1396.3,"rank":160,"pct":61.8,"board_size":417},"longer_query":{"rating":1405.4,"rank":142,"pct":64.4,"board_size":397},"non_english":{"rating":1395.7,"rank":143,"pct":66,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemini-2-5-flash-preview-09-2025"},{"slug":"gpt-5-high","name":"GPT-5 (High)","source_name":"GPT-5 (High)","base":"GPT-5","variant":"High","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":61.8,"rank":129,"coverage":0.75,"categories":{"coding":56.6,"reasoning":70.5,"math":64.6,"chat":65.1,"instructions":65.3}},"arena":{"text":{"rank":147,"date":"2026-10-28","rating":1406.2,"lo":1401.7,"hi":1410.6,"votes":31718,"pct":65.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":90,"date":"2026-10-19","rating":1208.2,"lo":1201.4,"hi":1215,"votes":34445,"pct":46.4,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1435.8,"rank":127,"pct":69,"board_size":414},"math":{"rating":1398.2,"rank":164,"pct":59.7,"board_size":405},"creative_writing":{"rating":1363.9,"rank":152,"pct":63.7,"board_size":417},"instruction_following":{"rating":1388.3,"rank":146,"pct":65.3,"board_size":419},"hard_prompts":{"rating":1415.5,"rank":141,"pct":66.5,"board_size":419},"multi_turn":{"rating":1399.1,"rank":155,"pct":63,"board_size":417},"longer_query":{"rating":1387.2,"rank":170,"pct":57.3,"board_size":397},"non_english":{"rating":1397,"rank":142,"pct":66.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8617,"stderr":0.0208,"tested_as":"gpt-5-2025-08-07_high","approx":false,"run_date":"2025-10-29","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F9nPyNrZxwtoT7eS4DZbQF6.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":72.3,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.501,"stderr":0.0158,"tested_as":"gpt-5-2025-08-07_high","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FgTLurbyKU63i2opsGkJGwh.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":72.7,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9139,"stderr":0.0366,"tested_as":"gpt-5-2025-08-07_high","approx":false,"run_date":"2025-10-29","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F3D8aaFBLZwQcnWHYKwvnmq.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":75.3,"tested_models":313},{"benchmark":"frontiermath","score":0.5544,"stderr":0.0295,"tested_as":"gpt-5-2025-08-07_high","approx":false,"run_date":"2026-06-10","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":58.7,"tested_models":122},{"benchmark":"swe_bench_verified","score":0.7355,"stderr":0.0201,"tested_as":"gpt-5-2025-08-07_high","approx":false,"run_date":"2026-02-06","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FC85Bnci9xVzq5jmt8zNnbw.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":44.1,"tested_models":35}],"price":{"openrouter_id":"openai/gpt-5","input_per_m":1.25,"output_per_m":10,"blended_per_m":3.4375,"context_length":400000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-high"},{"slug":"hunyuan-vision-1-5-thinking","name":"Hunyuan Vision 1.5 Thinking","source_name":"Hunyuan Vision 1.5 Thinking","base":"Hunyuan Vision 1.5 Thinking","variant":null,"org":"tencent","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"coding":63.4,"reasoning":67.2,"chat":64.8,"instructions":67}},"arena":{"text":{"rank":148,"date":"2026-10-28","rating":1405.8,"lo":1393.4,"hi":1418.2,"votes":2169,"pct":64.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":105,"date":"2026-10-19","rating":1179.7,"lo":1167.6,"hi":1191.8,"votes":2424,"pct":37.3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1419.8,"rank":152,"pct":63.4,"board_size":414},"creative_writing":{"rating":1389.4,"rank":119,"pct":71.6,"board_size":417},"instruction_following":{"rating":1397.4,"rank":139,"pct":67,"board_size":419},"hard_prompts":{"rating":1417.1,"rank":138,"pct":67.2,"board_size":419},"multi_turn":{"rating":1422.8,"rank":115,"pct":72.6,"board_size":417},"longer_query":{"rating":1405.3,"rank":143,"pct":64.1,"board_size":397},"non_english":{"rating":1382.7,"rank":161,"pct":61.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/hunyuan-vision-1-5-thinking"},{"slug":"nvidia-nemotron-3-5-super-vl-120b-a12b-nvfp4","name":"Nemotron 3.5 Super VL 120B A12B (NVFP4)","source_name":"NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)","base":"Nemotron 3.5 Super VL 120B A12B","variant":"NVFP4","org":"nvidia","open_weights":true,"model_license":"OpenMDW-1.1","siscope":{"score":46.5,"rank":204,"coverage":1,"categories":{"coding":50.1,"agents":5.4,"reasoning":65.1,"math":65.3,"chat":64.6,"instructions":67.9}},"arena":{"text":{"rank":149,"date":"2026-10-28","rating":1405,"lo":1395.6,"hi":1414.3,"votes":4178,"pct":64.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":101,"date":"2026-10-28","rating":1399.2,"lo":1386.3,"hi":1412.1,"votes":3193,"pct":33.8,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":92,"date":"2026-10-19","rating":1204.7,"lo":1191.9,"hi":1217.6,"votes":2509,"pct":45.2,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":54,"date":"2026-11-02","score":-0.1592,"lo":-0.1689,"hi":-0.1494,"sessions":20299,"cost_per_task_p50":null,"pct":5.4,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1427.8,"rank":140,"pct":66.3,"board_size":414},"math":{"rating":1412.3,"rank":141,"pct":65.3,"board_size":405},"creative_writing":{"rating":1376.5,"rank":136,"pct":67.5,"board_size":417},"instruction_following":{"rating":1398.4,"rank":135,"pct":67.9,"board_size":419},"hard_prompts":{"rating":1413.1,"rank":147,"pct":65.1,"board_size":419},"multi_turn":{"rating":1413,"rank":131,"pct":68.8,"board_size":417},"longer_query":{"rating":1399.4,"rank":150,"pct":62.1,"board_size":397},"non_english":{"rating":1384.5,"rank":158,"pct":62.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/nvidia-nemotron-3-5-super-vl-120b-a12b-nvfp4"},{"slug":"minimax-m2-7","name":"MiniMax-M2.7","source_name":"MiniMax-M2.7","base":"MiniMax-M2.7","variant":null,"org":"minimax","open_weights":true,"model_license":"Modified MIT","siscope":{"score":61.9,"rank":128,"coverage":0.75,"categories":{"coding":55.1,"reasoning":69.4,"math":69.6,"chat":64.4,"instructions":72.2}},"arena":{"text":{"rank":150,"date":"2026-10-28","rating":1404.8,"lo":1401.5,"hi":1408.1,"votes":89197,"pct":64.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":102,"date":"2026-10-28","rating":1398.2,"lo":1392.4,"hi":1404,"votes":15890,"pct":33.1,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1453.6,"rank":96,"pct":77,"board_size":414},"math":{"rating":1421,"rank":124,"pct":69.6,"board_size":405},"creative_writing":{"rating":1353.8,"rank":165,"pct":60.6,"board_size":417},"instruction_following":{"rating":1405.4,"rank":117,"pct":72.2,"board_size":419},"hard_prompts":{"rating":1422.3,"rank":129,"pct":69.4,"board_size":419},"multi_turn":{"rating":1411.7,"rank":134,"pct":68,"board_size":417},"longer_query":{"rating":1418.6,"rank":114,"pct":71.5,"board_size":397},"non_english":{"rating":1382.6,"rank":162,"pct":61.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"minimax/minimax-m2.7","input_per_m":0.3,"output_per_m":1.2,"blended_per_m":0.525,"context_length":204800,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/minimax-m2-7"},{"slug":"gpt-5-chat","name":"GPT-5 Chat","source_name":"GPT-5 Chat","base":"GPT-5 Chat","variant":null,"org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":59.9,"rank":138,"coverage":0.75,"categories":{"coding":57.1,"reasoning":62,"math":62.4,"chat":64.1,"instructions":62.7}},"arena":{"text":{"rank":151,"date":"2026-10-28","rating":1403.3,"lo":1399,"hi":1407.5,"votes":31187,"pct":64.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":78,"date":"2026-10-19","rating":1232.2,"lo":1225.2,"hi":1239.2,"votes":39894,"pct":53.6,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1397.9,"rank":178,"pct":57.1,"board_size":414},"math":{"rating":1407,"rank":153,"pct":62.4,"board_size":405},"creative_writing":{"rating":1364.9,"rank":150,"pct":64.2,"board_size":417},"instruction_following":{"rating":1381.1,"rank":157,"pct":62.7,"board_size":419},"hard_prompts":{"rating":1404.4,"rank":160,"pct":62,"board_size":419},"multi_turn":{"rating":1426.1,"rank":110,"pct":73.8,"board_size":417},"longer_query":{"rating":1398.5,"rank":154,"pct":61.4,"board_size":397},"non_english":{"rating":1394.6,"rank":146,"pct":65.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gpt-5-chat"},{"slug":"step-3-5-flash","name":"Step 3.5 Flash","source_name":"Step-3.5-Flash","base":"Step 3.5 Flash","variant":null,"org":"stepfun","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":64.9,"rank":112,"coverage":0.75,"categories":{"coding":69,"reasoning":64.4,"math":63.1,"chat":63.9,"instructions":63.6}},"arena":{"text":{"rank":152,"date":"2026-10-28","rating":1402.8,"lo":1399.2,"hi":1406.3,"votes":60305,"pct":63.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1435.8,"rank":128,"pct":69,"board_size":414},"math":{"rating":1408.2,"rank":150,"pct":63.1,"board_size":405},"creative_writing":{"rating":1357,"rank":161,"pct":61.5,"board_size":417},"instruction_following":{"rating":1384.9,"rank":153,"pct":63.6,"board_size":419},"hard_prompts":{"rating":1410.7,"rank":150,"pct":64.4,"board_size":419},"multi_turn":{"rating":1404.7,"rank":148,"pct":64.7,"board_size":417},"longer_query":{"rating":1401.9,"rank":146,"pct":63.4,"board_size":397},"non_english":{"rating":1385.2,"rank":155,"pct":63.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"stepfun/step-3.5-flash","input_per_m":0.1,"output_per_m":0.3,"blended_per_m":0.15,"context_length":262144,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/step-3-5-flash"},{"slug":"hy3-preview","name":"Hy3 preview","source_name":"Hy3 preview","base":"Hy3 preview","variant":null,"org":"tencent","open_weights":true,"model_license":"tencent-hunyuan-community","siscope":{"score":54.6,"rank":161,"coverage":0.75,"categories":{"coding":42.7,"reasoning":64.8,"math":71.5,"chat":63.6,"instructions":63.4}},"arena":{"text":{"rank":153,"date":"2026-10-28","rating":1401.2,"lo":1393.8,"hi":1408.6,"votes":6869,"pct":63.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":120,"date":"2026-10-28","rating":1356.9,"lo":1339.5,"hi":1374.3,"votes":1444,"pct":21.2,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1421,"rank":149,"pct":64.2,"board_size":414},"math":{"rating":1424.2,"rank":116,"pct":71.5,"board_size":405},"creative_writing":{"rating":1338.6,"rank":184,"pct":56,"board_size":417},"instruction_following":{"rating":1382.8,"rank":154,"pct":63.4,"board_size":419},"hard_prompts":{"rating":1412.6,"rank":148,"pct":64.8,"board_size":419},"multi_turn":{"rating":1410.3,"rank":138,"pct":67.1,"board_size":417},"longer_query":{"rating":1401.6,"rank":147,"pct":63.1,"board_size":397},"non_english":{"rating":1389.7,"rank":150,"pct":64.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"tencent/hy3-preview","input_per_m":0.18,"output_per_m":0.6,"blended_per_m":0.285,"context_length":262144,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/hy3-preview"},{"slug":"claude-haiku-5-5-high","name":"Claude Haiku 5.5 (High)","source_name":"Claude Haiku 5.5 (High)","base":"Claude Haiku 5.5","variant":"High","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":68.8,"rank":89,"coverage":1,"categories":{"coding":77.3,"agents":53.6,"reasoning":68.4,"math":81.5,"chat":63.4,"instructions":77.3}},"arena":{"text":{"rank":154,"date":"2026-10-28","rating":1400.9,"lo":1393.4,"hi":1408.4,"votes":7890,"pct":63.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":36,"date":"2026-10-28","rating":1588.8,"lo":1579.2,"hi":1598.5,"votes":4758,"pct":76.8,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":27,"date":"2026-11-02","score":0.0065,"lo":-0.0037,"hi":0.0168,"sessions":30507,"cost_per_task_p50":0.096,"pct":53.6,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1454.3,"rank":93,"pct":77.7,"board_size":414},"math":{"rating":1433.5,"rank":96,"pct":76.5,"board_size":405},"creative_writing":{"rating":1335.8,"rank":186,"pct":55.5,"board_size":417},"instruction_following":{"rating":1415.4,"rank":96,"pct":77.3,"board_size":419},"hard_prompts":{"rating":1421,"rank":133,"pct":68.4,"board_size":419},"multi_turn":{"rating":1397.5,"rank":158,"pct":62.3,"board_size":417},"longer_query":{"rating":1399.9,"rank":149,"pct":62.6,"board_size":397},"non_english":{"rating":1387.4,"rank":153,"pct":63.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"otis_mock_aime","score":0.9722,"stderr":0.0131,"tested_as":"claude-haiku-5-5_high","approx":false,"run_date":"2026-10-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FLycbwGumF6Q7ySpmGY94XW.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":86.5,"tested_models":313}],"price":{"openrouter_id":"anthropic/claude-haiku-5.5","input_per_m":0.1,"output_per_m":0.5,"blended_per_m":0.2,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-haiku-5-5-high"},{"slug":"hunyuan-t1-20250711","name":"Hunyuan T1 (2025-07-11)","source_name":"Hunyuan T1 (20250711)","base":"Hunyuan T1","variant":"2025-07-11","org":"tencent","open_weights":false,"model_license":"Proprietary","siscope":{"score":58.7,"rank":140,"coverage":0.75,"categories":{"coding":55,"reasoning":60,"math":65.8,"chat":63.2,"instructions":60.5}},"arena":{"text":{"rank":155,"date":"2026-10-28","rating":1400.7,"lo":1392,"hi":1409.3,"votes":4595,"pct":63.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1389.3,"rank":187,"pct":55,"board_size":414},"math":{"rating":1413.5,"rank":139,"pct":65.8,"board_size":405},"creative_writing":{"rating":1393.5,"rank":112,"pct":73.3,"board_size":417},"instruction_following":{"rating":1375.4,"rank":166,"pct":60.5,"board_size":419},"hard_prompts":{"rating":1399,"rank":168,"pct":60,"board_size":419},"multi_turn":{"rating":1393.3,"rank":163,"pct":61.1,"board_size":417},"longer_query":{"rating":1384.8,"rank":171,"pct":56.8,"board_size":397},"non_english":{"rating":1394.6,"rank":145,"pct":65.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/hunyuan-t1-20250711"},{"slug":"qwen3-vl-235b-a22b-thinking","name":"Qwen3 VL 235B A22B Thinking","source_name":"Qwen3-VL-235B-A22B-Thinking","base":"Qwen3 VL 235B A22B Thinking","variant":null,"org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":62.5,"rank":124,"coverage":0.75,"categories":{"coding":64.9,"reasoning":62.7,"math":63.6,"chat":62.9,"instructions":59.8}},"arena":{"text":{"rank":156,"date":"2026-10-28","rating":1400.5,"lo":1393.7,"hi":1407.3,"votes":7862,"pct":62.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":91,"date":"2026-10-19","rating":1207,"lo":1194.7,"hi":1219.2,"votes":2387,"pct":45.8,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1425,"rank":146,"pct":64.9,"board_size":414},"math":{"rating":1409.5,"rank":147,"pct":63.6,"board_size":405},"creative_writing":{"rating":1343.6,"rank":176,"pct":57.9,"board_size":417},"instruction_following":{"rating":1374.3,"rank":169,"pct":59.8,"board_size":419},"hard_prompts":{"rating":1406.9,"rank":157,"pct":62.7,"board_size":419},"multi_turn":{"rating":1387.4,"rank":172,"pct":58.9,"board_size":417},"longer_query":{"rating":1390.8,"rank":165,"pct":58.6,"board_size":397},"non_english":{"rating":1376.6,"rank":169,"pct":59.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen3-vl-235b-a22b-thinking"},{"slug":"grok-4-fast-reasoning","name":"Grok 4 Fast (Reasoning)","source_name":"Grok 4 Fast (Reasoning)","base":"Grok 4 Fast","variant":"Reasoning","org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":47.1,"rank":200,"coverage":0.75,"categories":{"coding":32.2,"reasoning":62.2,"math":60.6,"chat":62.7,"instructions":63.2}},"arena":{"text":{"rank":157,"date":"2026-10-28","rating":1399.6,"lo":1394.6,"hi":1404.6,"votes":18270,"pct":62.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":151,"date":"2026-10-28","rating":1159.1,"lo":1131.7,"hi":1186.5,"votes":742,"pct":0.7,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1420,"rank":151,"pct":63.7,"board_size":414},"math":{"rating":1403.6,"rank":160,"pct":60.6,"board_size":405},"creative_writing":{"rating":1378,"rank":134,"pct":68,"board_size":417},"instruction_following":{"rating":1382.5,"rank":155,"pct":63.2,"board_size":419},"hard_prompts":{"rating":1404.7,"rank":159,"pct":62.2,"board_size":419},"multi_turn":{"rating":1404.2,"rank":150,"pct":64.2,"board_size":417},"longer_query":{"rating":1412.2,"rank":128,"pct":67.9,"board_size":397},"non_english":{"rating":1388.5,"rank":151,"pct":64.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/grok-4-fast-reasoning"},{"slug":"grok-4-7-xhigh","name":"Grok 4.7 (xHigh)","source_name":"Grok 4.7 (xHigh)","base":"Grok 4.7","variant":"xHigh","org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":73.7,"rank":67,"coverage":1,"categories":{"coding":76.4,"agents":73.2,"reasoning":79.1,"math":70.5,"chat":62.4,"instructions":73.2}},"arena":{"text":{"rank":158,"date":"2026-10-28","rating":1398.1,"lo":1392.4,"hi":1403.9,"votes":16442,"pct":62.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":21,"date":"2026-10-28","rating":1637.5,"lo":1628.7,"hi":1646.2,"votes":6572,"pct":86.8,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":79,"date":"2026-10-19","rating":1231,"lo":1220.3,"hi":1241.6,"votes":3736,"pct":53,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":16,"date":"2026-11-02","score":0.0264,"lo":0.0118,"hi":0.0411,"sessions":18788,"cost_per_task_p50":2.611,"pct":73.2,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1427.6,"rank":141,"pct":66.1,"board_size":414},"math":{"rating":1412.9,"rank":140,"pct":65.6,"board_size":405},"creative_writing":{"rating":1381.2,"rank":130,"pct":69,"board_size":417},"instruction_following":{"rating":1406.3,"rank":112,"pct":73.2,"board_size":419},"hard_prompts":{"rating":1413.6,"rank":146,"pct":65.3,"board_size":419},"multi_turn":{"rating":1394.1,"rank":162,"pct":61.3,"board_size":417},"longer_query":{"rating":1414.9,"rank":121,"pct":69.7,"board_size":397},"non_english":{"rating":1383.8,"rank":160,"pct":62,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9274,"stderr":0.0155,"tested_as":"grok-4.7_xhigh","approx":false,"run_date":"2026-09-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FhxAhYJfXdPNanxatXpG5hC.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":92.2,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.56,"stderr":0.0157,"tested_as":"grok-4.7_xhigh","approx":false,"run_date":"2026-09-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F6izDCw5ygCLZJEKPS8jV5T.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":79.8,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9806,"stderr":0.0143,"tested_as":"grok-4.7_xhigh","approx":false,"run_date":"2026-09-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FJhgwm7QpspGcvm7DUVqUDg.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":89.7,"tested_models":313},{"benchmark":"frontiermath","score":0.5298,"stderr":0.0296,"tested_as":"grok-4.7_xhigh","approx":false,"run_date":"2026-09-22","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":56.2,"tested_models":122}],"price":{"openrouter_id":"x-ai/grok-4.7","input_per_m":2,"output_per_m":6,"blended_per_m":3,"context_length":500000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/grok-4-7-xhigh"},{"slug":"gpt-6-sol-max","name":"GPT-6 Sol (Max)","source_name":"GPT-6 Sol (Max)","base":"GPT-6 Sol","variant":"Max","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":80.3,"rank":43,"coverage":1,"categories":{"coding":83.5,"agents":80.4,"reasoning":83.6,"math":84.3,"chat":62.2,"instructions":74.9}},"arena":{"text":{"rank":159,"date":"2026-10-28","rating":1397.4,"lo":1391.5,"hi":1403.3,"votes":15807,"pct":62.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":12,"date":"2026-10-28","rating":1678.2,"lo":1668.8,"hi":1687.6,"votes":5714,"pct":92.7,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":74,"date":"2026-10-19","rating":1239.9,"lo":1228.7,"hi":1251.2,"votes":3221,"pct":56,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":12,"date":"2026-11-02","score":0.0695,"lo":0.0536,"hi":0.0854,"sessions":12478,"cost_per_task_p50":1.739,"pct":80.4,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1447.4,"rank":107,"pct":74.3,"board_size":414},"math":{"rating":1403.7,"rank":159,"pct":60.9,"board_size":405},"creative_writing":{"rating":1377.8,"rank":135,"pct":67.8,"board_size":417},"instruction_following":{"rating":1410.9,"rank":106,"pct":74.9,"board_size":419},"hard_prompts":{"rating":1419.8,"rank":137,"pct":67.5,"board_size":419},"multi_turn":{"rating":1411.4,"rank":135,"pct":67.8,"board_size":417},"longer_query":{"rating":1415.5,"rank":117,"pct":70.7,"board_size":397},"non_english":{"rating":1388.1,"rank":152,"pct":63.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9432,"stderr":0.0149,"tested_as":"gpt-6-sol_max","approx":false,"run_date":"2026-09-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FaJD7ZfFftu2cZoToJhhzF7.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":97.3,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.607,"stderr":0.0155,"tested_as":"gpt-6-sol_max","approx":false,"run_date":"2026-09-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FdonMeEKBZZdqpQsojKWJEm.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":85.9,"tested_models":100},{"benchmark":"otis_mock_aime","score":1,"stderr":0,"tested_as":"gpt-6-sol_max","approx":false,"run_date":"2026-09-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FVZAUcNkzeMSMm9paxBhj6B.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":96.2,"tested_models":313},{"benchmark":"frontiermath","score":0.8982,"stderr":0.0179,"tested_as":"gpt-6-sol_max","approx":false,"run_date":"2026-09-22","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":95.9,"tested_models":122}],"price":{"openrouter_id":"openai/gpt-6-sol","input_per_m":2,"output_per_m":10,"blended_per_m":4,"context_length":1050000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-6-sol-max"},{"slug":"qwen3-5-flash","name":"Qwen3.5-Flash","source_name":"Qwen3.5-Flash","base":"Qwen3.5-Flash","variant":null,"org":"alibaba","open_weights":false,"model_license":"Proprietary","siscope":{"score":42.3,"rank":224,"coverage":0.75,"categories":{"coding":34.2,"reasoning":46.2,"math":45.4,"chat":62,"instructions":60}},"arena":{"text":{"rank":160,"date":"2026-10-28","rating":1397.1,"lo":1393.4,"hi":1400.7,"votes":61776,"pct":62,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":140,"date":"2026-10-28","rating":1243.7,"lo":1224,"hi":1263.4,"votes":1321,"pct":7.9,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1411.8,"rank":164,"pct":60.5,"board_size":414},"math":{"rating":1407.6,"rank":152,"pct":62.6,"board_size":405},"creative_writing":{"rating":1343.4,"rank":178,"pct":57.5,"board_size":417},"instruction_following":{"rating":1374.9,"rank":168,"pct":60,"board_size":419},"hard_prompts":{"rating":1403.4,"rank":162,"pct":61.2,"board_size":419},"multi_turn":{"rating":1392.6,"rank":165,"pct":60.6,"board_size":417},"longer_query":{"rating":1391.7,"rank":162,"pct":59.3,"board_size":397},"non_english":{"rating":1384.9,"rank":157,"pct":62.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8232,"stderr":0.0272,"tested_as":"qwen3.5-flash","approx":false,"run_date":"2026-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FS7wbot7JR53BAjM8F9gaws.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":61.1,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.2032,"stderr":0.0127,"tested_as":"qwen3.5-flash","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FK8zTckSXLKLesoLBv24TWc.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":16.2,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.8444,"stderr":0.0546,"tested_as":"qwen3.5-flash","approx":false,"run_date":"2026-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FawDKyKbPXRzBVZzfdQucef.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":63.8,"tested_models":313},{"benchmark":"frontiermath","score":0.0947,"stderr":0.0174,"tested_as":"qwen3.5-flash","approx":false,"run_date":"2026-08-28","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F6XZAenohp9pCgQ3gVeUAi8.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":9.9,"tested_models":122}],"price":{"openrouter_id":"qwen/qwen3.5-flash-02-23","input_per_m":0.065,"output_per_m":0.26,"blended_per_m":0.1138,"context_length":1000000,"modalities_in":["text","image","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/qwen3-5-flash"},{"slug":"grok-4-3","name":"Grok 4.3","source_name":"Grok 4.3","base":"Grok 4.3","variant":null,"org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":50.2,"rank":186,"coverage":0.75,"categories":{"coding":42.1,"reasoning":59.1,"math":55,"chat":61.5,"instructions":58.1}},"arena":{"text":{"rank":161,"date":"2026-10-28","rating":1396.9,"lo":1393.3,"hi":1400.5,"votes":71287,"pct":61.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":119,"date":"2026-10-28","rating":1357.6,"lo":1351.3,"hi":1363.8,"votes":14906,"pct":21.9,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":80,"date":"2026-10-19","rating":1229.3,"lo":1223.5,"hi":1235.1,"votes":27901,"pct":52.4,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1414.4,"rank":157,"pct":62.2,"board_size":414},"math":{"rating":1387.1,"rank":183,"pct":55,"board_size":405},"creative_writing":{"rating":1379.5,"rank":132,"pct":68.5,"board_size":417},"instruction_following":{"rating":1365.7,"rank":176,"pct":58.1,"board_size":419},"hard_prompts":{"rating":1396.5,"rank":172,"pct":59.1,"board_size":419},"multi_turn":{"rating":1405.7,"rank":146,"pct":65.1,"board_size":417},"longer_query":{"rating":1392.5,"rank":161,"pct":59.6,"board_size":397},"non_english":{"rating":1385.3,"rank":154,"pct":63.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"x-ai/grok-4.3","input_per_m":1.25,"output_per_m":2.5,"blended_per_m":1.5625,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/grok-4-3"},{"slug":"claude-haiku-4-5-20251001","name":"Claude Haiku 4.5 (2025-10-01)","source_name":"Claude Haiku 4.5 (20251001)","base":"Claude Haiku 4.5","variant":"2025-10-01","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":44.4,"rank":216,"coverage":0.75,"categories":{"coding":46.6,"reasoning":36.3,"math":42.9,"chat":61.5,"instructions":76.6}},"arena":{"text":{"rank":162,"date":"2026-10-28","rating":1396.9,"lo":1394.5,"hi":1399.3,"votes":154063,"pct":61.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":128,"date":"2026-10-28","rating":1330.4,"lo":1325.4,"hi":1335.3,"votes":28961,"pct":15.9,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1453.8,"rank":95,"pct":77.2,"board_size":414},"math":{"rating":1397.7,"rank":166,"pct":59.2,"board_size":405},"creative_writing":{"rating":1370.4,"rank":144,"pct":65.4,"board_size":417},"instruction_following":{"rating":1414.4,"rank":99,"pct":76.6,"board_size":419},"hard_prompts":{"rating":1420.4,"rank":134,"pct":67.9,"board_size":419},"multi_turn":{"rating":1409.4,"rank":140,"pct":66.6,"board_size":417},"longer_query":{"rating":1427.1,"rank":100,"pct":75,"board_size":397},"non_english":{"rating":1376.8,"rank":168,"pct":60,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.6048,"stderr":0.0282,"tested_as":"claude-haiku-4-5-20251001","approx":false,"run_date":"2025-10-16","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FcgnopvpB6mzsfb9yGnYK2z.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":32.8,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.132,"stderr":0.0107,"tested_as":"claude-haiku-4-5-20251001","approx":false,"run_date":"2026-08-10","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":8.1,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.3583,"stderr":0.0624,"tested_as":"claude-haiku-4-5-20251001","approx":false,"run_date":"2025-10-16","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FWf2kwcXu8YXNgzDCxChtvj.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":26.6,"tested_models":313}],"price":{"openrouter_id":"anthropic/claude-haiku-4.5","input_per_m":1,"output_per_m":5,"blended_per_m":2,"context_length":200000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-haiku-4-5-20251001"},{"slug":"amazon-nova-experimental-chat-26-01-10","name":"Amazon Nova Experimental Chat (26-01-10)","source_name":"amazon-nova-experimental-chat (26-01-10)","base":"Amazon Nova Experimental Chat","variant":"26-01-10","org":"amazon","open_weights":false,"model_license":"Proprietary","siscope":{"score":65.5,"rank":103,"coverage":0.75,"categories":{"coding":74.1,"reasoning":66,"math":61.4,"chat":61.2,"instructions":62.2}},"arena":{"text":{"rank":163,"date":"2026-10-28","rating":1395.8,"lo":1386.2,"hi":1405.4,"votes":3534,"pct":61.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1446.9,"rank":108,"pct":74.1,"board_size":414},"math":{"rating":1404.2,"rank":157,"pct":61.4,"board_size":405},"creative_writing":{"rating":1330,"rank":195,"pct":53.4,"board_size":417},"instruction_following":{"rating":1380.6,"rank":159,"pct":62.2,"board_size":419},"hard_prompts":{"rating":1414.9,"rank":143,"pct":66,"board_size":419},"multi_turn":{"rating":1380.1,"rank":177,"pct":57.7,"board_size":417},"longer_query":{"rating":1399.4,"rank":151,"pct":62.1,"board_size":397},"non_english":{"rating":1380.7,"rank":164,"pct":61,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/amazon-nova-experimental-chat-26-01-10"},{"slug":"mimo-v2-flash-thinking","name":"MiMo-V2-Flash (Thinking)","source_name":"MiMo-V2-Flash (Thinking)","base":"MiMo-V2-Flash","variant":"Thinking","org":"xiaomi","open_weights":true,"model_license":"MIT","siscope":{"score":48.4,"rank":196,"coverage":0.75,"categories":{"coding":37.9,"reasoning":61.7,"math":53.7,"chat":61,"instructions":59.3}},"arena":{"text":{"rank":164,"date":"2026-10-28","rating":1394.6,"lo":1388.4,"hi":1400.7,"votes":11135,"pct":61,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":133,"date":"2026-10-28","rating":1291.7,"lo":1275.2,"hi":1308.2,"votes":1681,"pct":12.6,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1418.1,"rank":153,"pct":63.2,"board_size":414},"math":{"rating":1377.4,"rank":188,"pct":53.7,"board_size":405},"creative_writing":{"rating":1347.9,"rank":169,"pct":59.6,"board_size":417},"instruction_following":{"rating":1373,"rank":171,"pct":59.3,"board_size":419},"hard_prompts":{"rating":1403.5,"rank":161,"pct":61.7,"board_size":419},"multi_turn":{"rating":1377.5,"rank":180,"pct":57,"board_size":417},"longer_query":{"rating":1392.9,"rank":160,"pct":59.8,"board_size":397},"non_english":{"rating":1373.2,"rank":170,"pct":59.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/mimo-v2-flash-thinking"},{"slug":"qwen3-5-35b-a3b","name":"Qwen3.5 35B A3B","source_name":"Qwen3.5-35B-A3B","base":"Qwen3.5 35B A3B","variant":null,"org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":46.3,"rank":208,"coverage":0.75,"categories":{"coding":34.3,"reasoning":63.1,"math":49.3,"chat":60.8,"instructions":62}},"arena":{"text":{"rank":165,"date":"2026-10-28","rating":1394.5,"lo":1390.3,"hi":1398.7,"votes":30427,"pct":60.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":139,"date":"2026-10-28","rating":1254.2,"lo":1236.7,"hi":1271.6,"votes":1612,"pct":8.6,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1409.7,"rank":166,"pct":60,"board_size":414},"math":{"rating":1403.9,"rank":158,"pct":61.1,"board_size":405},"creative_writing":{"rating":1347.5,"rank":170,"pct":59.4,"board_size":417},"instruction_following":{"rating":1379.3,"rank":160,"pct":62,"board_size":419},"hard_prompts":{"rating":1399.7,"rank":166,"pct":60.5,"board_size":419},"multi_turn":{"rating":1390.2,"rank":167,"pct":60.1,"board_size":417},"longer_query":{"rating":1389.2,"rank":168,"pct":57.8,"board_size":397},"non_english":{"rating":1378.1,"rank":166,"pct":60.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8346,"stderr":0.0218,"tested_as":"qwen3.5-35b-a3b","approx":false,"run_date":"2026-08-28","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FRWjuCuVGvaRd4vDjJJ6aP2.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":65.7,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.5444,"stderr":0.0619,"tested_as":"qwen3.5-35b-a3b","approx":false,"run_date":"2026-08-30","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F9WS6kHXT8XFtJWtE2wWLAo.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":37.5,"tested_models":313}],"price":{"openrouter_id":"qwen/qwen3.5-35b-a3b","input_per_m":0.14,"output_per_m":1,"blended_per_m":0.355,"context_length":262144,"modalities_in":["text","image","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/qwen3-5-35b-a3b"},{"slug":"amazon-nova-experimental-chat-10-20","name":"Amazon Nova Experimental Chat (10-20)","source_name":"amazon-nova-experimental-chat (10-20)","base":"Amazon Nova Experimental Chat","variant":"10-20","org":"amazon","open_weights":false,"model_license":"Proprietary","siscope":{"score":61.4,"rank":132,"coverage":0.75,"categories":{"coding":61.3,"reasoning":58.9,"math":72.5,"chat":60.5,"instructions":57.9}},"arena":{"text":{"rank":166,"date":"2026-10-28","rating":1393.9,"lo":1387.9,"hi":1400,"votes":11625,"pct":60.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1412.8,"rank":160,"pct":61.3,"board_size":414},"math":{"rating":1425.9,"rank":112,"pct":72.5,"board_size":405},"creative_writing":{"rating":1318.1,"rank":205,"pct":51,"board_size":417},"instruction_following":{"rating":1364.7,"rank":177,"pct":57.9,"board_size":419},"hard_prompts":{"rating":1396,"rank":173,"pct":58.9,"board_size":419},"multi_turn":{"rating":1364,"rank":191,"pct":54.3,"board_size":417},"longer_query":{"rating":1370,"rank":184,"pct":53.8,"board_size":397},"non_english":{"rating":1372,"rank":172,"pct":59.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/amazon-nova-experimental-chat-10-20"},{"slug":"qwen3-235b-a22b-non-thinking","name":"Qwen3 235B A22B (Non-Thinking)","source_name":"Qwen3-235B-A22B (Non-Thinking)","base":"Qwen3 235B A22B","variant":"Non-Thinking","org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":57.9,"rank":146,"coverage":0.75,"categories":{"coding":56.9,"reasoning":58.6,"math":58.7,"chat":60.3,"instructions":57.2}},"arena":{"text":{"rank":167,"date":"2026-10-28","rating":1393.5,"lo":1389,"hi":1398,"votes":37472,"pct":60.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1397.5,"rank":179,"pct":56.9,"board_size":414},"math":{"rating":1396.7,"rank":168,"pct":58.7,"board_size":405},"creative_writing":{"rating":1356.1,"rank":162,"pct":61.3,"board_size":417},"instruction_following":{"rating":1361.6,"rank":180,"pct":57.2,"board_size":419},"hard_prompts":{"rating":1393.1,"rank":174,"pct":58.6,"board_size":419},"multi_turn":{"rating":1398.1,"rank":156,"pct":62.7,"board_size":417},"longer_query":{"rating":1388.8,"rank":169,"pct":57.6,"board_size":397},"non_english":{"rating":1384.1,"rank":159,"pct":62.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen3-235b-a22b-non-thinking"},{"slug":"minimax-m2-1-preview","name":"MiniMax-M2.1 Preview","source_name":"MiniMax-M2.1 Preview","base":"MiniMax-M2.1 Preview","variant":null,"org":"minimax","open_weights":true,"model_license":"MIT","siscope":{"score":53.9,"rank":165,"coverage":0.75,"categories":{"coding":45.9,"reasoning":64.1,"math":58.4,"chat":60,"instructions":68.7}},"arena":{"text":{"rank":168,"date":"2026-10-28","rating":1392,"lo":1386.9,"hi":1397.1,"votes":17222,"pct":60,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":110,"date":"2026-10-28","rating":1384,"lo":1374.4,"hi":1393.5,"votes":7573,"pct":27.8,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1420.1,"rank":150,"pct":63.9,"board_size":414},"math":{"rating":1396.5,"rank":169,"pct":58.4,"board_size":405},"creative_writing":{"rating":1362,"rank":155,"pct":62.7,"board_size":417},"instruction_following":{"rating":1400.1,"rank":132,"pct":68.7,"board_size":419},"hard_prompts":{"rating":1410.5,"rank":151,"pct":64.1,"board_size":419},"multi_turn":{"rating":1396.3,"rank":159,"pct":61.8,"board_size":417},"longer_query":{"rating":1415.4,"rank":118,"pct":70.5,"board_size":397},"non_english":{"rating":1377.7,"rank":167,"pct":60.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/minimax-m2-1-preview"},{"slug":"muse-glimmer","name":"Muse Glimmer","source_name":"Muse Glimmer","base":"Muse Glimmer","variant":null,"org":"meta","open_weights":true,"model_license":"Apache-2.0","siscope":{"score":51.5,"rank":175,"coverage":0.75,"categories":{"coding":41.5,"reasoning":59.3,"math":66.1,"chat":59.8,"instructions":60.8}},"arena":{"text":{"rank":169,"date":"2026-10-28","rating":1389.3,"lo":1379.7,"hi":1399,"votes":3884,"pct":59.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":121,"date":"2026-10-28","rating":1355.1,"lo":1339.4,"hi":1370.7,"votes":1632,"pct":20.5,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1415.7,"rank":156,"pct":62.5,"board_size":414},"math":{"rating":1414.4,"rank":138,"pct":66.1,"board_size":405},"creative_writing":{"rating":1338.8,"rank":183,"pct":56.2,"board_size":417},"instruction_following":{"rating":1376,"rank":164,"pct":60.8,"board_size":419},"hard_prompts":{"rating":1396.7,"rank":171,"pct":59.3,"board_size":419},"multi_turn":{"rating":1399.9,"rank":153,"pct":63.2,"board_size":417},"longer_query":{"rating":1381.8,"rank":174,"pct":56.3,"board_size":397},"non_english":{"rating":1385,"rank":156,"pct":62.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/muse-glimmer"},{"slug":"gpt-6-luna-max","name":"GPT-6 Luna (Max)","source_name":"GPT-6 Luna (Max)","base":"GPT-6 Luna","variant":"Max","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":68.6,"rank":90,"coverage":1,"categories":{"coding":71.6,"agents":62.5,"reasoning":67,"math":80.4,"chat":59.6,"instructions":72.5}},"arena":{"text":{"rank":170,"date":"2026-10-28","rating":1389.2,"lo":1384.9,"hi":1393.4,"votes":86478,"pct":59.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":41,"date":"2026-10-28","rating":1579.4,"lo":1573.6,"hi":1585.2,"votes":27808,"pct":73.5,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":85,"date":"2026-10-19","rating":1216.1,"lo":1205.3,"hi":1226.9,"votes":3662,"pct":49.4,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":22,"date":"2026-11-02","score":0.0192,"lo":0.0149,"hi":0.0234,"sessions":223505,"cost_per_task_p50":0.091,"pct":62.5,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1436.6,"rank":126,"pct":69.7,"board_size":414},"math":{"rating":1409.6,"rank":146,"pct":64.1,"board_size":405},"creative_writing":{"rating":1362,"rank":156,"pct":62.7,"board_size":417},"instruction_following":{"rating":1405.8,"rank":116,"pct":72.5,"board_size":419},"hard_prompts":{"rating":1408.2,"rank":154,"pct":63.4,"board_size":419},"multi_turn":{"rating":1393,"rank":164,"pct":60.8,"board_size":417},"longer_query":{"rating":1406.6,"rank":138,"pct":65.4,"board_size":397},"non_english":{"rating":1380,"rank":165,"pct":60.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9047,"stderr":0.0185,"tested_as":"gpt-6-luna_max","approx":false,"run_date":"2026-09-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F7F3QFMAkwnCV62HcvxP96q.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":86.1,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.414,"stderr":0.0156,"tested_as":"gpt-6-luna_max","approx":false,"run_date":"2026-09-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FHX9sRVWJtZiNvneALnVzs8.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":51.5,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9889,"stderr":0.0067,"tested_as":"gpt-6-luna_max","approx":false,"run_date":"2026-09-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F4uDz9b6SosxDSZf7swMD9D.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":92,"tested_models":313},{"benchmark":"frontiermath","score":0.7895,"stderr":0.0242,"tested_as":"gpt-6-luna_max","approx":false,"run_date":"2026-09-22","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":85.1,"tested_models":122}],"price":{"openrouter_id":"openai/gpt-6-luna","input_per_m":0.1,"output_per_m":0.5,"blended_per_m":0.2,"context_length":1050000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-6-luna-max"},{"slug":"gpt-5-3-chat","name":"GPT-5.3 Chat","source_name":"GPT-5.3 Chat","base":"GPT-5.3 Chat","variant":null,"org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":58.2,"rank":143,"coverage":0.75,"categories":{"coding":59.6,"reasoning":59.8,"math":55.7,"chat":59.3,"instructions":61.7}},"arena":{"text":{"rank":171,"date":"2026-10-28","rating":1389,"lo":1384.8,"hi":1393.2,"votes":34316,"pct":59.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1407.5,"rank":168,"pct":59.6,"board_size":414},"math":{"rating":1388.8,"rank":180,"pct":55.7,"board_size":405},"creative_writing":{"rating":1355.6,"rank":163,"pct":61.1,"board_size":417},"instruction_following":{"rating":1378.2,"rank":161,"pct":61.7,"board_size":419},"hard_prompts":{"rating":1398.6,"rank":169,"pct":59.8,"board_size":419},"multi_turn":{"rating":1412.1,"rank":133,"pct":68.3,"board_size":417},"longer_query":{"rating":1395,"rank":157,"pct":60.6,"board_size":397},"non_english":{"rating":1382.1,"rank":163,"pct":61.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gpt-5-3-chat"},{"slug":"solar-pro-4","name":"Solar Pro 4","source_name":"Solar Pro 4","base":"Solar Pro 4","variant":null,"org":"upstage","open_weights":false,"model_license":"Proprietary","siscope":{"score":43.1,"rank":219,"coverage":1,"categories":{"coding":47.9,"agents":0,"reasoning":60.8,"math":66.6,"chat":59.1,"instructions":60.3}},"arena":{"text":{"rank":172,"date":"2026-10-28","rating":1388.5,"lo":1383.5,"hi":1393.5,"votes":26159,"pct":59.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":113,"date":"2026-10-28","rating":1370.2,"lo":1359.8,"hi":1380.5,"votes":4630,"pct":25.8,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":57,"date":"2026-11-02","score":-0.2094,"lo":-0.2304,"hi":-0.1885,"sessions":10951,"cost_per_task_p50":0.054,"pct":0,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1437.4,"rank":125,"pct":70,"board_size":414},"math":{"rating":1414.9,"rank":134,"pct":66.6,"board_size":405},"creative_writing":{"rating":1318.2,"rank":204,"pct":51.2,"board_size":417},"instruction_following":{"rating":1375.1,"rank":167,"pct":60.3,"board_size":419},"hard_prompts":{"rating":1400.4,"rank":165,"pct":60.8,"board_size":419},"multi_turn":{"rating":1387.3,"rank":173,"pct":58.7,"board_size":417},"longer_query":{"rating":1382.7,"rank":173,"pct":56.6,"board_size":397},"non_english":{"rating":1363.2,"rank":177,"pct":57.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"upstage/solar-pro4","input_per_m":0.15,"output_per_m":0.6,"blended_per_m":0.2625,"context_length":524288,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/solar-pro-4"},{"slug":"qwen3-30b-a3b-instruct-2507","name":"Qwen3 30B A3B Instruct (2507)","source_name":"Qwen3-30B-A3B-Instruct (2507)","base":"Qwen3 30B A3B Instruct","variant":"2507","org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":59.3,"rank":139,"coverage":0.75,"categories":{"coding":62.7,"reasoning":59.6,"math":57.2,"chat":58.9,"instructions":57.7}},"arena":{"text":{"rank":173,"date":"2026-10-28","rating":1383.8,"lo":1378.9,"hi":1388.7,"votes":23312,"pct":58.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1416,"rank":155,"pct":62.7,"board_size":414},"math":{"rating":1394.3,"rank":174,"pct":57.2,"board_size":405},"creative_writing":{"rating":1316.9,"rank":207,"pct":50.5,"board_size":417},"instruction_following":{"rating":1362.9,"rank":178,"pct":57.7,"board_size":419},"hard_prompts":{"rating":1397.8,"rank":170,"pct":59.6,"board_size":419},"multi_turn":{"rating":1378.5,"rank":179,"pct":57.2,"board_size":417},"longer_query":{"rating":1378.3,"rank":176,"pct":55.8,"board_size":397},"non_english":{"rating":1371.5,"rank":173,"pct":58.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen3-30b-a3b-instruct-2507"},{"slug":"glm-4-5-air","name":"GLM-4.5-Air","source_name":"GLM-4.5-Air","base":"GLM-4.5-Air","variant":null,"org":"zai","open_weights":true,"model_license":"MIT","siscope":{"score":56.8,"rank":151,"coverage":0.75,"categories":{"coding":56.7,"reasoning":57.2,"math":57.7,"chat":58.6,"instructions":55.7}},"arena":{"text":{"rank":174,"date":"2026-10-28","rating":1383.7,"lo":1379.5,"hi":1387.9,"votes":30652,"pct":58.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1396.7,"rank":180,"pct":56.7,"board_size":414},"math":{"rating":1395.5,"rank":172,"pct":57.7,"board_size":405},"creative_writing":{"rating":1343.1,"rank":179,"pct":57.2,"board_size":417},"instruction_following":{"rating":1353.7,"rank":186,"pct":55.7,"board_size":419},"hard_prompts":{"rating":1378.6,"rank":180,"pct":57.2,"board_size":419},"multi_turn":{"rating":1371,"rank":182,"pct":56.5,"board_size":417},"longer_query":{"rating":1365.9,"rank":185,"pct":53.5,"board_size":397},"non_english":{"rating":1366,"rank":176,"pct":58.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"z-ai/glm-4.5-air","input_per_m":0.13,"output_per_m":0.85,"blended_per_m":0.31,"context_length":131072,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/glm-4-5-air"},{"slug":"gpt-4-1-2025-04-14","name":"GPT-4.1 (2025-04-14)","source_name":"GPT-4.1 (2025-04-14)","base":"GPT-4.1","variant":"2025-04-14","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":35.7,"rank":250,"coverage":0.75,"categories":{"coding":29.3,"reasoning":41.3,"math":28.3,"chat":58.4,"instructions":58.6}},"arena":{"text":{"rank":175,"date":"2026-10-28","rating":1382.9,"lo":1379.2,"hi":1386.6,"votes":50298,"pct":58.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":88,"date":"2026-10-19","rating":1210.4,"lo":1203.8,"hi":1217.1,"votes":40998,"pct":47.6,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1390.7,"rank":184,"pct":55.7,"board_size":414},"math":{"rating":1369.4,"rank":199,"pct":51,"board_size":405},"creative_writing":{"rating":1363.4,"rank":153,"pct":63.5,"board_size":417},"instruction_following":{"rating":1366.9,"rank":174,"pct":58.6,"board_size":419},"hard_prompts":{"rating":1384.1,"rank":176,"pct":58.1,"board_size":419},"multi_turn":{"rating":1397.7,"rank":157,"pct":62.5,"board_size":417},"longer_query":{"rating":1384.8,"rank":172,"pct":56.8,"board_size":397},"non_english":{"rating":1369.7,"rank":174,"pct":58.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.6692,"stderr":0.0282,"tested_as":"gpt-4.1-2025-04-14","approx":false,"run_date":"2025-04-14","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FGj8pd5gU9r4LqwDK8XZ4mL.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":38.6,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.311,"stderr":0.0146,"tested_as":"gpt-4.1-2025-04-14","approx":false,"run_date":"2026-08-31","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FavdYKfKUuY6EvfVdxftBE8.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":27.3,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.3833,"stderr":0.0632,"tested_as":"gpt-4.1-2025-04-14","approx":false,"run_date":"2025-04-14","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FVAQtARXUPTpdxGKMekUSbX.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":28.2,"tested_models":313},{"benchmark":"frontiermath","score":0.0596,"stderr":0.0141,"tested_as":"gpt-4.1-2025-04-14","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FkCG2nzspryMy7LBwWPqwXy.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":5.8,"tested_models":122},{"benchmark":"swe_bench_verified","score":0.4854,"stderr":0.0228,"tested_as":"gpt-4.1-2025-04-14","approx":false,"run_date":"2026-02-08","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FSheUt9cNpkSevy4r6Gsr3u.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":2.9,"tested_models":35}],"price":{"openrouter_id":"openai/gpt-4.1","input_per_m":2,"output_per_m":8,"blended_per_m":3.5,"context_length":1047576,"modalities_in":["image","text","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-4-1-2025-04-14"},{"slug":"kimi-k2-preview-0905","name":"Kimi K2 Preview (0905)","source_name":"Kimi K2 Preview (0905)","base":"Kimi K2 Preview","variant":"0905","org":"moonshot","open_weights":true,"model_license":"Modified MIT","siscope":{"score":56.9,"rank":150,"coverage":0.75,"categories":{"coding":57.4,"reasoning":57.9,"math":58.9,"chat":58.1,"instructions":54.5}},"arena":{"text":{"rank":176,"date":"2026-10-28","rating":1379.9,"lo":1373.4,"hi":1386.4,"votes":11592,"pct":58.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1399.1,"rank":177,"pct":57.4,"board_size":414},"math":{"rating":1397.3,"rank":167,"pct":58.9,"board_size":405},"creative_writing":{"rating":1349.4,"rank":167,"pct":60.1,"board_size":417},"instruction_following":{"rating":1347.6,"rank":191,"pct":54.5,"board_size":419},"hard_prompts":{"rating":1383.6,"rank":177,"pct":57.9,"board_size":419},"multi_turn":{"rating":1365.1,"rank":188,"pct":55,"board_size":417},"longer_query":{"rating":1352.8,"rank":199,"pct":50,"board_size":397},"non_english":{"rating":1372.4,"rank":171,"pct":59.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/kimi-k2-preview-0905"},{"slug":"gemini-2-5-flash-lite-preview-non-thinking-09-2025","name":"Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)","source_name":"Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)","base":"Gemini 2.5 Flash-Lite Preview","variant":"Non-Thinking, 09-2025","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":53.2,"rank":166,"coverage":0.75,"categories":{"coding":50.6,"reasoning":56.9,"math":52.7,"chat":57.9,"instructions":56}},"arena":{"text":{"rank":177,"date":"2026-10-28","rating":1379.3,"lo":1375.9,"hi":1382.7,"votes":47418,"pct":57.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":95,"date":"2026-10-19","rating":1198.3,"lo":1188.8,"hi":1207.8,"votes":4862,"pct":43.4,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1371.7,"rank":205,"pct":50.6,"board_size":414},"math":{"rating":1373.1,"rank":192,"pct":52.7,"board_size":405},"creative_writing":{"rating":1358.2,"rank":160,"pct":61.8,"board_size":417},"instruction_following":{"rating":1355.3,"rank":185,"pct":56,"board_size":419},"hard_prompts":{"rating":1377.1,"rank":181,"pct":56.9,"board_size":419},"multi_turn":{"rating":1366.2,"rank":186,"pct":55.5,"board_size":417},"longer_query":{"rating":1372.7,"rank":180,"pct":54.8,"board_size":397},"non_english":{"rating":1368.7,"rank":175,"pct":58.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemini-2-5-flash-lite-preview-non-thinking-09-2025"},{"slug":"nvidia-nemotron-3-super-120b-a12b","name":"Nemotron 3 Super 120B A12B","source_name":"NVIDIA-Nemotron-3-Super-120B-A12B","base":"Nemotron 3 Super 120B A12B","variant":null,"org":"nvidia","open_weights":true,"model_license":"NVIDIA Open Model","siscope":{"score":56.5,"rank":153,"coverage":0.75,"categories":{"coding":58.4,"reasoning":58.4,"math":54.5,"chat":57.7,"instructions":54.1}},"arena":{"text":{"rank":178,"date":"2026-10-28","rating":1377.4,"lo":1370.3,"hi":1384.4,"votes":7870,"pct":57.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1403.3,"rank":173,"pct":58.4,"board_size":414},"math":{"rating":1380.1,"rank":185,"pct":54.5,"board_size":405},"creative_writing":{"rating":1316,"rank":209,"pct":49.8,"board_size":417},"instruction_following":{"rating":1347.3,"rank":193,"pct":54.1,"board_size":419},"hard_prompts":{"rating":1385.9,"rank":175,"pct":58.4,"board_size":419},"multi_turn":{"rating":1368.8,"rank":184,"pct":56,"board_size":417},"longer_query":{"rating":1361.6,"rank":189,"pct":52.5,"board_size":397},"non_english":{"rating":1355.5,"rank":188,"pct":55.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/nvidia-nemotron-3-super-120b-a12b"},{"slug":"hunyuan-turbos-20250416","name":"Hunyuan TurboS (2025-04-16)","source_name":"Hunyuan TurboS (20250416)","base":"Hunyuan TurboS","variant":"2025-04-16","org":"tencent","open_weights":false,"model_license":"Proprietary","siscope":{"score":50.1,"rank":187,"coverage":0.75,"categories":{"coding":46.7,"reasoning":56,"math":47.8,"chat":57.4,"instructions":53.3}},"arena":{"text":{"rank":179,"date":"2026-10-28","rating":1377.2,"lo":1370.7,"hi":1383.6,"votes":10623,"pct":57.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1361.2,"rank":221,"pct":46.7,"board_size":414},"math":{"rating":1358.5,"rank":212,"pct":47.8,"board_size":405},"creative_writing":{"rating":1358.4,"rank":159,"pct":62,"board_size":417},"instruction_following":{"rating":1343.6,"rank":196,"pct":53.3,"board_size":419},"hard_prompts":{"rating":1373.9,"rank":185,"pct":56,"board_size":419},"multi_turn":{"rating":1387,"rank":174,"pct":58.4,"board_size":417},"longer_query":{"rating":1365.6,"rank":187,"pct":53,"board_size":397},"non_english":{"rating":1362.8,"rank":178,"pct":57.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/hunyuan-turbos-20250416"},{"slug":"claude-opus-4-thinking-16k-20250514","name":"Claude Opus 4 (Thinking 16K, 2025-05-14)","source_name":"Claude Opus 4 (Thinking 16K, 20250514)","base":"Claude Opus 4","variant":"Thinking 16K, 2025-05-14","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":58.1,"rank":144,"coverage":0.75,"categories":{"coding":72.2,"reasoning":55.5,"math":49.1,"chat":57.2,"instructions":73.2}},"arena":{"text":{"rank":180,"date":"2026-10-28","rating":1377.1,"lo":1372.6,"hi":1381.5,"votes":35904,"pct":57.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":99,"date":"2026-10-19","rating":1191.8,"lo":1175.8,"hi":1207.7,"votes":1290,"pct":41,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1442.1,"rank":116,"pct":72.2,"board_size":414},"math":{"rating":1390.7,"rank":177,"pct":56.4,"board_size":405},"creative_writing":{"rating":1386,"rank":127,"pct":69.7,"board_size":417},"instruction_following":{"rating":1406.3,"rank":113,"pct":73.2,"board_size":419},"hard_prompts":{"rating":1399.3,"rank":167,"pct":60.3,"board_size":419},"multi_turn":{"rating":1395.8,"rank":161,"pct":61.5,"board_size":417},"longer_query":{"rating":1422,"rank":107,"pct":73.2,"board_size":397},"non_english":{"rating":1361.5,"rank":180,"pct":57.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.7626,"stderr":0.0303,"tested_as":"claude-opus-4-20250514_16K","approx":false,"run_date":"2025-05-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FCtxFusPxCraL3EeRJu2c5k.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":50.6,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.6,"stderr":0.0739,"tested_as":"claude-opus-4-20250514_16K","approx":false,"run_date":"2025-05-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FXz2F28L5k8HFNfY7Lo8Ggw.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":41.7,"tested_models":313}],"price":null,"url":"https://siscope.app/models/claude-opus-4-thinking-16k-20250514"},{"slug":"glm-4-6v","name":"GLM-4.6V","source_name":"GLM-4.6V","base":"GLM-4.6V","variant":null,"org":"zai","open_weights":true,"model_license":"MIT","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"coding":55.2,"reasoning":54.3,"chat":56.9,"instructions":54.8}},"arena":{"text":{"rank":181,"date":"2026-10-28","rating":1376.5,"lo":1365.3,"hi":1387.6,"votes":2833,"pct":56.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":113,"date":"2026-10-19","rating":1163.9,"lo":1150.2,"hi":1177.6,"votes":2455,"pct":32.5,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1389.8,"rank":186,"pct":55.2,"board_size":414},"creative_writing":{"rating":1347.3,"rank":171,"pct":59.1,"board_size":417},"instruction_following":{"rating":1351.3,"rank":190,"pct":54.8,"board_size":419},"hard_prompts":{"rating":1367.5,"rank":192,"pct":54.3,"board_size":419},"multi_turn":{"rating":1358.9,"rank":197,"pct":52.9,"board_size":417},"longer_query":{"rating":1357.6,"rank":192,"pct":51.5,"board_size":397},"non_english":{"rating":1358.8,"rank":183,"pct":56.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"z-ai/glm-4.6v","input_per_m":0.3,"output_per_m":0.9,"blended_per_m":0.45,"context_length":131072,"modalities_in":["image","text","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/glm-4-6v"},{"slug":"deepseek-v3-0324","name":"DeepSeek-V3 (0324)","source_name":"DeepSeek-V3 (0324)","base":"DeepSeek-V3","variant":"0324","org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":51.6,"rank":174,"coverage":0.75,"categories":{"coding":49.4,"reasoning":53.6,"math":52,"chat":56.7,"instructions":53.6}},"arena":{"text":{"rank":182,"date":"2026-10-28","rating":1374.6,"lo":1370.8,"hi":1378.5,"votes":44977,"pct":56.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1367.8,"rank":210,"pct":49.4,"board_size":414},"math":{"rating":1372.5,"rank":195,"pct":52,"board_size":405},"creative_writing":{"rating":1364,"rank":151,"pct":63.9,"board_size":417},"instruction_following":{"rating":1344.5,"rank":195,"pct":53.6,"board_size":419},"hard_prompts":{"rating":1364.9,"rank":195,"pct":53.6,"board_size":419},"multi_turn":{"rating":1388.6,"rank":169,"pct":59.6,"board_size":417},"longer_query":{"rating":1352,"rank":201,"pct":49.5,"board_size":397},"non_english":{"rating":1357.8,"rank":185,"pct":56,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/deepseek-v3-0324"},{"slug":"gpt-5-mini-high","name":"GPT-5 mini (High)","source_name":"GPT-5 mini (High)","base":"GPT-5 mini","variant":"High","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":50.3,"rank":185,"coverage":0.75,"categories":{"coding":58.8,"reasoning":40.8,"math":58.4,"chat":56.5,"instructions":56.5}},"arena":{"text":{"rank":183,"date":"2026-10-28","rating":1373.2,"lo":1368.6,"hi":1377.8,"votes":26793,"pct":56.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":93,"date":"2026-10-19","rating":1202.2,"lo":1194.4,"hi":1210,"votes":28943,"pct":44.6,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1405.7,"rank":171,"pct":58.8,"board_size":414},"math":{"rating":1378,"rank":186,"pct":54.2,"board_size":405},"creative_writing":{"rating":1325,"rank":198,"pct":52.6,"board_size":417},"instruction_following":{"rating":1356.5,"rank":183,"pct":56.5,"board_size":419},"hard_prompts":{"rating":1379.9,"rank":179,"pct":57.4,"board_size":419},"multi_turn":{"rating":1362.8,"rank":193,"pct":53.8,"board_size":417},"longer_query":{"rating":1354.6,"rank":197,"pct":50.5,"board_size":397},"non_english":{"rating":1362.4,"rank":179,"pct":57.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.75,"stderr":0.0228,"tested_as":"gpt-5-mini-2025-08-07_high","approx":false,"run_date":"2025-10-30","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FjP8EyLtPFsakgnsHe2oJM6.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":47.9,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.216,"stderr":0.013,"tested_as":"gpt-5-mini-2025-08-07_high","approx":false,"run_date":"2026-08-10","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":17.2,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.8667,"stderr":0.0429,"tested_as":"gpt-5-mini-2025-08-07_high","approx":false,"run_date":"2025-10-30","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FR82gycJfm5jaCdh32tFkH4.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":67.3,"tested_models":313},{"benchmark":"frontiermath","score":0.4667,"stderr":0.0296,"tested_as":"gpt-5-mini-2025-08-07_high","approx":false,"run_date":"2026-06-12","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FYSR9WCR2SnJYvP7DJwX7YN.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":53.7,"tested_models":122}],"price":{"openrouter_id":"openai/gpt-5-mini","input_per_m":0.25,"output_per_m":2,"blended_per_m":0.6875,"context_length":400000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-mini-high"},{"slug":"deepseek-r1","name":"DeepSeek-R1","source_name":"DeepSeek-R1","base":"DeepSeek-R1","variant":null,"org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":49.1,"rank":191,"coverage":0.75,"categories":{"coding":50.4,"reasoning":47.4,"math":46.4,"chat":56.2,"instructions":56.9}},"arena":{"text":{"rank":184,"date":"2026-10-28","rating":1372.7,"lo":1367.8,"hi":1377.5,"votes":18524,"pct":56.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1371.1,"rank":206,"pct":50.4,"board_size":414},"math":{"rating":1392.5,"rank":175,"pct":56.9,"board_size":405},"creative_writing":{"rating":1353.9,"rank":164,"pct":60.8,"board_size":417},"instruction_following":{"rating":1357.3,"rank":181,"pct":56.9,"board_size":419},"hard_prompts":{"rating":1361.1,"rank":203,"pct":51.7,"board_size":419},"multi_turn":{"rating":1390.5,"rank":166,"pct":60.3,"board_size":417},"longer_query":{"rating":1354.7,"rank":195,"pct":51,"board_size":397},"non_english":{"rating":1356.4,"rank":187,"pct":55.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.7172,"stderr":0.0307,"tested_as":"DeepSeek-R1","approx":false,"run_date":"2025-05-26","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FfFGyQR2mfDufvrSV2rzWyV.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":43.1,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.5333,"stderr":0.0752,"tested_as":"DeepSeek-R1","approx":false,"run_date":"2025-02-26","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FbBY5VZzpDkmTBdSSvu5Ups.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":35.9,"tested_models":313}],"price":null,"url":"https://siscope.app/models/deepseek-r1"},{"slug":"gpt-5-4-nano-high","name":"GPT-5.4 nano (High)","source_name":"GPT-5.4 nano (High)","base":"GPT-5.4 nano","variant":"High","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":49.6,"rank":189,"coverage":0.75,"categories":{"coding":58.6,"reasoning":38.5,"math":60.8,"chat":56,"instructions":57.4}},"arena":{"text":{"rank":185,"date":"2026-10-28","rating":1372,"lo":1368.2,"hi":1375.7,"votes":62314,"pct":56,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":96,"date":"2026-10-19","rating":1195.6,"lo":1189.3,"hi":1201.9,"votes":25624,"pct":42.8,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1404.5,"rank":172,"pct":58.6,"board_size":414},"math":{"rating":1405.2,"rank":155,"pct":61.9,"board_size":405},"creative_writing":{"rating":1314,"rank":212,"pct":49,"board_size":417},"instruction_following":{"rating":1361.7,"rank":179,"pct":57.4,"board_size":419},"hard_prompts":{"rating":1380.4,"rank":178,"pct":57.7,"board_size":419},"multi_turn":{"rating":1382.1,"rank":176,"pct":57.9,"board_size":417},"longer_query":{"rating":1365.2,"rank":188,"pct":52.8,"board_size":397},"non_english":{"rating":1359.4,"rank":182,"pct":56.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.7847,"stderr":0.0244,"tested_as":"gpt-5.4-nano-2026-03-17_high","approx":false,"run_date":"2026-04-14","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FfZB3qGSohAVYzN97mniuUp.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":54.8,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.117,"stderr":0.0102,"tested_as":"gpt-5.4-nano-2026-03-17_high","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F3QBsxKkbF2R2LEXTd6HDrJ.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":3,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.8778,"stderr":0.0394,"tested_as":"gpt-5.4-nano-2026-03-17_high","approx":false,"run_date":"2026-04-14","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FjVv9m8DjkdpZaLPdUzAnG9.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":70.2,"tested_models":313},{"benchmark":"frontiermath","score":0.4491,"stderr":0.0295,"tested_as":"gpt-5.4-nano-2026-03-17_high","approx":false,"run_date":"2026-06-12","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FiKtopjTjyCWZqJaEjcc7ZL.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":50.4,"tested_models":122}],"price":{"openrouter_id":"openai/gpt-5.4-nano","input_per_m":0.2,"output_per_m":1.25,"blended_per_m":0.4625,"context_length":400000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-4-nano-high"},{"slug":"kimi-k2-preview-0711","name":"Kimi K2 Preview (0711)","source_name":"Kimi K2 Preview (0711)","base":"Kimi K2 Preview","variant":"0711","org":"moonshot","open_weights":true,"model_license":"Modified MIT","siscope":{"score":51.5,"rank":176,"coverage":0.75,"categories":{"coding":51.3,"reasoning":53.8,"math":50.5,"chat":55.7,"instructions":49.3}},"arena":{"text":{"rank":186,"date":"2026-10-28","rating":1370.7,"lo":1365.9,"hi":1375.6,"votes":27139,"pct":55.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1376.6,"rank":202,"pct":51.3,"board_size":414},"math":{"rating":1367.2,"rank":201,"pct":50.5,"board_size":405},"creative_writing":{"rating":1323.3,"rank":199,"pct":52.4,"board_size":417},"instruction_following":{"rating":1324.2,"rank":213,"pct":49.3,"board_size":419},"hard_prompts":{"rating":1365.4,"rank":193,"pct":53.8,"board_size":419},"multi_turn":{"rating":1370.7,"rank":183,"pct":56.2,"board_size":417},"longer_query":{"rating":1325.7,"rank":222,"pct":44.2,"board_size":397},"non_english":{"rating":1357.7,"rank":186,"pct":55.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/kimi-k2-preview-0711"},{"slug":"mistral-medium-3-2505","name":"Mistral Medium 3 (2505)","source_name":"Mistral Medium 3 (2505)","base":"Mistral Medium 3","variant":"2505","org":"mistral","open_weights":false,"model_license":"Proprietary","siscope":{"score":51.1,"rank":181,"coverage":0.75,"categories":{"coding":54.5,"reasoning":53.3,"math":46.5,"chat":55.5,"instructions":52.6}},"arena":{"text":{"rank":187,"date":"2026-10-28","rating":1370.1,"lo":1365.4,"hi":1374.8,"votes":32777,"pct":55.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":117,"date":"2026-10-19","rating":1157,"lo":1148.7,"hi":1165.3,"votes":10793,"pct":30.1,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1385.5,"rank":189,"pct":54.5,"board_size":414},"math":{"rating":1352.5,"rank":217,"pct":46.5,"board_size":405},"creative_writing":{"rating":1343.4,"rank":177,"pct":57.5,"board_size":417},"instruction_following":{"rating":1338.4,"rank":199,"pct":52.6,"board_size":419},"hard_prompts":{"rating":1364.4,"rank":196,"pct":53.3,"board_size":419},"multi_turn":{"rating":1383.4,"rank":175,"pct":58.2,"board_size":417},"longer_query":{"rating":1360,"rank":190,"pct":52.3,"board_size":397},"non_english":{"rating":1353,"rank":189,"pct":55,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"mistralai/mistral-medium-3","input_per_m":0.4,"output_per_m":2,"blended_per_m":0.8,"context_length":131072,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/mistral-medium-3-2505"},{"slug":"grok-3-mini-high","name":"Grok 3 Mini (High)","source_name":"Grok 3 Mini (High)","base":"Grok 3 Mini","variant":"High","org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":54,"rank":164,"coverage":0.75,"categories":{"coding":52.3,"reasoning":56.2,"math":54.7,"chat":55.3,"instructions":56.7}},"arena":{"text":{"rank":188,"date":"2026-10-28","rating":1369.5,"lo":1364.1,"hi":1374.9,"votes":15595,"pct":55.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1379,"rank":198,"pct":52.3,"board_size":414},"math":{"rating":1385.4,"rank":184,"pct":54.7,"board_size":405},"creative_writing":{"rating":1334.3,"rank":188,"pct":55,"board_size":417},"instruction_following":{"rating":1356.6,"rank":182,"pct":56.7,"board_size":419},"hard_prompts":{"rating":1374.4,"rank":184,"pct":56.2,"board_size":419},"multi_turn":{"rating":1354.8,"rank":199,"pct":52.4,"board_size":417},"longer_query":{"rating":1371.6,"rank":182,"pct":54.3,"board_size":397},"non_english":{"rating":1351.9,"rank":191,"pct":54.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/grok-3-mini-high"},{"slug":"gemini-2-5-flash-lite-preview-thinking-06-17","name":"Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)","source_name":"Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)","base":"Gemini 2.5 Flash-Lite Preview","variant":"Thinking, 06-17","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":52,"rank":168,"coverage":0.75,"categories":{"coding":50.8,"reasoning":55.7,"math":49.3,"chat":55,"instructions":58.4}},"arena":{"text":{"rank":189,"date":"2026-10-28","rating":1369.2,"lo":1364.7,"hi":1373.7,"votes":32381,"pct":55,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":101,"date":"2026-10-19","rating":1187.5,"lo":1180.1,"hi":1194.9,"votes":35914,"pct":39.8,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1372.5,"rank":204,"pct":50.8,"board_size":414},"math":{"rating":1362.1,"rank":206,"pct":49.3,"board_size":405},"creative_writing":{"rating":1366.8,"rank":148,"pct":64.7,"board_size":417},"instruction_following":{"rating":1366.6,"rank":175,"pct":58.4,"board_size":419},"hard_prompts":{"rating":1373.6,"rank":186,"pct":55.7,"board_size":419},"multi_turn":{"rating":1359.6,"rank":196,"pct":53.1,"board_size":417},"longer_query":{"rating":1373.2,"rank":179,"pct":55.1,"board_size":397},"non_english":{"rating":1360,"rank":181,"pct":56.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemini-2-5-flash-lite-preview-thinking-06-17"},{"slug":"qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking","source_name":"Qwen3-Next-80B-A3B-Thinking","base":"Qwen3 Next 80B A3B Thinking","variant":null,"org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":55.2,"rank":159,"coverage":0.75,"categories":{"coding":55.9,"reasoning":54.5,"math":59.4,"chat":54.8,"instructions":53.1}},"arena":{"text":{"rank":190,"date":"2026-10-28","rating":1368.1,"lo":1362.2,"hi":1373.9,"votes":13476,"pct":54.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1391.3,"rank":183,"pct":55.9,"board_size":414},"math":{"rating":1397.9,"rank":165,"pct":59.4,"board_size":405},"creative_writing":{"rating":1314,"rank":213,"pct":49,"board_size":417},"instruction_following":{"rating":1343.1,"rank":197,"pct":53.1,"board_size":419},"hard_prompts":{"rating":1371.2,"rank":191,"pct":54.5,"board_size":419},"multi_turn":{"rating":1346,"rank":208,"pct":50.2,"board_size":417},"longer_query":{"rating":1352.7,"rank":200,"pct":49.7,"board_size":397},"non_english":{"rating":1342.3,"rank":197,"pct":53.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen3-next-80b-a3b-thinking"},{"slug":"qwen2-5-max","name":"Qwen2.5-Max","source_name":"Qwen2.5-Max","base":"Qwen2.5-Max","variant":null,"org":"alibaba","open_weights":false,"model_license":"Proprietary","siscope":{"score":49,"rank":192,"coverage":0.75,"categories":{"coding":46.2,"reasoning":51.4,"math":50.7,"chat":54.5,"instructions":51.7}},"arena":{"text":{"rank":191,"date":"2026-10-28","rating":1366.6,"lo":1362.5,"hi":1370.7,"votes":32487,"pct":54.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1359,"rank":223,"pct":46.2,"board_size":414},"math":{"rating":1369.1,"rank":200,"pct":50.7,"board_size":405},"creative_writing":{"rating":1338.4,"rank":185,"pct":55.8,"board_size":417},"instruction_following":{"rating":1334.7,"rank":203,"pct":51.7,"board_size":419},"hard_prompts":{"rating":1359.5,"rank":204,"pct":51.4,"board_size":419},"multi_turn":{"rating":1364.4,"rank":190,"pct":54.6,"board_size":417},"longer_query":{"rating":1357.6,"rank":193,"pct":51.5,"board_size":397},"non_english":{"rating":1352,"rank":190,"pct":54.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen2-5-max"},{"slug":"qwen3-235b-a22b","name":"Qwen3 235B A22B","source_name":"Qwen3-235B-A22B","base":"Qwen3 235B A22B","variant":null,"org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":51.1,"rank":180,"coverage":0.75,"categories":{"coding":54,"reasoning":46.8,"math":57.4,"chat":54.3,"instructions":51.2}},"arena":{"text":{"rank":192,"date":"2026-10-28","rating":1366.2,"lo":1361.5,"hi":1370.9,"votes":25950,"pct":54.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1384.4,"rank":191,"pct":54,"board_size":414},"math":{"rating":1394.9,"rank":173,"pct":57.4,"board_size":405},"creative_writing":{"rating":1316,"rank":210,"pct":49.8,"board_size":417},"instruction_following":{"rating":1332.9,"rank":205,"pct":51.2,"board_size":419},"hard_prompts":{"rating":1362.1,"rank":201,"pct":52.2,"board_size":419},"multi_turn":{"rating":1360.5,"rank":195,"pct":53.4,"board_size":417},"longer_query":{"rating":1351.9,"rank":202,"pct":49.2,"board_size":397},"non_english":{"rating":1348.5,"rank":194,"pct":53.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.7071,"stderr":0.0271,"tested_as":"qwen3-235b-a22b","approx":false,"run_date":"2025-06-03","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FagebmxGseTvmvN4AHN8i4m.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":41.3,"tested_models":333}],"price":null,"url":"https://siscope.app/models/qwen3-235b-a22b"},{"slug":"claude-opus-4-20250514","name":"Claude Opus 4 (2025-05-14)","source_name":"Claude Opus 4 (20250514)","base":"Claude Opus 4","variant":"2025-05-14","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":45,"rank":212,"coverage":0.75,"categories":{"coding":42.3,"reasoning":48.6,"math":40.9,"chat":54.1,"instructions":59.6}},"arena":{"text":{"rank":193,"date":"2026-10-28","rating":1366,"lo":1361.6,"hi":1370.3,"votes":43037,"pct":54.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":107,"date":"2026-10-19","rating":1175.6,"lo":1162.7,"hi":1188.6,"votes":2172,"pct":36.1,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1401.5,"rank":174,"pct":58.1,"board_size":414},"math":{"rating":1372.9,"rank":194,"pct":52.2,"board_size":405},"creative_writing":{"rating":1374.6,"rank":141,"pct":66.3,"board_size":417},"instruction_following":{"rating":1373.5,"rank":170,"pct":59.6,"board_size":419},"hard_prompts":{"rating":1376.5,"rank":182,"pct":56.7,"board_size":419},"multi_turn":{"rating":1388.3,"rank":170,"pct":59.4,"board_size":417},"longer_query":{"rating":1401.5,"rank":148,"pct":62.9,"board_size":397},"non_english":{"rating":1351.9,"rank":192,"pct":54.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.6919,"stderr":0.0329,"tested_as":"claude-opus-4-20250514","approx":false,"run_date":"2025-05-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FEnjJ8bGi9vRNNQFzfkLCkQ.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":40.4,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.4222,"stderr":0.0745,"tested_as":"claude-opus-4-20250514","approx":false,"run_date":"2025-05-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FaCbfcxGpLpPc9XkZNcuF4o.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":29.5,"tested_models":313},{"benchmark":"swe_bench_verified","score":0.7066,"stderr":0.0207,"tested_as":"claude-opus-4-20250514","approx":false,"run_date":"2026-02-06","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FRbcvuVChvxK6SMQbPK8iRn.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":26.5,"tested_models":35}],"price":null,"url":"https://siscope.app/models/claude-opus-4-20250514"},{"slug":"o1-2024-12-17","name":"o1 (2024-12-17)","source_name":"o1 (2024-12-17)","base":"o1","variant":"2024-12-17","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":51.9,"rank":169,"coverage":0.75,"categories":{"coding":48.7,"reasoning":54.8,"math":55.4,"chat":53.8,"instructions":58.9}},"arena":{"text":{"rank":194,"date":"2026-10-28","rating":1365.8,"lo":1361.3,"hi":1370.3,"votes":27807,"pct":53.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":111,"date":"2026-10-19","rating":1168.4,"lo":1157.6,"hi":1179.1,"votes":3694,"pct":33.7,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1366.6,"rank":213,"pct":48.7,"board_size":414},"math":{"rating":1388.4,"rank":181,"pct":55.4,"board_size":405},"creative_writing":{"rating":1347.2,"rank":172,"pct":58.9,"board_size":417},"instruction_following":{"rating":1367.2,"rank":173,"pct":58.9,"board_size":419},"hard_prompts":{"rating":1371.4,"rank":190,"pct":54.8,"board_size":419},"multi_turn":{"rating":1354.7,"rank":200,"pct":52.2,"board_size":417},"longer_query":{"rating":1377.5,"rank":178,"pct":55.3,"board_size":397},"non_english":{"rating":1358.4,"rank":184,"pct":56.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/o1-2024-12-17"},{"slug":"gpt-oss-120b","name":"gpt-oss-120b","source_name":"gpt-oss-120b","base":"gpt-oss-120b","variant":null,"org":"openai","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":51.7,"rank":171,"coverage":0.75,"categories":{"coding":52.5,"reasoning":52.6,"math":55.2,"chat":53.6,"instructions":48.1}},"arena":{"text":{"rank":195,"date":"2026-10-28","rating":1365.5,"lo":1361.1,"hi":1369.8,"votes":30200,"pct":53.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1379.2,"rank":196,"pct":52.5,"board_size":414},"math":{"rating":1388.3,"rank":182,"pct":55.2,"board_size":405},"creative_writing":{"rating":1274.5,"rank":244,"pct":41.6,"board_size":417},"instruction_following":{"rating":1317.8,"rank":218,"pct":48.1,"board_size":419},"hard_prompts":{"rating":1363.3,"rank":199,"pct":52.6,"board_size":419},"multi_turn":{"rating":1339.6,"rank":215,"pct":48.6,"board_size":417},"longer_query":{"rating":1319,"rank":232,"pct":41.7,"board_size":397},"non_english":{"rating":1350.4,"rank":193,"pct":54.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/gpt-oss-120b","input_per_m":0.027,"output_per_m":0.099,"blended_per_m":0.045,"context_length":131072,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-oss-120b"},{"slug":"grok-3-mini-beta","name":"Grok 3 Mini Beta","source_name":"Grok 3 Mini Beta","base":"Grok 3 Mini Beta","variant":null,"org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":50.4,"rank":183,"coverage":0.75,"categories":{"coding":48.2,"reasoning":52.9,"math":51.5,"chat":53.3,"instructions":53.8}},"arena":{"text":{"rank":196,"date":"2026-10-28","rating":1364.2,"lo":1359.1,"hi":1369.3,"votes":20930,"pct":53.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1366.3,"rank":215,"pct":48.2,"board_size":414},"math":{"rating":1372.3,"rank":197,"pct":51.5,"board_size":405},"creative_writing":{"rating":1341.2,"rank":181,"pct":56.7,"board_size":417},"instruction_following":{"rating":1345.9,"rank":194,"pct":53.8,"board_size":419},"hard_prompts":{"rating":1363.6,"rank":198,"pct":52.9,"board_size":419},"multi_turn":{"rating":1351,"rank":203,"pct":51.4,"board_size":417},"longer_query":{"rating":1357,"rank":194,"pct":51.3,"board_size":397},"non_english":{"rating":1348.3,"rank":195,"pct":53.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/grok-3-mini-beta"},{"slug":"amazon-nova-experimental-chat-10-09","name":"Amazon Nova Experimental Chat (10-09)","source_name":"amazon-nova-experimental-chat (10-09)","base":"Amazon Nova Experimental Chat","variant":"10-09","org":"amazon","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"coding":49.9,"reasoning":50.7,"chat":53.1,"instructions":46.9}},"arena":{"text":{"rank":197,"date":"2026-10-28","rating":1363.9,"lo":1353,"hi":1374.8,"votes":2781,"pct":53.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1369.6,"rank":208,"pct":49.9,"board_size":414},"creative_writing":{"rating":1306.2,"rank":219,"pct":47.6,"board_size":417},"instruction_following":{"rating":1314.5,"rank":223,"pct":46.9,"board_size":419},"hard_prompts":{"rating":1355.5,"rank":207,"pct":50.7,"board_size":419},"multi_turn":{"rating":1354.6,"rank":201,"pct":51.9,"board_size":417},"longer_query":{"rating":1332.7,"rank":214,"pct":46.2,"board_size":397},"non_english":{"rating":1339.8,"rank":200,"pct":52.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/amazon-nova-experimental-chat-10-09"},{"slug":"amazon-nova-2-lite","name":"Amazon Nova 2 Lite","source_name":"Amazon Nova 2 Lite","base":"Amazon Nova 2 Lite","variant":null,"org":"amazon","open_weights":false,"model_license":"Proprietary","siscope":{"score":51.3,"rank":178,"coverage":0.75,"categories":{"coding":54.2,"reasoning":53.1,"math":48,"chat":52.9,"instructions":51.9}},"arena":{"text":{"rank":198,"date":"2026-10-28","rating":1361.9,"lo":1355.9,"hi":1367.9,"votes":12415,"pct":52.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1385.2,"rank":190,"pct":54.2,"board_size":414},"math":{"rating":1358.7,"rank":211,"pct":48,"board_size":405},"creative_writing":{"rating":1292.4,"rank":227,"pct":45.7,"board_size":417},"instruction_following":{"rating":1335,"rank":202,"pct":51.9,"board_size":419},"hard_prompts":{"rating":1364.1,"rank":197,"pct":53.1,"board_size":419},"multi_turn":{"rating":1338.1,"rank":219,"pct":47.6,"board_size":417},"longer_query":{"rating":1335.5,"rank":211,"pct":47,"board_size":397},"non_english":{"rating":1337.2,"rank":202,"pct":51.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/amazon-nova-2-lite"},{"slug":"granite-4-2-30b","name":"Granite 4.2 30B","source_name":"Granite 4.2 30B","base":"Granite 4.2 30B","variant":null,"org":"ibm","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"coding":56.2,"reasoning":56.5,"chat":52.6,"instructions":54.3}},"arena":{"text":{"rank":199,"date":"2026-10-28","rating":1361.4,"lo":1351,"hi":1371.9,"votes":3389,"pct":52.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1395.7,"rank":182,"pct":56.2,"board_size":414},"creative_writing":{"rating":1286,"rank":237,"pct":43.3,"board_size":417},"instruction_following":{"rating":1347.4,"rank":192,"pct":54.3,"board_size":419},"hard_prompts":{"rating":1375,"rank":183,"pct":56.5,"board_size":419},"multi_turn":{"rating":1339.3,"rank":216,"pct":48.3,"board_size":417},"longer_query":{"rating":1359.1,"rank":191,"pct":52,"board_size":397},"non_english":{"rating":1340.6,"rank":199,"pct":52.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/granite-4-2-30b"},{"slug":"ling-flash-2-0","name":"Ling Flash 2.0","source_name":"Ling-flash-2.0","base":"Ling Flash 2.0","variant":null,"org":"ant-group","open_weights":true,"model_license":"MIT","siscope":{"score":51.3,"rank":177,"coverage":0.75,"categories":{"coding":54.7,"reasoning":52.4,"math":49.5,"chat":52.4,"instructions":48.3}},"arena":{"text":{"rank":200,"date":"2026-10-28","rating":1361.1,"lo":1353.9,"hi":1368.3,"votes":6952,"pct":52.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1389,"rank":188,"pct":54.7,"board_size":414},"math":{"rating":1364,"rank":205,"pct":49.5,"board_size":405},"creative_writing":{"rating":1287.2,"rank":233,"pct":44.2,"board_size":417},"instruction_following":{"rating":1318.4,"rank":217,"pct":48.3,"board_size":419},"hard_prompts":{"rating":1362.7,"rank":200,"pct":52.4,"board_size":419},"multi_turn":{"rating":1323,"rank":230,"pct":45,"board_size":417},"longer_query":{"rating":1324.1,"rank":225,"pct":43.4,"board_size":397},"non_english":{"rating":1334.9,"rank":204,"pct":51.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/ling-flash-2-0"},{"slug":"minimax-m2-5","name":"MiniMax-M2.5","source_name":"MiniMax-M2.5","base":"MiniMax-M2.5","variant":null,"org":"minimax","open_weights":true,"model_license":"Modified MIT","siscope":{"score":47.9,"rank":198,"coverage":0.75,"categories":{"coding":41.4,"reasoning":55.3,"math":54,"chat":52.2,"instructions":55.5}},"arena":{"text":{"rank":201,"date":"2026-10-28","rating":1359.1,"lo":1355.3,"hi":1363,"votes":42783,"pct":52.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":107,"date":"2026-10-28","rating":1386.2,"lo":1377.8,"hi":1394.5,"votes":7594,"pct":29.8,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1380.4,"rank":195,"pct":53,"board_size":414},"math":{"rating":1377.8,"rank":187,"pct":54,"board_size":405},"creative_writing":{"rating":1330,"rank":194,"pct":53.4,"board_size":417},"instruction_following":{"rating":1352.8,"rank":187,"pct":55.5,"board_size":419},"hard_prompts":{"rating":1371.9,"rank":188,"pct":55.3,"board_size":419},"multi_turn":{"rating":1363.9,"rank":192,"pct":54.1,"board_size":417},"longer_query":{"rating":1365.6,"rank":186,"pct":53,"board_size":397},"non_english":{"rating":1337.8,"rank":201,"pct":52.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"minimax/minimax-m2.5","input_per_m":0.27,"output_per_m":0.95,"blended_per_m":0.44,"context_length":204800,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/minimax-m2-5"},{"slug":"gemma-3-27b-it","name":"Gemma 3 27B IT","source_name":"Gemma 3 27B IT","base":"Gemma 3 27B IT","variant":null,"org":"google","open_weights":true,"model_license":"Gemma","siscope":{"score":37.6,"rank":241,"coverage":0.75,"categories":{"coding":41.4,"reasoning":35,"math":31.7,"chat":51.9,"instructions":48.8}},"arena":{"text":{"rank":202,"date":"2026-10-28","rating":1357.7,"lo":1354.1,"hi":1361.4,"votes":46670,"pct":51.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":112,"date":"2026-10-19","rating":1164.5,"lo":1156.5,"hi":1172.6,"votes":16982,"pct":33.1,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1321.7,"rank":243,"pct":41.4,"board_size":414},"math":{"rating":1312.2,"rank":232,"pct":42.8,"board_size":405},"creative_writing":{"rating":1345.2,"rank":174,"pct":58.4,"board_size":417},"instruction_following":{"rating":1320.5,"rank":215,"pct":48.8,"board_size":419},"hard_prompts":{"rating":1340.1,"rank":220,"pct":47.6,"board_size":419},"multi_turn":{"rating":1344.6,"rank":209,"pct":50,"board_size":417},"longer_query":{"rating":1333,"rank":213,"pct":46.5,"board_size":397},"non_english":{"rating":1334.3,"rank":205,"pct":51.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.4773,"stderr":0.027,"tested_as":"gemma-3-27b-it","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FjdFH2zZdssYKDVJQPKXvNB.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":22.3,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.225,"stderr":0.0528,"tested_as":"gemma-3-27b-it","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FDhJ248BX3ZPBHXvkRG4Qsz.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":20.5,"tested_models":313}],"price":null,"url":"https://siscope.app/models/gemma-3-27b-it"},{"slug":"qwen3-coder-480b-a35b-instruct","name":"Qwen3 Coder 480B A35B Instruct","source_name":"Qwen3-Coder-480B-A35B-Instruct","base":"Qwen3 Coder 480B A35B Instruct","variant":null,"org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":44.6,"rank":214,"coverage":0.75,"categories":{"coding":36.4,"reasoning":55,"math":49.8,"chat":51.7,"instructions":56.2}},"arena":{"text":{"rank":203,"date":"2026-10-28","rating":1356.6,"lo":1351.6,"hi":1361.6,"votes":25190,"pct":51.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":134,"date":"2026-10-28","rating":1274.8,"lo":1267,"hi":1282.5,"votes":12675,"pct":11.9,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1412,"rank":163,"pct":60.8,"board_size":414},"math":{"rating":1365.2,"rank":204,"pct":49.8,"board_size":405},"creative_writing":{"rating":1332.8,"rank":190,"pct":54.6,"board_size":417},"instruction_following":{"rating":1355.4,"rank":184,"pct":56.2,"board_size":419},"hard_prompts":{"rating":1371.8,"rank":189,"pct":55,"board_size":419},"multi_turn":{"rating":1365.4,"rank":187,"pct":55.3,"board_size":417},"longer_query":{"rating":1378,"rank":177,"pct":55.6,"board_size":397},"non_english":{"rating":1345.5,"rank":196,"pct":53.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen3-coder-480b-a35b-instruct"},{"slug":"intellect-3","name":"INTELLECT-3","source_name":"INTELLECT-3","base":"INTELLECT-3","variant":null,"org":"other","open_weights":true,"model_license":"MIT","siscope":{"score":50,"rank":188,"coverage":0.75,"categories":{"coding":51.1,"reasoning":49.8,"math":53.2,"chat":51.4,"instructions":47.1}},"arena":{"text":{"rank":204,"date":"2026-10-28","rating":1355.6,"lo":1347.4,"hi":1363.8,"votes":5435,"pct":51.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1373.9,"rank":203,"pct":51.1,"board_size":414},"math":{"rating":1374.8,"rank":190,"pct":53.2,"board_size":405},"creative_writing":{"rating":1315.9,"rank":211,"pct":49.5,"board_size":417},"instruction_following":{"rating":1314.8,"rank":222,"pct":47.1,"board_size":419},"hard_prompts":{"rating":1351.5,"rank":211,"pct":49.8,"board_size":419},"multi_turn":{"rating":1350.4,"rank":204,"pct":51.2,"board_size":417},"longer_query":{"rating":1330.7,"rank":216,"pct":45.7,"board_size":397},"non_english":{"rating":1328.1,"rank":210,"pct":50,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/intellect-3"},{"slug":"mercury-2","name":"Mercury 2","source_name":"Mercury 2","base":"Mercury 2","variant":null,"org":"inception-ai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"coding":28.7,"reasoning":51.9,"chat":51.2,"instructions":50.2}},"arena":{"text":{"rank":205,"date":"2026-10-28","rating":1354.8,"lo":1344.4,"hi":1365.2,"votes":3191,"pct":51.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":149,"date":"2026-10-28","rating":1170.4,"lo":1145.8,"hi":1194.9,"votes":954,"pct":2,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1390.4,"rank":185,"pct":55.4,"board_size":414},"creative_writing":{"rating":1286.9,"rank":234,"pct":44,"board_size":417},"instruction_following":{"rating":1328.3,"rank":209,"pct":50.2,"board_size":419},"hard_prompts":{"rating":1361.8,"rank":202,"pct":51.9,"board_size":419},"multi_turn":{"rating":1356.7,"rank":198,"pct":52.6,"board_size":417},"longer_query":{"rating":1329.6,"rank":217,"pct":45.5,"board_size":397},"non_english":{"rating":1330.8,"rank":207,"pct":50.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"inception/mercury-2","input_per_m":0.25,"output_per_m":0.75,"blended_per_m":0.375,"context_length":128000,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/mercury-2"},{"slug":"gemini-2-0-flash-001","name":"Gemini 2.0 Flash (001)","source_name":"Gemini 2.0 Flash (001)","base":"Gemini 2.0 Flash","variant":"001","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":46.7,"rank":203,"coverage":0.75,"categories":{"coding":44.8,"reasoning":48.6,"math":46,"chat":51,"instructions":52.2}},"arena":{"text":{"rank":206,"date":"2026-10-28","rating":1354,"lo":1350.3,"hi":1357.8,"votes":43443,"pct":51,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":116,"date":"2026-10-19","rating":1157.9,"lo":1150.7,"hi":1165.1,"votes":10135,"pct":30.7,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1350.2,"rank":229,"pct":44.8,"board_size":414},"math":{"rating":1351.8,"rank":219,"pct":46,"board_size":405},"creative_writing":{"rating":1339.2,"rank":182,"pct":56.5,"board_size":417},"instruction_following":{"rating":1335.8,"rank":201,"pct":52.2,"board_size":419},"hard_prompts":{"rating":1346.2,"rank":216,"pct":48.6,"board_size":419},"multi_turn":{"rating":1349.6,"rank":206,"pct":50.7,"board_size":417},"longer_query":{"rating":1344.2,"rank":205,"pct":48.5,"board_size":397},"non_english":{"rating":1342,"rank":198,"pct":52.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemini-2-0-flash-001"},{"slug":"o4-mini-2025-04-16","name":"o4-mini (2025-04-16)","source_name":"o4-mini (2025-04-16)","base":"o4-mini","variant":"2025-04-16","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":50.3,"rank":184,"coverage":0.75,"categories":{"coding":49.6,"reasoning":49.5,"math":55.9,"chat":50.7,"instructions":48.6}},"arena":{"text":{"rank":207,"date":"2026-10-28","rating":1353.2,"lo":1349.3,"hi":1357.2,"votes":44843,"pct":50.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":98,"date":"2026-10-19","rating":1194,"lo":1187,"hi":1201.1,"votes":41316,"pct":41.6,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1368,"rank":209,"pct":49.6,"board_size":414},"math":{"rating":1389.2,"rank":179,"pct":55.9,"board_size":405},"creative_writing":{"rating":1293.7,"rank":226,"pct":45.9,"board_size":417},"instruction_following":{"rating":1320.3,"rank":216,"pct":48.6,"board_size":419},"hard_prompts":{"rating":1350.4,"rank":212,"pct":49.5,"board_size":419},"multi_turn":{"rating":1349.7,"rank":205,"pct":51,"board_size":417},"longer_query":{"rating":1314.4,"rank":237,"pct":40.4,"board_size":397},"non_english":{"rating":1336.4,"rank":203,"pct":51.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/o4-mini-2025-04-16"},{"slug":"o1-preview","name":"o1-preview","source_name":"o1-preview","base":"o1-preview","variant":null,"org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":42.5,"rank":222,"coverage":0.75,"categories":{"coding":48.2,"reasoning":37.7,"math":38.8,"chat":50.5,"instructions":52.9}},"arena":{"text":{"rank":208,"date":"2026-10-28","rating":1352.7,"lo":1347.7,"hi":1357.8,"votes":31122,"pct":50.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1366.3,"rank":214,"pct":48.2,"board_size":414},"math":{"rating":1373,"rank":193,"pct":52.5,"board_size":405},"creative_writing":{"rating":1317.9,"rank":206,"pct":50.7,"board_size":417},"instruction_following":{"rating":1341.5,"rank":198,"pct":52.9,"board_size":419},"hard_prompts":{"rating":1354,"rank":210,"pct":50,"board_size":419},"multi_turn":{"rating":1368.5,"rank":185,"pct":55.8,"board_size":417},"longer_query":{"rating":1343.7,"rank":207,"pct":48,"board_size":397},"non_english":{"rating":1314.9,"rank":224,"pct":46.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.5032,"stderr":0.0283,"tested_as":"o1-preview-2024-09-12","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F7CkADTsoNbDd88uqYbqfwj.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":25.3,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.3111,"stderr":0.0698,"tested_as":"o1-preview-2024-09-12","approx":false,"run_date":"2025-03-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FCprjaj9JQ9MY5NCXqeQR5H.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":25,"tested_models":313}],"price":null,"url":"https://siscope.app/models/o1-preview"},{"slug":"claude-sonnet-4-thinking-32k-20250514","name":"Claude Sonnet 4 (Thinking 32K, 2025-05-14)","source_name":"Claude Sonnet 4 (Thinking 32K, 20250514)","base":"Claude Sonnet 4","variant":"Thinking 32K, 2025-05-14","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":55,"rank":160,"coverage":0.75,"categories":{"coding":62,"reasoning":55,"math":52.6,"chat":50.2,"instructions":60.8}},"arena":{"text":{"rank":209,"date":"2026-10-28","rating":1350.9,"lo":1346.4,"hi":1355.4,"votes":34128,"pct":50.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":100,"date":"2026-10-19","rating":1191.4,"lo":1174.5,"hi":1208.3,"votes":1144,"pct":40.4,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1414.2,"rank":158,"pct":62,"board_size":414},"math":{"rating":1374.9,"rank":189,"pct":53.5,"board_size":405},"creative_writing":{"rating":1345.1,"rank":175,"pct":58.2,"board_size":417},"instruction_following":{"rating":1376,"rank":165,"pct":60.8,"board_size":419},"hard_prompts":{"rating":1372.4,"rank":187,"pct":55.5,"board_size":419},"multi_turn":{"rating":1376.3,"rank":181,"pct":56.7,"board_size":417},"longer_query":{"rating":1397.6,"rank":155,"pct":61.1,"board_size":397},"non_english":{"rating":1332.6,"rank":206,"pct":51,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.7828,"stderr":0.0294,"tested_as":"claude-sonnet-4-20250514_32K","approx":false,"run_date":"2025-05-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F8hGbWtbpUjAQpebkKQfSi7.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":54.5,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.7111,"stderr":0.0683,"tested_as":"claude-sonnet-4-20250514_32K","approx":false,"run_date":"2025-05-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FFZHzYjwAQexVykNQTnRtwT.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":51.6,"tested_models":313}],"price":null,"url":"https://siscope.app/models/claude-sonnet-4-thinking-32k-20250514"},{"slug":"glm-4-7-flash","name":"GLM-4.7-Flash","source_name":"GLM-4.7-Flash","base":"GLM-4.7-Flash","variant":null,"org":"zai","open_weights":true,"model_license":"MIT","siscope":{"score":46.5,"rank":206,"coverage":0.75,"categories":{"coding":53.8,"reasoning":42.1,"math":44.2,"chat":50,"instructions":50}},"arena":{"text":{"rank":210,"date":"2026-10-28","rating":1350.8,"lo":1345.1,"hi":1356.4,"votes":12008,"pct":50,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1382.6,"rank":192,"pct":53.8,"board_size":414},"math":{"rating":1355.2,"rank":214,"pct":47.3,"board_size":405},"creative_writing":{"rating":1295.8,"rank":224,"pct":46.4,"board_size":417},"instruction_following":{"rating":1326.6,"rank":210,"pct":50,"board_size":419},"hard_prompts":{"rating":1356.1,"rank":206,"pct":51,"board_size":419},"multi_turn":{"rating":1342.2,"rank":211,"pct":49.5,"board_size":417},"longer_query":{"rating":1344.8,"rank":204,"pct":48.7,"board_size":397},"non_english":{"rating":1330.3,"rank":208,"pct":50.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.6054,"stderr":0.0293,"tested_as":"glm-4.7-flash","approx":false,"run_date":"2026-08-30","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FGL7htq7XRnbzqpAVK5f862.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":33.1,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.5833,"stderr":0.0656,"tested_as":"glm-4.7-flash","approx":false,"run_date":"2026-08-30","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F9ekki5tJhyjmA7ZMLoUxzo.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":41,"tested_models":313}],"price":{"openrouter_id":"z-ai/glm-4.7-flash","input_per_m":0.0605,"output_per_m":0.4,"blended_per_m":0.1454,"context_length":200000,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/glm-4-7-flash"},{"slug":"step-3","name":"Step 3","source_name":"Step-3","base":"Step 3","variant":null,"org":"stepfun","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":49.5,"rank":190,"coverage":0.75,"categories":{"coding":48.9,"reasoning":50.2,"math":50.2,"chat":49.8,"instructions":50.7}},"arena":{"text":{"rank":211,"date":"2026-10-28","rating":1350.4,"lo":1342.9,"hi":1357.8,"votes":6291,"pct":49.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":106,"date":"2026-10-19","rating":1176.4,"lo":1164.7,"hi":1188.1,"votes":3193,"pct":36.7,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1366.9,"rank":212,"pct":48.9,"board_size":414},"math":{"rating":1366.6,"rank":202,"pct":50.2,"board_size":405},"creative_writing":{"rating":1321.4,"rank":200,"pct":52.2,"board_size":417},"instruction_following":{"rating":1332.2,"rank":207,"pct":50.7,"board_size":419},"hard_prompts":{"rating":1354.8,"rank":209,"pct":50.2,"board_size":419},"multi_turn":{"rating":1340.2,"rank":214,"pct":48.8,"board_size":417},"longer_query":{"rating":1325.5,"rank":223,"pct":43.9,"board_size":397},"non_english":{"rating":1327.3,"rank":211,"pct":49.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/step-3"},{"slug":"nvidia-nemotron-3-nano-30b-a3b-bf16","name":"Nemotron 3 Nano 30B A3B (BF16)","source_name":"NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)","base":"Nemotron 3 Nano 30B A3B","variant":"BF16","org":"nvidia","open_weights":true,"model_license":"NVIDIA Open Model","siscope":{"score":48.6,"rank":194,"coverage":0.75,"categories":{"coding":52.1,"reasoning":48.8,"math":51.2,"chat":49.5,"instructions":44}},"arena":{"text":{"rank":212,"date":"2026-10-28","rating":1347.8,"lo":1342.5,"hi":1353.2,"votes":15761,"pct":49.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1378.2,"rank":199,"pct":52.1,"board_size":414},"math":{"rating":1371.1,"rank":198,"pct":51.2,"board_size":405},"creative_writing":{"rating":1269.6,"rank":252,"pct":39.7,"board_size":417},"instruction_following":{"rating":1303.8,"rank":235,"pct":44,"board_size":419},"hard_prompts":{"rating":1348.2,"rank":215,"pct":48.8,"board_size":419},"multi_turn":{"rating":1319.4,"rank":234,"pct":44,"board_size":417},"longer_query":{"rating":1300,"rank":249,"pct":37.4,"board_size":397},"non_english":{"rating":1319.9,"rank":214,"pct":49,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/nvidia-nemotron-3-nano-30b-a3b-bf16"},{"slug":"minimax-m1","name":"MiniMax-M1","source_name":"MiniMax-M1","base":"MiniMax-M1","variant":null,"org":"minimax","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":47.1,"rank":199,"coverage":0.75,"categories":{"coding":46,"reasoning":47.4,"math":49,"chat":49.3,"instructions":46.4}},"arena":{"text":{"rank":213,"date":"2026-10-28","rating":1342.6,"lo":1338.4,"hi":1346.9,"votes":34293,"pct":49.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1358.4,"rank":224,"pct":46,"board_size":414},"math":{"rating":1360.7,"rank":207,"pct":49,"board_size":405},"creative_writing":{"rating":1297.4,"rank":222,"pct":46.9,"board_size":417},"instruction_following":{"rating":1311.7,"rank":225,"pct":46.4,"board_size":419},"hard_prompts":{"rating":1339.2,"rank":221,"pct":47.4,"board_size":419},"multi_turn":{"rating":1334.8,"rank":222,"pct":46.9,"board_size":417},"longer_query":{"rating":1326.1,"rank":220,"pct":44.7,"board_size":397},"non_english":{"rating":1319.3,"rank":215,"pct":48.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"minimax/minimax-m1","input_per_m":0.55,"output_per_m":2.2,"blended_per_m":0.9625,"context_length":1000000,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/minimax-m1"},{"slug":"gpt-4-1-mini-2025-04-14","name":"GPT-4.1 mini (2025-04-14)","source_name":"GPT-4.1 mini (2025-04-14)","base":"GPT-4.1 mini","variant":"2025-04-14","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":37.3,"rank":244,"coverage":0.75,"categories":{"coding":49.2,"reasoning":31,"math":28.3,"chat":49,"instructions":51}},"arena":{"text":{"rank":214,"date":"2026-10-28","rating":1340.5,"lo":1336.2,"hi":1344.8,"votes":38696,"pct":49,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":103,"date":"2026-10-19","rating":1181.4,"lo":1173.9,"hi":1188.9,"votes":40201,"pct":38.6,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1367,"rank":211,"pct":49.2,"board_size":414},"math":{"rating":1342.8,"rank":221,"pct":45.5,"board_size":405},"creative_writing":{"rating":1299.3,"rank":221,"pct":47.1,"board_size":417},"instruction_following":{"rating":1332.6,"rank":206,"pct":51,"board_size":419},"hard_prompts":{"rating":1348.9,"rank":214,"pct":49,"board_size":419},"multi_turn":{"rating":1354,"rank":202,"pct":51.7,"board_size":417},"longer_query":{"rating":1343.7,"rank":206,"pct":48,"board_size":397},"non_english":{"rating":1317.8,"rank":219,"pct":47.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.6585,"stderr":0.0271,"tested_as":"gpt-4.1-mini-2025-04-14","approx":false,"run_date":"2025-04-14","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FdXHddeGRX7JRVa5UNfad5C.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":37,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.127,"stderr":0.0105,"tested_as":"gpt-4.1-mini-2025-04-14","approx":false,"run_date":"2026-08-31","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FgYV4CJTjSd7VonfzMmnwcw.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":7.1,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.4472,"stderr":0.0615,"tested_as":"gpt-4.1-mini-2025-04-14","approx":false,"run_date":"2025-04-14","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FcXbbdQDW2jeYassmRuZYpU.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":31.1,"tested_models":313},{"benchmark":"frontiermath","score":0.0667,"stderr":0.0148,"tested_as":"gpt-4.1-mini-2025-04-14","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F6EQrp2MY4QMYLfTxpioYTe.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":8.3,"tested_models":122}],"price":{"openrouter_id":"openai/gpt-4.1-mini","input_per_m":0.4,"output_per_m":1.6,"blended_per_m":0.7,"context_length":1047576,"modalities_in":["image","text","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-4-1-mini-2025-04-14"},{"slug":"trinity-large-thinking","name":"Trinity Large Thinking","source_name":"Trinity Large Thinking","base":"Trinity Large Thinking","variant":null,"org":"other","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":37.4,"rank":243,"coverage":0.75,"categories":{"coding":25.8,"reasoning":48.1,"math":50,"chat":48.8,"instructions":49.8}},"arena":{"text":{"rank":215,"date":"2026-10-28","rating":1340.3,"lo":1335.6,"hi":1344.9,"votes":30290,"pct":48.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":143,"date":"2026-10-28","rating":1238,"lo":1218,"hi":1258.1,"votes":1352,"pct":6,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1357.1,"rank":226,"pct":45.5,"board_size":414},"math":{"rating":1365.5,"rank":203,"pct":50,"board_size":405},"creative_writing":{"rating":1308.3,"rank":216,"pct":48.3,"board_size":417},"instruction_following":{"rating":1326.2,"rank":211,"pct":49.8,"board_size":419},"hard_prompts":{"rating":1341.9,"rank":218,"pct":48.1,"board_size":419},"multi_turn":{"rating":1320.3,"rank":232,"pct":44.5,"board_size":417},"longer_query":{"rating":1318.2,"rank":233,"pct":41.4,"board_size":397},"non_english":{"rating":1325.3,"rank":212,"pct":49.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/trinity-large-thinking"},{"slug":"minimax-m2","name":"MiniMax-M2","source_name":"MiniMax-M2","base":"MiniMax-M2","variant":null,"org":"minimax","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":40.4,"rank":231,"coverage":0.75,"categories":{"coding":31.7,"reasoning":51.2,"math":46.3,"chat":48.3,"instructions":50.5}},"arena":{"text":{"rank":216,"date":"2026-10-28","rating":1340.1,"lo":1332.4,"hi":1347.8,"votes":6850,"pct":48.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":132,"date":"2026-10-28","rating":1297.1,"lo":1286.2,"hi":1308.1,"votes":6683,"pct":13.2,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1370.5,"rank":207,"pct":50.1,"board_size":414},"math":{"rating":1351.9,"rank":218,"pct":46.3,"board_size":405},"creative_writing":{"rating":1286.4,"rank":236,"pct":43.5,"board_size":417},"instruction_following":{"rating":1329,"rank":208,"pct":50.5,"board_size":419},"hard_prompts":{"rating":1356.7,"rank":205,"pct":51.2,"board_size":419},"multi_turn":{"rating":1361.2,"rank":194,"pct":53.6,"board_size":417},"longer_query":{"rating":1331.1,"rank":215,"pct":46,"board_size":397},"non_english":{"rating":1313,"rank":226,"pct":46.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"minimax/minimax-m2","input_per_m":0.255,"output_per_m":1.02,"blended_per_m":0.4463,"context_length":204800,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/minimax-m2"},{"slug":"qwen3-32b","name":"Qwen3-32B","source_name":"Qwen3-32B","base":"Qwen3-32B","variant":null,"org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":45.3,"rank":210,"coverage":0.75,"categories":{"coding":45.8,"reasoning":41.6,"math":53.7,"chat":48.3,"instructions":44.7}},"arena":{"text":{"rank":217,"date":"2026-10-28","rating":1340.1,"lo":1330.8,"hi":1349.4,"votes":3926,"pct":48.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1357.4,"rank":225,"pct":45.8,"board_size":414},"math":{"rating":1398.5,"rank":163,"pct":59.9,"board_size":405},"creative_writing":{"rating":1297,"rank":223,"pct":46.6,"board_size":417},"instruction_following":{"rating":1304.7,"rank":232,"pct":44.7,"board_size":419},"hard_prompts":{"rating":1334.4,"rank":225,"pct":46.4,"board_size":419},"multi_turn":{"rating":1330.8,"rank":226,"pct":45.9,"board_size":417},"longer_query":{"rating":1327.1,"rank":218,"pct":45.2,"board_size":397},"non_english":{"rating":1316.6,"rank":220,"pct":47.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.6572,"stderr":0.0279,"tested_as":"Qwen3-32B","approx":false,"run_date":"2026-08-28","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FFfoxqm7YsZr3FimCGsGAJv.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":36.7,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.6694,"stderr":0.0604,"tested_as":"Qwen3-32B","approx":false,"run_date":"2026-08-30","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FBAi4jidcT3F6reBkSXDJKv.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":47.4,"tested_models":313}],"price":{"openrouter_id":"qwen/qwen3-32b","input_per_m":0.08,"output_per_m":0.28,"blended_per_m":0.13,"context_length":131072,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/qwen3-32b"},{"slug":"claude-sonnet-4-20250514","name":"Claude Sonnet 4 (2025-05-14)","source_name":"Claude Sonnet 4 (20250514)","base":"Claude Sonnet 4","variant":"2025-05-14","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":43.8,"rank":218,"coverage":0.75,"categories":{"coding":52.5,"reasoning":44.1,"math":35.7,"chat":48.1,"instructions":55.3}},"arena":{"text":{"rank":218,"date":"2026-10-28","rating":1339.4,"lo":1334.9,"hi":1343.8,"votes":39168,"pct":48.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":108,"date":"2026-10-19","rating":1175.4,"lo":1161.4,"hi":1189.4,"votes":1806,"pct":35.5,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1379.2,"rank":197,"pct":52.5,"board_size":414},"math":{"rating":1358.7,"rank":210,"pct":48,"board_size":405},"creative_writing":{"rating":1342,"rank":180,"pct":57,"board_size":417},"instruction_following":{"rating":1352.2,"rank":188,"pct":55.3,"board_size":419},"hard_prompts":{"rating":1355,"rank":208,"pct":50.5,"board_size":419},"multi_turn":{"rating":1364.9,"rank":189,"pct":54.8,"board_size":417},"longer_query":{"rating":1379.3,"rank":175,"pct":56.1,"board_size":397},"non_english":{"rating":1330.1,"rank":209,"pct":50.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.6667,"stderr":0.0336,"tested_as":"claude-sonnet-4-20250514","approx":false,"run_date":"2025-05-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FZF4eejw7J2KrcoNWd6hUbU.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":37.7,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.2889,"stderr":0.0683,"tested_as":"claude-sonnet-4-20250514","approx":false,"run_date":"2025-05-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FUa8sCkk3R3mBLWeSnnPG7a.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":23.4,"tested_models":313}],"price":null,"url":"https://siscope.app/models/claude-sonnet-4-20250514"},{"slug":"trinity-large-preview","name":"Trinity Large Preview","source_name":"Trinity Large Preview","base":"Trinity Large Preview","variant":null,"org":"other","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":48.5,"rank":195,"coverage":0.75,"categories":{"coding":53.5,"reasoning":49.3,"math":44.8,"chat":47.8,"instructions":51.4}},"arena":{"text":{"rank":219,"date":"2026-10-28","rating":1338.6,"lo":1334.4,"hi":1342.8,"votes":31233,"pct":47.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1380.7,"rank":193,"pct":53.5,"board_size":414},"math":{"rating":1335.7,"rank":224,"pct":44.8,"board_size":405},"creative_writing":{"rating":1319,"rank":201,"pct":51.9,"board_size":417},"instruction_following":{"rating":1333.7,"rank":204,"pct":51.4,"board_size":419},"hard_prompts":{"rating":1349.3,"rank":213,"pct":49.3,"board_size":419},"multi_turn":{"rating":1341.7,"rank":212,"pct":49.3,"board_size":417},"longer_query":{"rating":1354.1,"rank":198,"pct":50.3,"board_size":397},"non_english":{"rating":1318.2,"rank":217,"pct":48.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/trinity-large-preview"},{"slug":"llama-3-3-nemotron-super-49b-v1-5","name":"Llama 3.3 Nemotron Super 49B v1.5","source_name":"Llama 3.3 Nemotron Super 49B v1.5","base":"Llama 3.3 Nemotron Super 49B v1.5","variant":null,"org":"nvidia","open_weights":true,"model_license":"Nvidia Open","siscope":{"score":46.9,"rank":202,"coverage":0.75,"categories":{"coding":45.3,"reasoning":47.1,"math":56.7,"chat":47.6,"instructions":42.8}},"arena":{"text":{"rank":220,"date":"2026-10-28","rating":1338.1,"lo":1328.1,"hi":1348.1,"votes":3327,"pct":47.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1355.2,"rank":227,"pct":45.3,"board_size":414},"math":{"rating":1392.3,"rank":176,"pct":56.7,"board_size":405},"creative_writing":{"rating":1306.5,"rank":218,"pct":47.8,"board_size":417},"instruction_following":{"rating":1298.7,"rank":240,"pct":42.8,"board_size":419},"hard_prompts":{"rating":1335.5,"rank":222,"pct":47.1,"board_size":419},"multi_turn":{"rating":1333.5,"rank":224,"pct":46.4,"board_size":417},"longer_query":{"rating":1314.9,"rank":236,"pct":40.7,"board_size":397},"non_english":{"rating":1315.6,"rank":221,"pct":47.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/llama-3-3-nemotron-super-49b-v1-5"},{"slug":"mistral-small-3-2-2506","name":"Mistral Small 3.2 (2506)","source_name":"Mistral Small 3.2 (2506)","base":"Mistral Small 3.2","variant":"2506","org":"mistral","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":46.4,"rank":207,"coverage":0.75,"categories":{"coding":47.5,"reasoning":46.9,"math":45.3,"chat":47.4,"instructions":45.7}},"arena":{"text":{"rank":221,"date":"2026-10-28","rating":1338,"lo":1332.9,"hi":1343.2,"votes":17462,"pct":47.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":121,"date":"2026-10-19","rating":1141.7,"lo":1132.6,"hi":1150.8,"votes":10843,"pct":27.1,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1362.1,"rank":218,"pct":47.5,"board_size":414},"math":{"rating":1341,"rank":222,"pct":45.3,"board_size":405},"creative_writing":{"rating":1304.3,"rank":220,"pct":47.4,"board_size":417},"instruction_following":{"rating":1309.2,"rank":228,"pct":45.7,"board_size":419},"hard_prompts":{"rating":1335.2,"rank":223,"pct":46.9,"board_size":419},"multi_turn":{"rating":1343.4,"rank":210,"pct":49.8,"board_size":417},"longer_query":{"rating":1325.7,"rank":221,"pct":44.2,"board_size":397},"non_english":{"rating":1315,"rank":223,"pct":46.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/mistral-small-3-2-2506"},{"slug":"o3-mini-high","name":"o3-mini (High)","source_name":"o3-mini (High)","base":"o3-mini","variant":"High","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":44.3,"rank":217,"coverage":0.75,"categories":{"coding":51.6,"reasoning":38.5,"math":44.7,"chat":47.1,"instructions":52.4}},"arena":{"text":{"rank":222,"date":"2026-10-28","rating":1336.6,"lo":1331.3,"hi":1341.8,"votes":18589,"pct":47.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1377.9,"rank":200,"pct":51.6,"board_size":414},"math":{"rating":1395.7,"rank":170,"pct":58.2,"board_size":405},"creative_writing":{"rating":1285.5,"rank":238,"pct":43,"board_size":417},"instruction_following":{"rating":1337.3,"rank":200,"pct":52.4,"board_size":419},"hard_prompts":{"rating":1365.4,"rank":194,"pct":53.8,"board_size":419},"multi_turn":{"rating":1320.4,"rank":231,"pct":44.7,"board_size":417},"longer_query":{"rating":1342.7,"rank":209,"pct":47.5,"board_size":397},"non_english":{"rating":1318.6,"rank":216,"pct":48.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.7702,"stderr":0.0259,"tested_as":"o3-mini-2025-01-31_high","approx":false,"run_date":"2025-02-13","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FMzsTvCEEfEpzn4WvxYdJkX.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":52.7,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.153,"stderr":0.0114,"tested_as":"o3-mini-2025-01-31_high","approx":false,"run_date":"2026-08-31","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FUCba4H3NNtUiWXMisWnh9g.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":9.1,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.7694,"stderr":0.0524,"tested_as":"o3-mini-2025-01-31_high","approx":false,"run_date":"2025-02-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FMjx6vYbgAb2DHXK8xcupX8.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":56.1,"tested_models":313},{"benchmark":"frontiermath","score":0.186,"stderr":0.0231,"tested_as":"o3-mini-2025-01-31_high","approx":false,"run_date":"2026-06-11","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FmRJaJyBY2M2GGdbdMmT6iq.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":19.8,"tested_models":122}],"price":null,"url":"https://siscope.app/models/o3-mini-high"},{"slug":"step-1o-turbo-202506","name":"Step-1o Turbo (202506)","source_name":"Step-1o Turbo (202506)","base":"Step-1o Turbo","variant":"202506","org":"stepfun","open_weights":false,"model_license":"Proprietary","siscope":{"score":44.7,"rank":213,"coverage":0.75,"categories":{"coding":43.6,"reasoning":46.7,"math":43.8,"chat":46.9,"instructions":45.9}},"arena":{"text":{"rank":223,"date":"2026-10-28","rating":1335.6,"lo":1328.8,"hi":1342.5,"votes":8906,"pct":46.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":102,"date":"2026-10-19","rating":1185.9,"lo":1171.7,"hi":1200.2,"votes":1895,"pct":39.2,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1338.8,"rank":234,"pct":43.6,"board_size":414},"math":{"rating":1317.8,"rank":228,"pct":43.8,"board_size":405},"creative_writing":{"rating":1307,"rank":217,"pct":48.1,"board_size":417},"instruction_following":{"rating":1309.6,"rank":227,"pct":45.9,"board_size":419},"hard_prompts":{"rating":1335,"rank":224,"pct":46.7,"board_size":419},"multi_turn":{"rating":1340.3,"rank":213,"pct":49,"board_size":417},"longer_query":{"rating":1348.3,"rank":203,"pct":49,"board_size":397},"non_english":{"rating":1312.5,"rank":229,"pct":45.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/step-1o-turbo-202506"},{"slug":"gemma-3-12b-it","name":"Gemma 3 12B IT","source_name":"Gemma 3 12B IT","base":"Gemma 3 12B IT","variant":null,"org":"google","open_weights":true,"model_license":"Gemma","siscope":{"score":32.2,"rank":263,"coverage":0.75,"categories":{"coding":33.2,"reasoning":27.9,"math":30.2,"chat":46.7,"instructions":43.3}},"arena":{"text":{"rank":224,"date":"2026-10-28","rating":1334.2,"lo":1324.8,"hi":1343.6,"votes":3829,"pct":46.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1280.9,"rank":277,"pct":33.2,"board_size":414},"math":{"rating":1307.4,"rank":236,"pct":41.8,"board_size":405},"creative_writing":{"rating":1331,"rank":193,"pct":53.8,"board_size":417},"instruction_following":{"rating":1299.1,"rank":238,"pct":43.3,"board_size":419},"hard_prompts":{"rating":1309.2,"rank":243,"pct":42.1,"board_size":419},"multi_turn":{"rating":1333.7,"rank":223,"pct":46.6,"board_size":417},"longer_query":{"rating":1316.7,"rank":234,"pct":41.2,"board_size":397},"non_english":{"rating":1317.8,"rank":218,"pct":47.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.3946,"stderr":0.0253,"tested_as":"gemma-3-12b-it","approx":false,"run_date":"2026-08-28","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FKfQKr2ibCFMx5xBELoiM3Y.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":13.6,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.1667,"stderr":0.0424,"tested_as":"gemma-3-12b-it","approx":false,"run_date":"2026-08-28","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FCAyLyhDHZiMQBZDB3qd8tG.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":18.6,"tested_models":313}],"price":null,"url":"https://siscope.app/models/gemma-3-12b-it"},{"slug":"ring-flash-2-0","name":"Ring Flash 2.0","source_name":"Ring-flash-2.0","base":"Ring Flash 2.0","variant":null,"org":"ant-group","open_weights":true,"model_license":"MIT","siscope":{"score":46.9,"rank":201,"coverage":0.75,"categories":{"coding":47.9,"reasoning":48.3,"math":45.8,"chat":46.4,"instructions":46.7}},"arena":{"text":{"rank":225,"date":"2026-10-28","rating":1333.7,"lo":1326.5,"hi":1340.9,"votes":6987,"pct":46.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1366.1,"rank":216,"pct":47.9,"board_size":414},"math":{"rating":1349.3,"rank":220,"pct":45.8,"board_size":405},"creative_writing":{"rating":1269.9,"rank":251,"pct":39.9,"board_size":417},"instruction_following":{"rating":1313.6,"rank":224,"pct":46.7,"board_size":419},"hard_prompts":{"rating":1344.3,"rank":217,"pct":48.3,"board_size":419},"multi_turn":{"rating":1287.9,"rank":259,"pct":38,"board_size":417},"longer_query":{"rating":1320.6,"rank":227,"pct":42.9,"board_size":397},"non_english":{"rating":1299.4,"rank":236,"pct":43.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/ring-flash-2-0"},{"slug":"glm-4-5v","name":"GLM-4.5V","source_name":"GLM-4.5V","base":"GLM-4.5V","variant":null,"org":"zai","open_weights":true,"model_license":"MIT","siscope":{"score":45.5,"rank":209,"coverage":0.75,"categories":{"coding":44.6,"reasoning":46.2,"math":46.8,"chat":46.2,"instructions":46.2}},"arena":{"text":{"rank":226,"date":"2026-10-28","rating":1332.6,"lo":1324.2,"hi":1341.1,"votes":4817,"pct":46.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":118,"date":"2026-10-19","rating":1154.4,"lo":1142.8,"hi":1166,"votes":3243,"pct":29.5,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1347.4,"rank":230,"pct":44.6,"board_size":414},"math":{"rating":1353.6,"rank":216,"pct":46.8,"board_size":405},"creative_writing":{"rating":1294.5,"rank":225,"pct":46.2,"board_size":417},"instruction_following":{"rating":1310.4,"rank":226,"pct":46.2,"board_size":419},"hard_prompts":{"rating":1334.3,"rank":226,"pct":46.2,"board_size":419},"multi_turn":{"rating":1332.8,"rank":225,"pct":46.2,"board_size":417},"longer_query":{"rating":1304.5,"rank":246,"pct":38.1,"board_size":397},"non_english":{"rating":1303.2,"rank":233,"pct":44.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"z-ai/glm-4.5v","input_per_m":0.6,"output_per_m":1.8,"blended_per_m":0.9,"context_length":65536,"modalities_in":["text","image"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/glm-4-5v"},{"slug":"deepseek-v3","name":"DeepSeek-V3","source_name":"DeepSeek-V3","base":"DeepSeek-V3","variant":null,"org":"deepseek","open_weights":true,"model_license":"DeepSeek","siscope":{"score":36.8,"rank":245,"coverage":0.75,"categories":{"coding":42.1,"reasoning":36.7,"math":30,"chat":45.9,"instructions":47.4}},"arena":{"text":{"rank":227,"date":"2026-10-28","rating":1332.5,"lo":1327.7,"hi":1337.2,"votes":21770,"pct":45.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1324.7,"rank":240,"pct":42.1,"board_size":414},"math":{"rating":1310.7,"rank":234,"pct":42.3,"board_size":405},"creative_writing":{"rating":1328.7,"rank":196,"pct":53.1,"board_size":417},"instruction_following":{"rating":1314.9,"rank":221,"pct":47.4,"board_size":419},"hard_prompts":{"rating":1311.9,"rank":241,"pct":42.6,"board_size":419},"multi_turn":{"rating":1349.1,"rank":207,"pct":50.5,"board_size":417},"longer_query":{"rating":1342.8,"rank":208,"pct":47.7,"board_size":397},"non_english":{"rating":1315.4,"rank":222,"pct":47.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.5653,"stderr":0.0276,"tested_as":"DeepSeek-V3","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FVwo3nMA8g2gGBCyTdKFMQJ.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":30.7,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.1583,"stderr":0.0434,"tested_as":"DeepSeek-V3","approx":false,"run_date":"2025-02-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F7saSEhfVvXuz4yTcGy5u2y.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":17.6,"tested_models":313}],"price":{"openrouter_id":"deepseek/deepseek-chat","input_per_m":0.2574,"output_per_m":1.0287,"blended_per_m":0.4502,"context_length":163840,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/deepseek-v3"},{"slug":"command-a-03-2025","name":"Command A (03-2025)","source_name":"Command A (03-2025)","base":"Command A","variant":"03-2025","org":"cohere","open_weights":true,"model_license":"CC-BY-NC-4.0","siscope":{"score":42.6,"rank":220,"coverage":0.75,"categories":{"coding":42.6,"reasoning":44.7,"math":40.3,"chat":45.7,"instructions":45.5}},"arena":{"text":{"rank":228,"date":"2026-10-28","rating":1330.9,"lo":1327.5,"hi":1334.3,"votes":55763,"pct":45.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1329.9,"rank":238,"pct":42.6,"board_size":414},"math":{"rating":1300.3,"rank":242,"pct":40.3,"board_size":405},"creative_writing":{"rating":1318.8,"rank":202,"pct":51.7,"board_size":417},"instruction_following":{"rating":1308.6,"rank":229,"pct":45.5,"board_size":419},"hard_prompts":{"rating":1326.2,"rank":232,"pct":44.7,"board_size":419},"multi_turn":{"rating":1338.3,"rank":218,"pct":47.8,"board_size":417},"longer_query":{"rating":1334,"rank":212,"pct":46.7,"board_size":397},"non_english":{"rating":1312.9,"rank":227,"pct":45.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"cohere/command-a","input_per_m":2.5,"output_per_m":10,"blended_per_m":4.375,"context_length":256000,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/command-a-03-2025"},{"slug":"nvidia-nemotron-3-5-lightning-30b-a3b-nvfp4","name":"Nemotron 3.5 Lightning 30B A3B (NVFP4)","source_name":"NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4)","base":"Nemotron 3.5 Lightning 30B A3B","variant":"NVFP4","org":"nvidia","open_weights":true,"model_license":"OpenMDW-1.1","siscope":{"score":48.9,"rank":193,"coverage":0.75,"categories":{"coding":53.3,"reasoning":47.8,"math":51.5,"chat":45.2,"instructions":49}},"arena":{"text":{"rank":229,"date":"2026-10-28","rating":1330.8,"lo":1325.5,"hi":1336.1,"votes":24230,"pct":45.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1380.5,"rank":194,"pct":53.3,"board_size":414},"math":{"rating":1372.3,"rank":196,"pct":51.5,"board_size":405},"creative_writing":{"rating":1262.5,"rank":261,"pct":37.5,"board_size":417},"instruction_following":{"rating":1321.4,"rank":214,"pct":49,"board_size":419},"hard_prompts":{"rating":1341.3,"rank":219,"pct":47.8,"board_size":419},"multi_turn":{"rating":1326.2,"rank":227,"pct":45.7,"board_size":417},"longer_query":{"rating":1319.9,"rank":231,"pct":41.9,"board_size":397},"non_english":{"rating":1298.1,"rank":237,"pct":43.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/nvidia-nemotron-3-5-lightning-30b-a3b-nvfp4"},{"slug":"glm-4-plus-0111","name":"GLM-4-Plus (0111)","source_name":"GLM-4-Plus (0111)","base":"GLM-4-Plus","variant":"0111","org":"zai","open_weights":false,"model_license":"Proprietary","siscope":{"score":37.5,"rank":242,"coverage":0.75,"categories":{"coding":34.4,"reasoning":39.7,"math":38.6,"chat":45.2,"instructions":41.6}},"arena":{"text":{"rank":230,"date":"2026-10-28","rating":1330.8,"lo":1322.4,"hi":1339.2,"votes":5760,"pct":45.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1286.4,"rank":272,"pct":34.4,"board_size":414},"math":{"rating":1287.4,"rank":249,"pct":38.6,"board_size":405},"creative_writing":{"rating":1310.6,"rank":215,"pct":48.6,"board_size":417},"instruction_following":{"rating":1292.4,"rank":245,"pct":41.6,"board_size":419},"hard_prompts":{"rating":1293.4,"rank":253,"pct":39.7,"board_size":419},"multi_turn":{"rating":1323.7,"rank":229,"pct":45.2,"board_size":417},"longer_query":{"rating":1315.5,"rank":235,"pct":40.9,"board_size":397},"non_english":{"rating":1313.7,"rank":225,"pct":46.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/glm-4-plus-0111"},{"slug":"gemini-2-0-flash-lite-preview-02-05","name":"Gemini 2.0 Flash-Lite Preview (02-05)","source_name":"Gemini 2.0 Flash-Lite Preview (02-05)","base":"Gemini 2.0 Flash-Lite Preview","variant":"02-05","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":42.5,"rank":221,"coverage":0.75,"categories":{"coding":41.4,"reasoning":44,"math":42.1,"chat":45,"instructions":44.5}},"arena":{"text":{"rank":231,"date":"2026-10-28","rating":1329.5,"lo":1325.2,"hi":1333.8,"votes":24955,"pct":45,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":131,"date":"2026-10-19","rating":1100.4,"lo":1089.9,"hi":1110.9,"votes":3991,"pct":21.7,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1321.7,"rank":242,"pct":41.4,"board_size":414},"math":{"rating":1309.2,"rank":235,"pct":42.1,"board_size":405},"creative_writing":{"rating":1318.6,"rank":203,"pct":51.4,"board_size":417},"instruction_following":{"rating":1304.5,"rank":233,"pct":44.5,"board_size":419},"hard_prompts":{"rating":1324.2,"rank":235,"pct":44,"board_size":419},"multi_turn":{"rating":1307.3,"rank":243,"pct":41.8,"board_size":417},"longer_query":{"rating":1320.2,"rank":228,"pct":42.7,"board_size":397},"non_english":{"rating":1322.5,"rank":213,"pct":49.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemini-2-0-flash-lite-preview-02-05"},{"slug":"qwq-32b","name":"QwQ-32B","source_name":"QwQ-32B","base":"QwQ-32B","variant":null,"org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":42.1,"rank":227,"coverage":0.75,"categories":{"coding":42.9,"reasoning":40.2,"math":44.9,"chat":44.7,"instructions":42.3}},"arena":{"text":{"rank":232,"date":"2026-10-28","rating":1329,"lo":1324.6,"hi":1333.5,"votes":25177,"pct":44.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1333,"rank":237,"pct":42.9,"board_size":414},"math":{"rating":1358.9,"rank":209,"pct":48.5,"board_size":405},"creative_writing":{"rating":1287.5,"rank":232,"pct":44.5,"board_size":417},"instruction_following":{"rating":1296.8,"rank":242,"pct":42.3,"board_size":419},"hard_prompts":{"rating":1325.4,"rank":233,"pct":44.5,"board_size":419},"multi_turn":{"rating":1313.5,"rank":238,"pct":43,"board_size":417},"longer_query":{"rating":1307.9,"rank":243,"pct":38.9,"board_size":397},"non_english":{"rating":1305.3,"rank":232,"pct":44.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.6534,"stderr":0.0281,"tested_as":"QwQ-32B","approx":false,"run_date":"2026-08-28","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FPUXMxQiRY6XaG6NjwsEDLy.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":35.8,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.5917,"stderr":0.0635,"tested_as":"QwQ-32B","approx":false,"run_date":"2026-08-28","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2xMn6dbY9mw4pmkh8Tz9Gn.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":41.3,"tested_models":313}],"price":null,"url":"https://siscope.app/models/qwq-32b"},{"slug":"qwen-plus-0125","name":"Qwen-Plus (0125)","source_name":"Qwen-Plus (0125)","base":"Qwen-Plus","variant":"0125","org":"alibaba","open_weights":false,"model_license":"Proprietary","siscope":{"score":36.6,"rank":246,"coverage":0.75,"categories":{"coding":42.4,"reasoning":33.2,"math":31.8,"chat":44.5,"instructions":43.8}},"arena":{"text":{"rank":233,"date":"2026-10-28","rating":1326.4,"lo":1318.1,"hi":1334.7,"votes":5819,"pct":44.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1327.8,"rank":239,"pct":42.4,"board_size":414},"math":{"rating":1325.9,"rank":225,"pct":44.6,"board_size":405},"creative_writing":{"rating":1292.2,"rank":228,"pct":45.4,"board_size":417},"instruction_following":{"rating":1302.8,"rank":236,"pct":43.8,"board_size":419},"hard_prompts":{"rating":1316.4,"rank":237,"pct":43.5,"board_size":419},"multi_turn":{"rating":1336.1,"rank":221,"pct":47.1,"board_size":417},"longer_query":{"rating":1324.2,"rank":224,"pct":43.7,"board_size":397},"non_english":{"rating":1309.5,"rank":231,"pct":45,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.4811,"stderr":0.0271,"tested_as":"qwen-plus-2025-01-25","approx":false,"run_date":"2025-04-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FQtraMoKiQRRpZc9txpFAYF.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":22.9,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.1778,"stderr":0.0436,"tested_as":"qwen-plus-2025-01-25","approx":false,"run_date":"2025-04-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FAULNJG2C75JBP6uaiAgj3P.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":18.9,"tested_models":313}],"price":{"openrouter_id":"qwen/qwen-plus","input_per_m":0.26,"output_per_m":0.78,"blended_per_m":0.39,"context_length":1000000,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/qwen-plus-0125"},{"slug":"step-2-16k-exp-202412","name":"Step-2 16K Exp (202412)","source_name":"Step-2 16K Exp (202412)","base":"Step-2 16K Exp","variant":"202412","org":"stepfun","open_weights":false,"model_license":"Proprietary","siscope":{"score":40.9,"rank":229,"coverage":0.75,"categories":{"coding":40.4,"reasoning":40.4,"math":40.8,"chat":44.3,"instructions":41.4}},"arena":{"text":{"rank":234,"date":"2026-10-28","rating":1320.9,"lo":1312.3,"hi":1329.4,"votes":4833,"pct":44.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1315.9,"rank":247,"pct":40.4,"board_size":414},"math":{"rating":1304.5,"rank":240,"pct":40.8,"board_size":405},"creative_writing":{"rating":1327.3,"rank":197,"pct":52.9,"board_size":417},"instruction_following":{"rating":1286.6,"rank":246,"pct":41.4,"board_size":419},"hard_prompts":{"rating":1299,"rank":250,"pct":40.4,"board_size":419},"multi_turn":{"rating":1292.3,"rank":253,"pct":39.2,"board_size":417},"longer_query":{"rating":1306.2,"rank":245,"pct":38.4,"board_size":397},"non_english":{"rating":1289.9,"rank":241,"pct":42.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/step-2-16k-exp-202412"},{"slug":"gpt-5-nano-high","name":"GPT-5 nano (High)","source_name":"GPT-5 nano (High)","base":"GPT-5 nano","variant":"High","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":37.7,"rank":240,"coverage":0.75,"categories":{"coding":45,"reasoning":29.6,"math":42.8,"chat":44,"instructions":45}},"arena":{"text":{"rank":235,"date":"2026-10-28","rating":1319.9,"lo":1313,"hi":1326.7,"votes":8134,"pct":44,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":115,"date":"2026-10-19","rating":1159.5,"lo":1148.4,"hi":1170.5,"votes":3928,"pct":31.3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1350.8,"rank":228,"pct":45,"board_size":414},"math":{"rating":1318.3,"rank":227,"pct":44.1,"board_size":405},"creative_writing":{"rating":1249.3,"rank":269,"pct":35.6,"board_size":417},"instruction_following":{"rating":1306,"rank":231,"pct":45,"board_size":419},"hard_prompts":{"rating":1328.2,"rank":230,"pct":45.2,"board_size":419},"multi_turn":{"rating":1311.2,"rank":240,"pct":42.5,"board_size":417},"longer_query":{"rating":1311.8,"rank":239,"pct":39.9,"board_size":397},"non_english":{"rating":1312.6,"rank":228,"pct":45.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.6944,"stderr":0.0276,"tested_as":"gpt-5-nano-2025-08-07_high","approx":false,"run_date":"2025-10-30","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2pSDjMSGDh4HsAxkqUuNQP.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":40.7,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.117,"stderr":0.0102,"tested_as":"gpt-5-nano-2025-08-07_high","approx":false,"run_date":"2026-08-10","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":3,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.8111,"stderr":0.0463,"tested_as":"gpt-5-nano-2025-08-07_high","approx":false,"run_date":"2025-10-31","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FY9YnaJQWpPFAPhe6jtKMhH.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":60.3,"tested_models":313},{"benchmark":"frontiermath","score":0.2,"stderr":0.0237,"tested_as":"gpt-5-nano-2025-08-07_high","approx":false,"run_date":"2026-06-12","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FJH3PjDrbrQndEcc8fh5Qre.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":24,"tested_models":122}],"price":{"openrouter_id":"openai/gpt-5-nano","input_per_m":0.05,"output_per_m":0.4,"blended_per_m":0.1375,"context_length":400000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-nano-high"},{"slug":"hunyuan-turbos-20250226","name":"Hunyuan TurboS (2025-02-26)","source_name":"Hunyuan TurboS (20250226)","base":"Hunyuan TurboS","variant":"2025-02-26","org":"tencent","open_weights":false,"model_license":"Proprietary","siscope":{"score":42.3,"rank":225,"coverage":0.75,"categories":{"coding":44.1,"reasoning":44.3,"math":39.1,"chat":43.8,"instructions":47.8}},"arena":{"text":{"rank":236,"date":"2026-10-28","rating":1319.7,"lo":1308,"hi":1331.4,"votes":2220,"pct":43.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1342.3,"rank":232,"pct":44.1,"board_size":414},"math":{"rating":1294,"rank":247,"pct":39.1,"board_size":405},"creative_writing":{"rating":1270.1,"rank":250,"pct":40.1,"board_size":417},"instruction_following":{"rating":1315.5,"rank":219,"pct":47.8,"board_size":419},"hard_prompts":{"rating":1324.7,"rank":234,"pct":44.3,"board_size":419},"multi_turn":{"rating":1319.5,"rank":233,"pct":44.2,"board_size":417},"longer_query":{"rating":1320,"rank":230,"pct":42.2,"board_size":397},"non_english":{"rating":1297.8,"rank":238,"pct":43.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/hunyuan-turbos-20250226"},{"slug":"llama-3-1-nemotron-ultra-253b-v1","name":"Llama 3.1 Nemotron Ultra 253B v1","source_name":"Llama 3.1 Nemotron Ultra 253B v1","base":"Llama 3.1 Nemotron Ultra 253B v1","variant":null,"org":"nvidia","open_weights":true,"model_license":"Nvidia Open Model","siscope":{"score":42.2,"rank":226,"coverage":0.75,"categories":{"coding":39.2,"reasoning":43.3,"math":48.8,"chat":43.5,"instructions":45.2}},"arena":{"text":{"rank":237,"date":"2026-10-28","rating":1319.5,"lo":1308,"hi":1331,"votes":2549,"pct":43.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1311.5,"rank":252,"pct":39.2,"board_size":414},"math":{"rating":1359.6,"rank":208,"pct":48.8,"board_size":405},"creative_writing":{"rating":1313.9,"rank":214,"pct":48.8,"board_size":417},"instruction_following":{"rating":1307.6,"rank":230,"pct":45.2,"board_size":419},"hard_prompts":{"rating":1315.9,"rank":238,"pct":43.3,"board_size":419},"multi_turn":{"rating":1317.2,"rank":235,"pct":43.8,"board_size":417},"longer_query":{"rating":1298.6,"rank":251,"pct":36.9,"board_size":397},"non_english":{"rating":1282.1,"rank":248,"pct":40.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/llama-3-1-nemotron-ultra-253b-v1"},{"slug":"o3-mini","name":"o3-mini","source_name":"o3-mini","base":"o3-mini","variant":null,"org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":46.5,"rank":205,"coverage":0.75,"categories":{"coding":47.7,"reasoning":45.5,"math":53,"chat":43.3,"instructions":47.6}},"arena":{"text":{"rank":238,"date":"2026-10-28","rating":1319.4,"lo":1315.9,"hi":1323,"votes":56735,"pct":43.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1362.7,"rank":217,"pct":47.7,"board_size":414},"math":{"rating":1374.1,"rank":191,"pct":53,"board_size":405},"creative_writing":{"rating":1272.7,"rank":246,"pct":41.1,"board_size":417},"instruction_following":{"rating":1315,"rank":220,"pct":47.6,"board_size":419},"hard_prompts":{"rating":1332.5,"rank":229,"pct":45.5,"board_size":419},"multi_turn":{"rating":1312.9,"rank":239,"pct":42.8,"board_size":417},"longer_query":{"rating":1327,"rank":219,"pct":44.9,"board_size":397},"non_english":{"rating":1299.6,"rank":235,"pct":44,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/o3-mini"},{"slug":"gemini-1-5-pro-002","name":"Gemini 1.5 Pro (002)","source_name":"Gemini 1.5 Pro (002)","base":"Gemini 1.5 Pro","variant":"002","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":39.1,"rank":236,"coverage":0.75,"categories":{"coding":36.3,"reasoning":40.2,"math":43.1,"chat":43.1,"instructions":42.1}},"arena":{"text":{"rank":239,"date":"2026-10-28","rating":1319.1,"lo":1315.7,"hi":1322.5,"votes":55606,"pct":43.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":114,"date":"2026-10-19","rating":1161.4,"lo":1152.3,"hi":1170.5,"votes":8902,"pct":31.9,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1294.1,"rank":264,"pct":36.3,"board_size":414},"math":{"rating":1314.7,"rank":231,"pct":43.1,"board_size":405},"creative_writing":{"rating":1332.4,"rank":191,"pct":54.3,"board_size":417},"instruction_following":{"rating":1296.7,"rank":243,"pct":42.1,"board_size":419},"hard_prompts":{"rating":1296.2,"rank":251,"pct":40.2,"board_size":419},"multi_turn":{"rating":1296.1,"rank":252,"pct":39.7,"board_size":417},"longer_query":{"rating":1307.6,"rank":244,"pct":38.6,"board_size":397},"non_english":{"rating":1311.9,"rank":230,"pct":45.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemini-1-5-pro-002"},{"slug":"granite-4-2-8b","name":"Granite 4.2 8B","source_name":"Granite 4.2 8B","base":"Granite 4.2 8B","variant":null,"org":"ibm","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"coding":51.6,"reasoning":45,"chat":42.8,"instructions":43.5}},"arena":{"text":{"rank":240,"date":"2026-10-28","rating":1319,"lo":1307.9,"hi":1330.1,"votes":3251,"pct":42.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1377.9,"rank":201,"pct":51.6,"board_size":414},"creative_writing":{"rating":1235.2,"rank":287,"pct":31.2,"board_size":417},"instruction_following":{"rating":1300.3,"rank":237,"pct":43.5,"board_size":419},"hard_prompts":{"rating":1326.9,"rank":231,"pct":45,"board_size":419},"multi_turn":{"rating":1299.2,"rank":249,"pct":40.4,"board_size":417},"longer_query":{"rating":1323.8,"rank":226,"pct":43.2,"board_size":397},"non_english":{"rating":1299.6,"rank":234,"pct":44,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"ibm-granite/granite-4.2-8b","input_per_m":0.06,"output_per_m":0.25,"blended_per_m":0.1075,"context_length":131072,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/granite-4-2-8b"},{"slug":"o1-mini","name":"o1-mini","source_name":"o1-mini","base":"o1-mini","variant":null,"org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":45.2,"rank":211,"coverage":0.75,"categories":{"coding":47.2,"reasoning":45.9,"math":47.5,"chat":42.6,"instructions":44.3}},"arena":{"text":{"rank":241,"date":"2026-10-28","rating":1317.1,"lo":1313.4,"hi":1320.7,"votes":51981,"pct":42.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1362,"rank":219,"pct":47.2,"board_size":414},"math":{"rating":1358.2,"rank":213,"pct":47.5,"board_size":405},"creative_writing":{"rating":1244,"rank":276,"pct":33.9,"board_size":417},"instruction_following":{"rating":1303.9,"rank":234,"pct":44.3,"board_size":419},"hard_prompts":{"rating":1333,"rank":227,"pct":45.9,"board_size":419},"multi_turn":{"rating":1314,"rank":237,"pct":43.3,"board_size":417},"longer_query":{"rating":1320.1,"rank":229,"pct":42.4,"board_size":397},"non_english":{"rating":1288.4,"rank":242,"pct":42.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/o1-mini"},{"slug":"qwen3-30b-a3b","name":"Qwen3 30B A3B","source_name":"Qwen3-30B-A3B","base":"Qwen3 30B A3B","variant":null,"org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":41.1,"rank":228,"coverage":0.75,"categories":{"coding":43.1,"reasoning":38.3,"math":45.5,"chat":42.3,"instructions":41.1}},"arena":{"text":{"rank":242,"date":"2026-10-28","rating":1317,"lo":1312.2,"hi":1321.7,"votes":26156,"pct":42.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1336.5,"rank":236,"pct":43.1,"board_size":414},"math":{"rating":1354.6,"rank":215,"pct":47,"board_size":405},"creative_writing":{"rating":1271.3,"rank":248,"pct":40.6,"board_size":417},"instruction_following":{"rating":1283.4,"rank":247,"pct":41.1,"board_size":419},"hard_prompts":{"rating":1314,"rank":240,"pct":42.8,"board_size":419},"multi_turn":{"rating":1307,"rank":244,"pct":41.6,"board_size":417},"longer_query":{"rating":1311.7,"rank":240,"pct":39.6,"board_size":397},"non_english":{"rating":1295.1,"rank":240,"pct":42.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.6168,"stderr":0.0297,"tested_as":"Qwen3-30B-A3B","approx":false,"run_date":"2026-08-30","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FBnX67AoZzgVbHgaM8F8Brz.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":33.7,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.6278,"stderr":0.0621,"tested_as":"Qwen3-30B-A3B","approx":false,"run_date":"2026-08-28","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FXfjRkSyP4ub4gDsWcgS7KY.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":43.9,"tested_models":313}],"price":{"openrouter_id":"qwen/qwen3-30b-a3b","input_per_m":0.12,"output_per_m":0.5,"blended_per_m":0.215,"context_length":40960,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/qwen3-30b-a3b"},{"slug":"claude-3-7-sonnet-thinking-32k-20250219","name":"Claude 3.7 Sonnet (Thinking 32K, 2025-02-19)","source_name":"Claude 3.7 Sonnet (Thinking 32K, 20250219)","base":"Claude 3.7 Sonnet","variant":"Thinking 32K, 2025-02-19","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":44.5,"rank":215,"coverage":0.75,"categories":{"coding":46.5,"reasoning":48.6,"math":40.5,"chat":42.1,"instructions":55}},"arena":{"text":{"rank":243,"date":"2026-10-28","rating":1314.3,"lo":1310,"hi":1318.5,"votes":38156,"pct":42.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":110,"date":"2026-10-19","rating":1168.9,"lo":1153.4,"hi":1184.4,"votes":1436,"pct":34.3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1360.3,"rank":222,"pct":46.5,"board_size":414},"math":{"rating":1336.4,"rank":223,"pct":45,"board_size":405},"creative_writing":{"rating":1331.5,"rank":192,"pct":54.1,"board_size":417},"instruction_following":{"rating":1351.6,"rank":189,"pct":55,"board_size":419},"hard_prompts":{"rating":1332.9,"rank":228,"pct":45.7,"board_size":419},"multi_turn":{"rating":1337.5,"rank":220,"pct":47.4,"board_size":417},"longer_query":{"rating":1372.5,"rank":181,"pct":54.5,"board_size":397},"non_english":{"rating":1295.9,"rank":239,"pct":43.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.7677,"stderr":0.0301,"tested_as":"claude-3-7-sonnet-20250219_32K","approx":false,"run_date":"2025-03-10","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Fiv9yfwZ9vTznxQfvJF6J7p.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":51.5,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.5333,"stderr":0.0752,"tested_as":"claude-3-7-sonnet-20250219_32K","approx":false,"run_date":"2025-03-12","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FdSuGgEbnQErengjEboPn62.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":35.9,"tested_models":313}],"price":null,"url":"https://siscope.app/models/claude-3-7-sonnet-thinking-32k-20250219"},{"slug":"hunyuan-turbo-0110","name":"Hunyuan Turbo (0110)","source_name":"Hunyuan Turbo (0110)","base":"Hunyuan Turbo","variant":"0110","org":"tencent","open_weights":false,"model_license":"Proprietary","siscope":{"score":39.1,"rank":237,"coverage":0.75,"categories":{"coding":41.2,"reasoning":41.9,"math":35.4,"chat":41.9,"instructions":40.7}},"arena":{"text":{"rank":244,"date":"2026-10-28","rating":1311.4,"lo":1300,"hi":1322.8,"votes":2290,"pct":41.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1319.1,"rank":244,"pct":41.2,"board_size":414},"math":{"rating":1272.9,"rank":262,"pct":35.4,"board_size":405},"creative_writing":{"rating":1268.7,"rank":253,"pct":39.4,"board_size":417},"instruction_following":{"rating":1278.3,"rank":249,"pct":40.7,"board_size":419},"hard_prompts":{"rating":1308,"rank":244,"pct":41.9,"board_size":419},"multi_turn":{"rating":1303.4,"rank":245,"pct":41.3,"board_size":417},"longer_query":{"rating":1308.6,"rank":242,"pct":39.1,"board_size":397},"non_english":{"rating":1284.9,"rank":245,"pct":41.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/hunyuan-turbo-0110"},{"slug":"olmo-3-1-32b-instruct","name":"Olmo 3.1 32B Instruct","source_name":"Olmo 3.1 32B Instruct","base":"Olmo 3.1 32B Instruct","variant":null,"org":"allenai","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":42.5,"rank":223,"coverage":0.75,"categories":{"coding":44.3,"reasoning":43.8,"math":40.8,"chat":41.6,"instructions":43.1}},"arena":{"text":{"rank":245,"date":"2026-10-28","rating":1311.2,"lo":1305.1,"hi":1317.3,"votes":11805,"pct":41.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1346.9,"rank":231,"pct":44.3,"board_size":414},"math":{"rating":1304.5,"rank":239,"pct":40.8,"board_size":405},"creative_writing":{"rating":1264.6,"rank":258,"pct":38.2,"board_size":417},"instruction_following":{"rating":1299,"rank":239,"pct":43.1,"board_size":419},"hard_prompts":{"rating":1322,"rank":236,"pct":43.8,"board_size":419},"multi_turn":{"rating":1309.8,"rank":242,"pct":42.1,"board_size":417},"longer_query":{"rating":1312.7,"rank":238,"pct":40.2,"board_size":397},"non_english":{"rating":1275.1,"rank":252,"pct":40,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/olmo-3-1-32b-instruct"},{"slug":"llama-3-3-nemotron-super-49b-v1","name":"Llama 3.3 Nemotron Super 49B v1","source_name":"Llama 3.3 Nemotron Super 49B v1","base":"Llama 3.3 Nemotron Super 49B v1","variant":null,"org":"nvidia","open_weights":true,"model_license":"Nvidia","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"coding":36.6,"reasoning":42.3,"chat":41.4,"instructions":41.9}},"arena":{"text":{"rank":246,"date":"2026-10-28","rating":1308.4,"lo":1296.3,"hi":1320.4,"votes":2218,"pct":41.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1295.4,"rank":263,"pct":36.6,"board_size":414},"creative_writing":{"rating":1287.7,"rank":231,"pct":44.7,"board_size":417},"instruction_following":{"rating":1293.3,"rank":244,"pct":41.9,"board_size":419},"hard_prompts":{"rating":1311.1,"rank":242,"pct":42.3,"board_size":419},"multi_turn":{"rating":1315.1,"rank":236,"pct":43.5,"board_size":417},"longer_query":{"rating":1299.2,"rank":250,"pct":37.1,"board_size":397},"non_english":{"rating":1253.3,"rank":277,"pct":34,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/llama-3-3-nemotron-super-49b-v1"},{"slug":"gemma-3n-e4b-it","name":"Gemma 3n E4B IT","source_name":"Gemma 3n E4B IT","base":"Gemma 3n E4B IT","variant":null,"org":"google","open_weights":true,"model_license":"Gemma","siscope":{"score":33.4,"rank":259,"coverage":0.75,"categories":{"coding":31,"reasoning":38,"math":30.4,"chat":41.1,"instructions":35.4}},"arena":{"text":{"rank":247,"date":"2026-10-28","rating":1305.6,"lo":1300.4,"hi":1310.7,"votes":22136,"pct":41.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1268.1,"rank":285,"pct":31,"board_size":414},"math":{"rating":1250.8,"rank":282,"pct":30.4,"board_size":405},"creative_writing":{"rating":1286.8,"rank":235,"pct":43.8,"board_size":417},"instruction_following":{"rating":1255.1,"rank":271,"pct":35.4,"board_size":419},"hard_prompts":{"rating":1283.9,"rank":260,"pct":38,"board_size":419},"multi_turn":{"rating":1276.3,"rank":270,"pct":35.3,"board_size":417},"longer_query":{"rating":1275.8,"rank":271,"pct":31.8,"board_size":397},"non_english":{"rating":1285,"rank":244,"pct":41.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemma-3n-e4b-it"},{"slug":"grok-2-2024-08-13","name":"Grok 2 (2024-08-13)","source_name":"Grok 2 (2024-08-13)","base":"Grok 2","variant":"2024-08-13","org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":36.2,"rank":248,"coverage":0.75,"categories":{"coding":34.6,"reasoning":36.1,"math":37.6,"chat":40.9,"instructions":38.5}},"arena":{"text":{"rank":248,"date":"2026-10-28","rating":1304.6,"lo":1300.9,"hi":1308.2,"votes":63498,"pct":40.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1287.2,"rank":271,"pct":34.6,"board_size":414},"math":{"rating":1283.1,"rank":253,"pct":37.6,"board_size":405},"creative_writing":{"rating":1284,"rank":241,"pct":42.3,"board_size":417},"instruction_following":{"rating":1269.7,"rank":258,"pct":38.5,"board_size":419},"hard_prompts":{"rating":1271.9,"rank":268,"pct":36.1,"board_size":419},"multi_turn":{"rating":1290.2,"rank":255,"pct":38.9,"board_size":417},"longer_query":{"rating":1276,"rank":270,"pct":32.1,"board_size":397},"non_english":{"rating":1281.9,"rank":249,"pct":40.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/grok-2-2024-08-13"},{"slug":"yi-lightning","name":"Yi Lightning","source_name":"Yi Lightning","base":"Yi Lightning","variant":null,"org":"other","open_weights":false,"model_license":"Proprietary","siscope":{"score":40.1,"rank":232,"coverage":0.75,"categories":{"coding":39.7,"reasoning":41.1,"math":39.9,"chat":40.7,"instructions":40.4}},"arena":{"text":{"rank":249,"date":"2026-10-28","rating":1301.5,"lo":1296.6,"hi":1306.4,"votes":27332,"pct":40.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1312.1,"rank":250,"pct":39.7,"board_size":414},"math":{"rating":1299.6,"rank":244,"pct":39.9,"board_size":405},"creative_writing":{"rating":1279.8,"rank":243,"pct":41.8,"board_size":417},"instruction_following":{"rating":1278.1,"rank":250,"pct":40.4,"board_size":419},"hard_prompts":{"rating":1302,"rank":247,"pct":41.1,"board_size":419},"multi_turn":{"rating":1311.1,"rank":241,"pct":42.3,"board_size":417},"longer_query":{"rating":1296.6,"rank":253,"pct":36.4,"board_size":397},"non_english":{"rating":1268.9,"rank":259,"pct":38.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/yi-lightning"},{"slug":"gpt-4o-2024-05-13","name":"GPT-4o (2024-05-13)","source_name":"GPT-4o (2024-05-13)","base":"GPT-4o","variant":"2024-05-13","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":31.3,"rank":269,"coverage":0.75,"categories":{"coding":36.8,"reasoning":30.7,"math":24.7,"chat":40.4,"instructions":40.2}},"arena":{"text":{"rank":250,"date":"2026-10-28","rating":1300.4,"lo":1297,"hi":1303.8,"votes":112881,"pct":40.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":124,"date":"2026-10-19","rating":1136.6,"lo":1127.9,"hi":1145.4,"votes":23273,"pct":25.9,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1296.9,"rank":262,"pct":36.8,"board_size":414},"math":{"rating":1284.3,"rank":252,"pct":37.9,"board_size":405},"creative_writing":{"rating":1291.2,"rank":230,"pct":45,"board_size":417},"instruction_following":{"rating":1277.5,"rank":251,"pct":40.2,"board_size":419},"hard_prompts":{"rating":1280.7,"rank":261,"pct":37.8,"board_size":419},"multi_turn":{"rating":1301.6,"rank":246,"pct":41.1,"board_size":417},"longer_query":{"rating":1288.3,"rank":261,"pct":34.3,"board_size":397},"non_english":{"rating":1282.7,"rank":247,"pct":41.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.489,"stderr":0.0263,"tested_as":"gpt-4o-2024-05-13","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FY59q8WbEDp2HH8oovyJCj9.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":23.5,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.0625,"stderr":0.0232,"tested_as":"gpt-4o-2024-05-13","approx":false,"run_date":"2025-02-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F9cCn5aW522cTRxJSE69crm.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":11.5,"tested_models":313}],"price":null,"url":"https://siscope.app/models/gpt-4o-2024-05-13"},{"slug":"claude-3-7-sonnet-20250219","name":"Claude 3.7 Sonnet (2025-02-19)","source_name":"Claude 3.7 Sonnet (20250219)","base":"Claude 3.7 Sonnet","variant":"2025-02-19","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":33.1,"rank":260,"coverage":0.75,"categories":{"coding":27.6,"reasoning":40.2,"math":32.1,"chat":40,"instructions":49.5}},"arena":{"text":{"rank":251,"date":"2026-10-28","rating":1299.3,"lo":1295.4,"hi":1303.3,"votes":42573,"pct":40,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":120,"date":"2026-10-19","rating":1150.9,"lo":1141.6,"hi":1160.3,"votes":4517,"pct":28.3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1338.7,"rank":235,"pct":43.3,"board_size":414},"math":{"rating":1318.5,"rank":226,"pct":44.3,"board_size":405},"creative_writing":{"rating":1316.5,"rank":208,"pct":50.2,"board_size":417},"instruction_following":{"rating":1324.5,"rank":212,"pct":49.5,"board_size":419},"hard_prompts":{"rating":1315,"rank":239,"pct":43.1,"board_size":419},"multi_turn":{"rating":1339.2,"rank":217,"pct":48.1,"board_size":417},"longer_query":{"rating":1354.6,"rank":196,"pct":50.5,"board_size":397},"non_english":{"rating":1286.2,"rank":243,"pct":42.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.6604,"stderr":0.0267,"tested_as":"claude-3-7-sonnet-20250219","approx":false,"run_date":"2025-02-24","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FPyNEkFCfMEReodeE2oiPhh.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":37.3,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.2194,"stderr":0.0482,"tested_as":"claude-3-7-sonnet-20250219","approx":false,"run_date":"2025-02-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FN2NcmgmHyGJ9HNmQe5yvcS.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":19.9,"tested_models":313},{"benchmark":"swe_bench_verified","score":0.6095,"stderr":0.0222,"tested_as":"claude-3-7-sonnet-20250219","approx":false,"run_date":"2026-02-04","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FcnM8U6moeqrp74wnXRj2Jj.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":11.8,"tested_models":35}],"price":null,"url":"https://siscope.app/models/claude-3-7-sonnet-20250219"},{"slug":"olmo-3-32b-think","name":"Olmo 3 32B Think","source_name":"Olmo 3 32B Think","base":"Olmo 3 32B Think","variant":null,"org":"allenai","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":40.6,"rank":230,"coverage":0.75,"categories":{"coding":40.7,"reasoning":40.9,"math":43.3,"chat":40,"instructions":39.2}},"arena":{"text":{"rank":252,"date":"2026-10-28","rating":1299.3,"lo":1291.1,"hi":1307.6,"votes":5827,"pct":40,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1318.2,"rank":246,"pct":40.7,"board_size":414},"math":{"rating":1316.3,"rank":230,"pct":43.3,"board_size":405},"creative_writing":{"rating":1255.4,"rank":266,"pct":36.3,"board_size":417},"instruction_following":{"rating":1274,"rank":255,"pct":39.2,"board_size":419},"hard_prompts":{"rating":1301.5,"rank":248,"pct":40.9,"board_size":419},"multi_turn":{"rating":1289.8,"rank":256,"pct":38.7,"board_size":417},"longer_query":{"rating":1295.2,"rank":254,"pct":36.1,"board_size":397},"non_english":{"rating":1253.8,"rank":276,"pct":34.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/olmo-3-32b-think"},{"slug":"qwen2-5-plus-1127","name":"Qwen2.5-Plus (1127)","source_name":"Qwen2.5-Plus (1127)","base":"Qwen2.5-Plus","variant":"1127","org":"alibaba","open_weights":false,"model_license":"Proprietary","siscope":{"score":39.9,"rank":233,"coverage":0.75,"categories":{"coding":40.2,"reasoning":40.7,"math":39.4,"chat":39.7,"instructions":39.7}},"arena":{"text":{"rank":253,"date":"2026-10-28","rating":1299.1,"lo":1292.8,"hi":1305.5,"votes":10187,"pct":39.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1313.9,"rank":248,"pct":40.2,"board_size":414},"math":{"rating":1297.5,"rank":246,"pct":39.4,"board_size":405},"creative_writing":{"rating":1261.5,"rank":263,"pct":37,"board_size":417},"instruction_following":{"rating":1274.4,"rank":253,"pct":39.7,"board_size":419},"hard_prompts":{"rating":1299.2,"rank":249,"pct":40.7,"board_size":419},"multi_turn":{"rating":1299.2,"rank":247,"pct":40.4,"board_size":417},"longer_query":{"rating":1291.5,"rank":256,"pct":35.6,"board_size":397},"non_english":{"rating":1264.7,"rank":265,"pct":36.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen2-5-plus-1127"},{"slug":"claude-3-5-sonnet-20241022","name":"Claude 3.5 Sonnet (2024-10-22)","source_name":"Claude 3.5 Sonnet (20241022)","base":"Claude 3.5 Sonnet","variant":"2024-10-22","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":35.6,"rank":251,"coverage":0.75,"categories":{"coding":43.8,"reasoning":35,"math":28.8,"chat":39.5,"instructions":42.6}},"arena":{"text":{"rank":254,"date":"2026-10-28","rating":1297.8,"lo":1294.7,"hi":1301,"votes":87771,"pct":39.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":126,"date":"2026-10-19","rating":1125.5,"lo":1117.6,"hi":1133.4,"votes":10374,"pct":24.7,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1342.2,"rank":233,"pct":43.8,"board_size":414},"math":{"rating":1306.5,"rank":237,"pct":41.6,"board_size":405},"creative_writing":{"rating":1291.7,"rank":229,"pct":45.2,"board_size":417},"instruction_following":{"rating":1296.9,"rank":241,"pct":42.6,"board_size":419},"hard_prompts":{"rating":1304.9,"rank":246,"pct":41.4,"board_size":419},"multi_turn":{"rating":1325.8,"rank":228,"pct":45.4,"board_size":417},"longer_query":{"rating":1311,"rank":241,"pct":39.4,"board_size":397},"non_english":{"rating":1283,"rank":246,"pct":41.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.553,"stderr":0.0282,"tested_as":"claude-3-5-sonnet-20241022","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FJCCVcVLz3J4TQXSU67hMJZ.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":28.6,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.0847,"stderr":0.0264,"tested_as":"claude-3-5-sonnet-20241022","approx":false,"run_date":"2025-02-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FgeVVaRWxuprKUqnW2VzvCa.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":16,"tested_models":313}],"price":null,"url":"https://siscope.app/models/claude-3-5-sonnet-20241022"},{"slug":"deepseek-v2-5-1210","name":"DeepSeek-V2.5 (1210)","source_name":"DeepSeek-V2.5 (1210)","base":"DeepSeek-V2.5","variant":"1210","org":"deepseek","open_weights":true,"model_license":"DeepSeek","siscope":{"score":39.1,"rank":235,"coverage":0.75,"categories":{"coding":39,"reasoning":39.2,"math":38.9,"chat":39.2,"instructions":40.9}},"arena":{"text":{"rank":255,"date":"2026-10-28","rating":1293.9,"lo":1285.7,"hi":1302.1,"votes":6795,"pct":39.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1309.1,"rank":253,"pct":39,"board_size":414},"math":{"rating":1288.5,"rank":248,"pct":38.9,"board_size":405},"creative_writing":{"rating":1284.8,"rank":240,"pct":42.5,"board_size":417},"instruction_following":{"rating":1279.5,"rank":248,"pct":40.9,"board_size":419},"hard_prompts":{"rating":1289.1,"rank":255,"pct":39.2,"board_size":419},"multi_turn":{"rating":1296.6,"rank":251,"pct":39.9,"board_size":417},"longer_query":{"rating":1300.5,"rank":248,"pct":37.6,"board_size":397},"non_english":{"rating":1273.2,"rank":255,"pct":39.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/deepseek-v2-5-1210"},{"slug":"granite-4-2-3b","name":"Granite 4.2 3B","source_name":"Granite 4.2 3B","base":"Granite 4.2 3B","variant":null,"org":"ibm","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"coding":47,"reasoning":41.6,"chat":39,"instructions":39.5}},"arena":{"text":{"rank":256,"date":"2026-10-28","rating":1293.3,"lo":1281.8,"hi":1304.8,"votes":3249,"pct":39,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1361.6,"rank":220,"pct":47,"board_size":414},"creative_writing":{"rating":1206.8,"rank":304,"pct":27.2,"board_size":417},"instruction_following":{"rating":1274.2,"rank":254,"pct":39.5,"board_size":419},"hard_prompts":{"rating":1306.1,"rank":245,"pct":41.6,"board_size":419},"multi_turn":{"rating":1292.3,"rank":254,"pct":39.2,"board_size":417},"longer_query":{"rating":1291.3,"rank":257,"pct":35.4,"board_size":397},"non_english":{"rating":1267.5,"rank":262,"pct":37.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/granite-4-2-3b"},{"slug":"athene-v2-chat","name":"Athene V2 Chat","source_name":"Athene V2 Chat","base":"Athene V2 Chat","variant":null,"org":"other","open_weights":true,"model_license":"NexusFlow","siscope":{"score":39.3,"rank":234,"coverage":0.75,"categories":{"coding":39.5,"reasoning":39.5,"math":40.1,"chat":38.8,"instructions":39}},"arena":{"text":{"rank":257,"date":"2026-10-28","rating":1291.4,"lo":1286.9,"hi":1296,"votes":24739,"pct":38.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1311.9,"rank":251,"pct":39.5,"board_size":414},"math":{"rating":1300.2,"rank":243,"pct":40.1,"board_size":405},"creative_writing":{"rating":1234,"rank":290,"pct":30.5,"board_size":417},"instruction_following":{"rating":1270.4,"rank":256,"pct":39,"board_size":419},"hard_prompts":{"rating":1292.4,"rank":254,"pct":39.5,"board_size":419},"multi_turn":{"rating":1285.7,"rank":261,"pct":37.5,"board_size":417},"longer_query":{"rating":1289.2,"rank":259,"pct":34.8,"board_size":397},"non_english":{"rating":1268.1,"rank":261,"pct":37.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/athene-v2-chat"},{"slug":"gemma-3-4b-it","name":"Gemma 3 4B IT","source_name":"Gemma 3 4B IT","base":"Gemma 3 4B IT","variant":null,"org":"google","open_weights":true,"model_license":"Gemma","siscope":{"score":22.8,"rank":308,"coverage":0.75,"categories":{"coding":26.6,"reasoning":16.7,"math":21.5,"chat":38.5,"instructions":30.6}},"arena":{"text":{"rank":258,"date":"2026-10-28","rating":1290.8,"lo":1281.6,"hi":1300,"votes":4171,"pct":38.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1230,"rank":304,"pct":26.6,"board_size":414},"math":{"rating":1239.1,"rank":290,"pct":28.5,"board_size":405},"creative_writing":{"rating":1270.1,"rank":249,"pct":40.1,"board_size":417},"instruction_following":{"rating":1238.9,"rank":291,"pct":30.6,"board_size":419},"hard_prompts":{"rating":1252.5,"rank":287,"pct":31.6,"board_size":419},"multi_turn":{"rating":1255.2,"rank":290,"pct":30.5,"board_size":417},"longer_query":{"rating":1273.2,"rank":274,"pct":31.1,"board_size":397},"non_english":{"rating":1273.1,"rank":256,"pct":39,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.2323,"stderr":0.0187,"tested_as":"gemma-3-4b-it","approx":false,"run_date":"2026-08-28","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FMcJyXLHBzx5VjAqXjmrrsb.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":1.8,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.075,"stderr":0.0276,"tested_as":"gemma-3-4b-it","approx":false,"run_date":"2026-08-28","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FKAPGpH2CLMafAt8MnAQJT3.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":14.4,"tested_models":313}],"price":null,"url":"https://siscope.app/models/gemma-3-4b-it"},{"slug":"granite-4-1-8b","name":"Granite 4.1 8B","source_name":"Granite 4.1 8B","base":"Granite 4.1 8B","variant":null,"org":"ibm","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":30.8,"rank":272,"coverage":0.75,"categories":{"coding":21.3,"reasoning":40,"math":42.6,"chat":38.3,"instructions":38}},"arena":{"text":{"rank":259,"date":"2026-10-28","rating":1290.5,"lo":1280.6,"hi":1300.4,"votes":4177,"pct":38.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"webdev":{"rank":148,"date":"2026-10-28","rating":1192.5,"lo":1174,"hi":1210.9,"votes":1766,"pct":2.6,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1312.2,"rank":249,"pct":40,"board_size":414},"math":{"rating":1311.6,"rank":233,"pct":42.6,"board_size":405},"creative_writing":{"rating":1249,"rank":270,"pct":35.3,"board_size":417},"instruction_following":{"rating":1268,"rank":260,"pct":38,"board_size":419},"hard_prompts":{"rating":1293.7,"rank":252,"pct":40,"board_size":419},"multi_turn":{"rating":1267.7,"rank":279,"pct":33.2,"board_size":417},"longer_query":{"rating":1274.7,"rank":272,"pct":31.3,"board_size":397},"non_english":{"rating":1260.1,"rank":270,"pct":35.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/granite-4-1-8b"},{"slug":"glm-4-plus","name":"GLM-4-Plus","source_name":"GLM-4-Plus","base":"GLM-4-Plus","variant":null,"org":"zai","open_weights":false,"model_license":"Proprietary","siscope":{"score":36.1,"rank":249,"coverage":0.75,"categories":{"coding":35.4,"reasoning":36.6,"math":36.1,"chat":38,"instructions":37.1}},"arena":{"text":{"rank":260,"date":"2026-10-28","rating":1289.6,"lo":1284.7,"hi":1294.5,"votes":26126,"pct":38,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1290.2,"rank":268,"pct":35.4,"board_size":414},"math":{"rating":1274.8,"rank":259,"pct":36.1,"board_size":405},"creative_writing":{"rating":1263.3,"rank":260,"pct":37.7,"board_size":417},"instruction_following":{"rating":1264.1,"rank":264,"pct":37.1,"board_size":419},"hard_prompts":{"rating":1272.8,"rank":266,"pct":36.6,"board_size":419},"multi_turn":{"rating":1289.1,"rank":258,"pct":38.2,"board_size":417},"longer_query":{"rating":1285.7,"rank":263,"pct":33.8,"board_size":397},"non_english":{"rating":1275.2,"rank":251,"pct":40.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/glm-4-plus"},{"slug":"hunyuan-large-2025-02-10","name":"Hunyuan Large (2025-02-10)","source_name":"Hunyuan Large (2025-02-10)","base":"Hunyuan Large","variant":"2025-02-10","org":"tencent","open_weights":false,"model_license":"Proprietary","siscope":{"score":37.9,"rank":238,"coverage":0.75,"categories":{"coding":38.3,"reasoning":38.8,"math":36.9,"chat":37.8,"instructions":40}},"arena":{"text":{"rank":261,"date":"2026-10-28","rating":1287.9,"lo":1278.2,"hi":1297.7,"votes":3738,"pct":37.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1306.5,"rank":256,"pct":38.3,"board_size":414},"math":{"rating":1280.7,"rank":256,"pct":36.9,"board_size":405},"creative_writing":{"rating":1264,"rank":259,"pct":38,"board_size":417},"instruction_following":{"rating":1277,"rank":252,"pct":40,"board_size":419},"hard_prompts":{"rating":1286.2,"rank":257,"pct":38.8,"board_size":419},"multi_turn":{"rating":1284.4,"rank":263,"pct":37,"board_size":417},"longer_query":{"rating":1341.2,"rank":210,"pct":47.2,"board_size":397},"non_english":{"rating":1265.1,"rank":264,"pct":37.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/hunyuan-large-2025-02-10"},{"slug":"molmo-2-8b","name":"Molmo 2 8B","source_name":"Molmo 2 8B","base":"Molmo 2 8B","variant":null,"org":"allenai","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":null,"rank":null,"coverage":0.35,"categories":{"reasoning":39,"chat":37.6,"instructions":38.8}},"arena":{"text":{"rank":262,"date":"2026-10-28","rating":1287.4,"lo":1266.7,"hi":1308.2,"votes":822,"pct":37.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":136,"date":"2026-10-19","rating":1081,"lo":1061.4,"hi":1100.6,"votes":1190,"pct":18.7,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"instruction_following":{"rating":1270.2,"rank":257,"pct":38.8,"board_size":419},"hard_prompts":{"rating":1286.9,"rank":256,"pct":39,"board_size":419},"non_english":{"rating":1274.3,"rank":253,"pct":39.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/molmo-2-8b"},{"slug":"gpt-oss-20b","name":"gpt-oss-20b","source_name":"gpt-oss-20b","base":"gpt-oss-20b","variant":null,"org":"openai","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":36.3,"rank":247,"coverage":0.75,"categories":{"coding":38,"reasoning":36.8,"math":43.6,"chat":37.3,"instructions":30.4}},"arena":{"text":{"rank":263,"date":"2026-10-28","rating":1287.3,"lo":1280.9,"hi":1293.7,"votes":10416,"pct":37.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1306.4,"rank":257,"pct":38,"board_size":414},"math":{"rating":1316.9,"rank":229,"pct":43.6,"board_size":405},"creative_writing":{"rating":1200.5,"rank":309,"pct":26,"board_size":417},"instruction_following":{"rating":1236.1,"rank":292,"pct":30.4,"board_size":419},"hard_prompts":{"rating":1273.6,"rank":265,"pct":36.8,"board_size":419},"multi_turn":{"rating":1267.6,"rank":280,"pct":32.9,"board_size":417},"longer_query":{"rating":1250,"rank":292,"pct":26.5,"board_size":397},"non_english":{"rating":1268.4,"rank":260,"pct":38,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/gpt-oss-20b","input_per_m":0.03,"output_per_m":0.13,"blended_per_m":0.055,"context_length":131072,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-oss-20b"},{"slug":"llama-4-maverick-17b-128e-instruct","name":"Llama 4 Maverick 17B 128E Instruct","source_name":"Llama 4 Maverick 17B 128E Instruct","base":"Llama 4 Maverick 17B 128E Instruct","variant":null,"org":"meta","open_weights":true,"model_license":"Llama 4","siscope":{"score":37.7,"rank":239,"coverage":0.75,"categories":{"coding":37.3,"reasoning":37.6,"math":39.6,"chat":37.1,"instructions":37.8}},"arena":{"text":{"rank":264,"date":"2026-10-28","rating":1287.2,"lo":1283,"hi":1291.5,"votes":39439,"pct":37.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":122,"date":"2026-10-19","rating":1141.7,"lo":1132.7,"hi":1150.8,"votes":6923,"pct":27.1,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1301.3,"rank":260,"pct":37.3,"board_size":414},"math":{"rating":1299.3,"rank":245,"pct":39.6,"board_size":405},"creative_writing":{"rating":1266,"rank":257,"pct":38.5,"board_size":417},"instruction_following":{"rating":1266.9,"rank":261,"pct":37.8,"board_size":419},"hard_prompts":{"rating":1280.6,"rank":262,"pct":37.6,"board_size":419},"multi_turn":{"rating":1289.4,"rank":257,"pct":38.5,"board_size":417},"longer_query":{"rating":1279.6,"rank":268,"pct":32.6,"board_size":397},"non_english":{"rating":1269,"rank":258,"pct":38.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/llama-4-maverick-17b-128e-instruct"},{"slug":"gemini-1-5-flash-002","name":"Gemini 1.5 Flash (002)","source_name":"Gemini 1.5 Flash (002)","base":"Gemini 1.5 Flash","variant":"002","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":32,"rank":266,"coverage":0.75,"categories":{"coding":29.8,"reasoning":33,"math":33.4,"chat":36.8,"instructions":35.6}},"arena":{"text":{"rank":265,"date":"2026-10-28","rating":1286.6,"lo":1282.4,"hi":1290.8,"votes":34902,"pct":36.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":123,"date":"2026-10-19","rating":1140.7,"lo":1130.7,"hi":1150.6,"votes":7241,"pct":26.5,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1261.2,"rank":291,"pct":29.8,"board_size":414},"math":{"rating":1269.1,"rank":270,"pct":33.4,"board_size":405},"creative_writing":{"rating":1285.1,"rank":239,"pct":42.8,"board_size":417},"instruction_following":{"rating":1257.3,"rank":270,"pct":35.6,"board_size":419},"hard_prompts":{"rating":1257.1,"rank":280,"pct":33,"board_size":419},"multi_turn":{"rating":1252.6,"rank":292,"pct":30,"board_size":417},"longer_query":{"rating":1283.6,"rank":264,"pct":33.6,"board_size":397},"non_english":{"rating":1278.1,"rank":250,"pct":40.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemini-1-5-flash-002"},{"slug":"gpt-4o-mini-2024-07-18","name":"GPT-4o mini (2024-07-18)","source_name":"GPT-4o mini (2024-07-18)","base":"GPT-4o mini","variant":"2024-07-18","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":23.8,"rank":305,"coverage":0.75,"categories":{"coding":35.1,"reasoning":16,"math":16.1,"chat":36.6,"instructions":35.9}},"arena":{"text":{"rank":266,"date":"2026-10-28","rating":1286.4,"lo":1282.8,"hi":1289.9,"votes":68705,"pct":36.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":137,"date":"2026-10-19","rating":1065.6,"lo":1057.3,"hi":1073.9,"votes":17341,"pct":18.1,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1289.4,"rank":269,"pct":35.1,"board_size":414},"math":{"rating":1267.4,"rank":273,"pct":32.7,"board_size":405},"creative_writing":{"rating":1267.5,"rank":256,"pct":38.7,"board_size":417},"instruction_following":{"rating":1258.2,"rank":269,"pct":35.9,"board_size":419},"hard_prompts":{"rating":1266.8,"rank":273,"pct":34.7,"board_size":419},"multi_turn":{"rating":1285.1,"rank":262,"pct":37.3,"board_size":417},"longer_query":{"rating":1288.6,"rank":260,"pct":34.6,"board_size":397},"non_english":{"rating":1266.1,"rank":263,"pct":37.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.3772,"stderr":0.0241,"tested_as":"gpt-4o-mini-2024-07-18","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FL9yfwZC3snsKZshBXTaXjc.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":12.3,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.083,"stderr":0.0087,"tested_as":"gpt-4o-mini-2024-07-18","approx":false,"run_date":"2026-08-31","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FDLr586bZUHpghAf8m3GRSm.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":1,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.0694,"stderr":0.0274,"tested_as":"gpt-4o-mini-2024-07-18","approx":false,"run_date":"2025-07-30","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FMPJkYPEMsQrowqtecK3mmz.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":13.8,"tested_models":313},{"benchmark":"frontiermath","score":0.007,"stderr":0.005,"tested_as":"gpt-4o-mini-2024-07-18","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F6XhtKr59amKko65T7RUB2a.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":1.7,"tested_models":122}],"price":{"openrouter_id":"openai/gpt-4o-mini","input_per_m":0.15,"output_per_m":0.6,"blended_per_m":0.2625,"context_length":128000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-4o-mini-2024-07-18"},{"slug":"gpt-4-1-nano-2025-04-14","name":"GPT-4.1 nano (2025-04-14)","source_name":"GPT-4.1 nano (2025-04-14)","base":"GPT-4.1 nano","variant":"2025-04-14","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":28.7,"rank":282,"coverage":0.75,"categories":{"coding":37.5,"reasoning":20.8,"math":29.7,"chat":36.4,"instructions":37.3}},"arena":{"text":{"rank":267,"date":"2026-10-28","rating":1284.8,"lo":1277.1,"hi":1292.4,"votes":6103,"pct":36.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":139,"date":"2026-10-19","rating":1063.2,"lo":1044.9,"hi":1081.5,"votes":1211,"pct":16.9,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1305.4,"rank":259,"pct":37.5,"board_size":414},"math":{"rating":1274.3,"rank":260,"pct":35.9,"board_size":405},"creative_writing":{"rating":1259.8,"rank":264,"pct":36.8,"board_size":417},"instruction_following":{"rating":1266.4,"rank":263,"pct":37.3,"board_size":419},"hard_prompts":{"rating":1285.6,"rank":258,"pct":38.5,"board_size":419},"multi_turn":{"rating":1276.6,"rank":269,"pct":35.6,"board_size":417},"longer_query":{"rating":1282.4,"rank":266,"pct":33.1,"board_size":397},"non_english":{"rating":1259.9,"rank":271,"pct":35.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.4893,"stderr":0.0248,"tested_as":"gpt-4.1-nano-2025-04-14","approx":false,"run_date":"2025-04-14","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FazWfeFPP6zSocuQX3JYBU5.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":23.8,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.06,"stderr":0.0075,"tested_as":"gpt-4.1-nano-2025-04-14","approx":false,"run_date":"2026-08-31","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FA4JEeJR5LQfLR3Hb8z7kL2.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":0,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.2889,"stderr":0.0597,"tested_as":"gpt-4.1-nano-2025-04-14","approx":false,"run_date":"2025-04-14","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F3qLHwibDhgtWEbKGwxUYVa.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":23.4,"tested_models":313}],"price":{"openrouter_id":"openai/gpt-4.1-nano","input_per_m":0.1,"output_per_m":0.4,"blended_per_m":0.175,"context_length":1047576,"modalities_in":["image","text","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-4-1-nano-2025-04-14"},{"slug":"llama-3-1-405b-instruct-bf16","name":"Llama 3.1 405B Instruct (BF16)","source_name":"Llama 3.1 405B Instruct (BF16)","base":"Llama 3.1 405B Instruct","variant":"BF16","org":"meta","open_weights":true,"model_license":"Llama 3.1 Community","siscope":{"score":31.2,"rank":270,"coverage":0.75,"categories":{"coding":35.8,"reasoning":30.6,"math":26.7,"chat":36.1,"instructions":36.4}},"arena":{"text":{"rank":268,"date":"2026-10-28","rating":1283.7,"lo":1280,"hi":1287.4,"votes":41375,"pct":36.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1291,"rank":266,"pct":35.8,"board_size":414},"math":{"rating":1278.2,"rank":257,"pct":36.6,"board_size":405},"creative_writing":{"rating":1259.4,"rank":265,"pct":36.5,"board_size":417},"instruction_following":{"rating":1258.5,"rank":267,"pct":36.4,"board_size":419},"hard_prompts":{"rating":1269.3,"rank":272,"pct":35.2,"board_size":419},"multi_turn":{"rating":1296.8,"rank":250,"pct":40.1,"board_size":417},"longer_query":{"rating":1265.4,"rank":278,"pct":30.1,"board_size":397},"non_english":{"rating":1246.7,"rank":282,"pct":32.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.5092,"stderr":0.0259,"tested_as":"Llama-3.1-405B-Instruct","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FS5QYXSvQBRSbUbXSnAGbMm.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":25.9,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.0972,"stderr":0.0322,"tested_as":"Llama-3.1-405B-Instruct","approx":false,"run_date":"2025-02-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2fQJP3brRApfBdQq7Zy3bm.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":16.7,"tested_models":313}],"price":null,"url":"https://siscope.app/models/llama-3-1-405b-instruct-bf16"},{"slug":"llama-3-1-nemotron-70b-instruct","name":"Llama 3.1 Nemotron 70B Instruct","source_name":"Llama 3.1 Nemotron 70B Instruct","base":"Llama 3.1 Nemotron 70B Instruct","variant":null,"org":"nvidia","open_weights":true,"model_license":"Llama 3.1","siscope":{"score":33.4,"rank":258,"coverage":0.75,"categories":{"coding":32.2,"reasoning":34.4,"math":34.4,"chat":35.9,"instructions":34.2}},"arena":{"text":{"rank":269,"date":"2026-10-28","rating":1282.6,"lo":1274.9,"hi":1290.3,"votes":7140,"pct":35.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1271.5,"rank":281,"pct":32.2,"board_size":414},"math":{"rating":1271,"rank":266,"pct":34.4,"board_size":405},"creative_writing":{"rating":1268.3,"rank":254,"pct":39.2,"board_size":417},"instruction_following":{"rating":1251.7,"rank":276,"pct":34.2,"board_size":419},"hard_prompts":{"rating":1266.2,"rank":275,"pct":34.4,"board_size":419},"multi_turn":{"rating":1275.3,"rank":271,"pct":34.9,"board_size":417},"longer_query":{"rating":1238.1,"rank":297,"pct":25.3,"board_size":397},"non_english":{"rating":1244.8,"rank":285,"pct":32.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/llama-3-1-nemotron-70b-instruct"},{"slug":"gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","source_name":"GPT-4o (2024-08-06)","base":"GPT-4o","variant":"2024-08-06","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":26,"rank":292,"coverage":0.75,"categories":{"coding":33.4,"reasoning":27,"math":17,"chat":35.6,"instructions":37.6}},"arena":{"text":{"rank":270,"date":"2026-10-28","rating":1282.5,"lo":1278.3,"hi":1286.7,"votes":45499,"pct":35.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":138,"date":"2026-10-19","rating":1064.6,"lo":1052.1,"hi":1077.1,"votes":3376,"pct":17.5,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1283.2,"rank":275,"pct":33.4,"board_size":414},"math":{"rating":1285.3,"rank":251,"pct":38.1,"board_size":405},"creative_writing":{"rating":1274.3,"rank":245,"pct":41.3,"board_size":417},"instruction_following":{"rating":1266.5,"rank":262,"pct":37.6,"board_size":419},"hard_prompts":{"rating":1263.9,"rank":278,"pct":33.7,"board_size":419},"multi_turn":{"rating":1278.8,"rank":267,"pct":36.1,"board_size":417},"longer_query":{"rating":1283.2,"rank":265,"pct":33.3,"board_size":397},"non_english":{"rating":1261.5,"rank":268,"pct":36.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.4921,"stderr":0.026,"tested_as":"gpt-4o-2024-08-06","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FfairJpL9VekDBKxYHG9ZoG.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":25,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.26,"stderr":0.0139,"tested_as":"gpt-4o-2024-08-06","approx":false,"run_date":"2026-08-31","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FbDFqfWxMG7gLDq4Mz8PRTP.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":22.2,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.0639,"stderr":0.0256,"tested_as":"gpt-4o-2024-08-06","approx":false,"run_date":"2025-02-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FmBUKqiVQsqXd3qmdtKP5UP.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":12.2,"tested_models":313},{"benchmark":"frontiermath","score":0.0035,"stderr":0.0035,"tested_as":"gpt-4o-2024-08-06","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FikS95CXY2foitnUPDKwNJn.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":0.8,"tested_models":122}],"price":null,"url":"https://siscope.app/models/gpt-4o-2024-08-06"},{"slug":"mercury","name":"Mercury","source_name":"Mercury","base":"Mercury","variant":null,"org":"inception-ai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"coding":41.9,"reasoning":38.3,"chat":35.4,"instructions":30.9}},"arena":{"text":{"rank":271,"date":"2026-10-28","rating":1282,"lo":1268.3,"hi":1295.7,"votes":1966,"pct":35.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1322.2,"rank":241,"pct":41.9,"board_size":414},"creative_writing":{"rating":1189,"rank":317,"pct":24,"board_size":417},"instruction_following":{"rating":1239.9,"rank":290,"pct":30.9,"board_size":419},"hard_prompts":{"rating":1285,"rank":259,"pct":38.3,"board_size":419},"multi_turn":{"rating":1282.2,"rank":264,"pct":36.8,"board_size":417},"longer_query":{"rating":1264.3,"rank":280,"pct":29.5,"board_size":397},"non_english":{"rating":1259.5,"rank":272,"pct":35.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/mercury"},{"slug":"qwen-max-0919","name":"Qwen-Max (0919)","source_name":"Qwen-Max (0919)","base":"Qwen-Max","variant":"0919","org":"alibaba","open_weights":false,"model_license":"Qwen","siscope":{"score":35.3,"rank":253,"coverage":0.75,"categories":{"coding":34.9,"reasoning":35.2,"math":36.4,"chat":35.2,"instructions":36.6}},"arena":{"text":{"rank":272,"date":"2026-10-28","rating":1281.9,"lo":1276.2,"hi":1287.5,"votes":16478,"pct":35.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1287.8,"rank":270,"pct":34.9,"board_size":414},"math":{"rating":1275,"rank":258,"pct":36.4,"board_size":405},"creative_writing":{"rating":1247.8,"rank":272,"pct":34.9,"board_size":417},"instruction_following":{"rating":1261.7,"rank":266,"pct":36.6,"board_size":419},"hard_prompts":{"rating":1269.3,"rank":271,"pct":35.2,"board_size":419},"multi_turn":{"rating":1276.7,"rank":268,"pct":35.8,"board_size":417},"longer_query":{"rating":1288.1,"rank":262,"pct":34.1,"board_size":397},"non_english":{"rating":1262.8,"rank":267,"pct":36.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen-max-0919"},{"slug":"llama-3-1-405b-instruct-fp8","name":"Llama 3.1 405B Instruct (FP8)","source_name":"Llama 3.1 405B Instruct (FP8)","base":"Llama 3.1 405B Instruct","variant":"FP8","org":"meta","open_weights":true,"model_license":"Llama 3.1 Community","siscope":{"score":30.3,"rank":275,"coverage":0.75,"categories":{"coding":33.4,"reasoning":29.7,"math":26.9,"chat":34.9,"instructions":36.1}},"arena":{"text":{"rank":273,"date":"2026-10-28","rating":1281.8,"lo":1278.2,"hi":1285.4,"votes":59656,"pct":34.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1283.2,"rank":276,"pct":33.4,"board_size":414},"math":{"rating":1281.3,"rank":255,"pct":37.1,"board_size":405},"creative_writing":{"rating":1261.7,"rank":262,"pct":37.3,"board_size":417},"instruction_following":{"rating":1258.4,"rank":268,"pct":36.1,"board_size":419},"hard_prompts":{"rating":1263.3,"rank":279,"pct":33.5,"board_size":419},"multi_turn":{"rating":1287.3,"rank":260,"pct":37.7,"board_size":417},"longer_query":{"rating":1259.2,"rank":283,"pct":28.8,"board_size":397},"non_english":{"rating":1247.7,"rank":281,"pct":33,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.5092,"stderr":0.0259,"tested_as":"Llama-3.1-405B-Instruct","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FS5QYXSvQBRSbUbXSnAGbMm.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":25.9,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.0972,"stderr":0.0322,"tested_as":"Llama-3.1-405B-Instruct","approx":false,"run_date":"2025-02-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2fQJP3brRApfBdQq7Zy3bm.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":16.7,"tested_models":313}],"price":null,"url":"https://siscope.app/models/llama-3-1-405b-instruct-fp8"},{"slug":"claude-3-5-sonnet-20240620","name":"Claude 3.5 Sonnet (2024-06-20)","source_name":"Claude 3.5 Sonnet (20240620)","base":"Claude 3.5 Sonnet","variant":"2024-06-20","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":32,"rank":267,"coverage":0.75,"categories":{"coding":37.8,"reasoning":32.6,"math":26.6,"chat":34.7,"instructions":38.3}},"arena":{"text":{"rank":274,"date":"2026-10-28","rating":1280.9,"lo":1277.5,"hi":1284.3,"votes":82419,"pct":34.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":128,"date":"2026-10-19","rating":1120.3,"lo":1110.2,"hi":1130.4,"votes":21624,"pct":23.5,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1306.2,"rank":258,"pct":37.8,"board_size":414},"math":{"rating":1303.3,"rank":241,"pct":40.6,"board_size":405},"creative_writing":{"rating":1237.8,"rank":284,"pct":32,"board_size":417},"instruction_following":{"rating":1269.4,"rank":259,"pct":38.3,"board_size":419},"hard_prompts":{"rating":1275.3,"rank":264,"pct":37.1,"board_size":419},"multi_turn":{"rating":1299.2,"rank":248,"pct":40.4,"board_size":417},"longer_query":{"rating":1274.7,"rank":273,"pct":31.3,"board_size":397},"non_english":{"rating":1269.9,"rank":257,"pct":38.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.5404,"stderr":0.0275,"tested_as":"claude-3-5-sonnet-20240620","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F78Wpvp8WDByAcQRBas72cs.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":28,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.0653,"stderr":0.0223,"tested_as":"claude-3-5-sonnet-20240620","approx":false,"run_date":"2025-02-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F2xNPhKLsiWLHQBLLDGU4VJ.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":12.5,"tested_models":313}],"price":null,"url":"https://siscope.app/models/claude-3-5-sonnet-20240620"},{"slug":"grok-2-mini-2024-08-13","name":"Grok 2 mini (2024-08-13)","source_name":"Grok 2 mini (2024-08-13)","base":"Grok 2 mini","variant":"2024-08-13","org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":32,"rank":265,"coverage":0.75,"categories":{"coding":31.5,"reasoning":32.1,"math":32.2,"chat":34.4,"instructions":31.8}},"arena":{"text":{"rank":275,"date":"2026-10-28","rating":1280.7,"lo":1277,"hi":1284.4,"votes":52567,"pct":34.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1268.3,"rank":284,"pct":31.5,"board_size":414},"math":{"rating":1265.1,"rank":275,"pct":32.2,"board_size":405},"creative_writing":{"rating":1241.2,"rank":280,"pct":32.9,"board_size":417},"instruction_following":{"rating":1244.6,"rank":286,"pct":31.8,"board_size":419},"hard_prompts":{"rating":1254.8,"rank":285,"pct":32.1,"board_size":419},"multi_turn":{"rating":1265.4,"rank":282,"pct":32.5,"board_size":417},"longer_query":{"rating":1266.1,"rank":277,"pct":30.3,"board_size":397},"non_english":{"rating":1256.9,"rank":274,"pct":34.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/grok-2-mini-2024-08-13"},{"slug":"llama-4-scout-17b-16e-instruct","name":"Llama 4 Scout 17B 16E Instruct","source_name":"Llama 4 Scout 17B 16E Instruct","base":"Llama 4 Scout 17B 16E Instruct","variant":null,"org":"meta","open_weights":true,"model_license":"Llama","siscope":{"score":30.2,"rank":276,"coverage":0.75,"categories":{"coding":33.9,"reasoning":30.4,"math":26.6,"chat":34.2,"instructions":32.5}},"arena":{"text":{"rank":276,"date":"2026-10-28","rating":1279.1,"lo":1274.4,"hi":1283.9,"votes":29823,"pct":34.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":129,"date":"2026-10-19","rating":1118.4,"lo":1108.9,"hi":1127.8,"votes":6446,"pct":22.9,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1285.7,"rank":274,"pct":33.9,"board_size":414},"math":{"rating":1286.8,"rank":250,"pct":38.4,"board_size":405},"creative_writing":{"rating":1248.6,"rank":271,"pct":35.1,"board_size":417},"instruction_following":{"rating":1247.6,"rank":283,"pct":32.5,"board_size":419},"hard_prompts":{"rating":1266,"rank":276,"pct":34.2,"board_size":419},"multi_turn":{"rating":1279.9,"rank":265,"pct":36.5,"board_size":417},"longer_query":{"rating":1264.8,"rank":279,"pct":29.8,"board_size":397},"non_english":{"rating":1252.2,"rank":279,"pct":33.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.5183,"stderr":0.0315,"tested_as":"Llama-4-Scout-17B-16E-Instruct","approx":false,"run_date":"2025-04-08","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FMsXAXDEKP3xBKtiA7aTBBG.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":26.5,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.0778,"stderr":0.0301,"tested_as":"Llama-4-Scout-17B-16E-Instruct","approx":false,"run_date":"2025-04-08","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FT3X5DeC47iqCaoRYXu5k8L.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":14.7,"tested_models":313}],"price":null,"url":"https://siscope.app/models/llama-4-scout-17b-16e-instruct"},{"slug":"gemini-advanced-0514","name":"Gemini Advanced (0514)","source_name":"Gemini Advanced (0514)","base":"Gemini Advanced","variant":"0514","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":31.1,"rank":271,"coverage":0.75,"categories":{"coding":29.3,"reasoning":30.6,"math":34.7,"chat":34,"instructions":34.4}},"arena":{"text":{"rank":277,"date":"2026-10-28","rating":1278.5,"lo":1273.4,"hi":1283.6,"votes":50148,"pct":34,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1254.5,"rank":293,"pct":29.3,"board_size":414},"math":{"rating":1271.6,"rank":264,"pct":34.7,"board_size":405},"creative_writing":{"rating":1283.9,"rank":242,"pct":42.1,"board_size":417},"instruction_following":{"rating":1253.3,"rank":275,"pct":34.4,"board_size":419},"hard_prompts":{"rating":1248.1,"rank":291,"pct":30.6,"board_size":419},"multi_turn":{"rating":1268.9,"rank":277,"pct":33.7,"board_size":417},"longer_query":{"rating":1253.2,"rank":289,"pct":27.3,"board_size":397},"non_english":{"rating":1273.9,"rank":254,"pct":39.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemini-advanced-0514"},{"slug":"mistral-small-3-1-24b-instruct-2503","name":"Mistral Small 3.1 24B Instruct (2503)","source_name":"Mistral Small 3.1 24B Instruct (2503)","base":"Mistral Small 3.1 24B Instruct","variant":"2503","org":"mistral","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":34.9,"rank":254,"coverage":0.75,"categories":{"coding":38.7,"reasoning":37.3,"math":31.4,"chat":33.7,"instructions":36.8}},"arena":{"text":{"rank":278,"date":"2026-10-28","rating":1277,"lo":1272.5,"hi":1281.5,"votes":32722,"pct":33.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":125,"date":"2026-10-19","rating":1136.5,"lo":1128,"hi":1144.9,"votes":28490,"pct":25.3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1308.7,"rank":254,"pct":38.7,"board_size":414},"math":{"rating":1260.9,"rank":278,"pct":31.4,"board_size":405},"creative_writing":{"rating":1251.9,"rank":267,"pct":36.1,"board_size":417},"instruction_following":{"rating":1263,"rank":265,"pct":36.8,"board_size":419},"hard_prompts":{"rating":1277.6,"rank":263,"pct":37.3,"board_size":419},"multi_turn":{"rating":1270.2,"rank":276,"pct":33.9,"board_size":417},"longer_query":{"rating":1298.2,"rank":252,"pct":36.6,"board_size":397},"non_english":{"rating":1254.5,"rank":275,"pct":34.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/mistral-small-3-1-24b-instruct-2503"},{"slug":"llama-3-3-70b-instruct","name":"Llama 3.3 70B Instruct","source_name":"Llama 3.3 70B Instruct","base":"Llama 3.3 70B Instruct","variant":null,"org":"meta","open_weights":true,"model_license":"Llama-3.3","siscope":{"score":26.6,"rank":288,"coverage":0.75,"categories":{"coding":30.8,"reasoning":27.1,"math":21.4,"chat":33.5,"instructions":31.6}},"arena":{"text":{"rank":279,"date":"2026-10-28","rating":1274.2,"lo":1270.8,"hi":1277.7,"votes":54493,"pct":33.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1267.8,"rank":287,"pct":30.8,"board_size":414},"math":{"rating":1267.1,"rank":274,"pct":32.4,"board_size":405},"creative_writing":{"rating":1250.1,"rank":268,"pct":35.8,"board_size":417},"instruction_following":{"rating":1241.7,"rank":287,"pct":31.6,"board_size":419},"hard_prompts":{"rating":1257.1,"rank":281,"pct":33,"board_size":419},"multi_turn":{"rating":1279.5,"rank":266,"pct":36.3,"board_size":417},"longer_query":{"rating":1255.3,"rank":286,"pct":28,"board_size":397},"non_english":{"rating":1236.2,"rank":290,"pct":30.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.4744,"stderr":0.0285,"tested_as":"Llama-3.3-70B-Instruct","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FTxXS78Wg2pSCDbpmeJuzQn.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":21.1,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.0514,"stderr":0.0236,"tested_as":"Llama-3.3-70B-Instruct","approx":false,"run_date":"2025-02-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FZjsXQpZ7SsejXDo52aetZZ.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":10.3,"tested_models":313}],"price":{"openrouter_id":"meta-llama/llama-3.3-70b-instruct","input_per_m":0.1,"output_per_m":0.32,"blended_per_m":0.155,"context_length":131072,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/llama-3-3-70b-instruct"},{"slug":"hunyuan-standard-2025-02-10","name":"Hunyuan Standard (2025-02-10)","source_name":"Hunyuan Standard (2025-02-10)","base":"Hunyuan Standard","variant":"2025-02-10","org":"tencent","open_weights":false,"model_license":"Proprietary","siscope":{"score":32.9,"rank":261,"coverage":0.75,"categories":{"coding":31.7,"reasoning":34,"math":35.6,"chat":33.3,"instructions":32.1}},"arena":{"text":{"rank":280,"date":"2026-10-28","rating":1274,"lo":1264.3,"hi":1283.6,"votes":3904,"pct":33.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1269.4,"rank":283,"pct":31.7,"board_size":414},"math":{"rating":1274.1,"rank":261,"pct":35.6,"board_size":405},"creative_writing":{"rating":1241.9,"rank":278,"pct":33.4,"board_size":417},"instruction_following":{"rating":1244.8,"rank":285,"pct":32.1,"board_size":419},"hard_prompts":{"rating":1264.2,"rank":277,"pct":34,"board_size":419},"multi_turn":{"rating":1274.8,"rank":274,"pct":34.4,"board_size":417},"longer_query":{"rating":1300.6,"rank":247,"pct":37.9,"board_size":397},"non_english":{"rating":1261.4,"rank":269,"pct":35.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/hunyuan-standard-2025-02-10"},{"slug":"gemini-1-5-pro-001","name":"Gemini 1.5 Pro (001)","source_name":"Gemini 1.5 Pro (001)","base":"Gemini 1.5 Pro","variant":"001","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":31.6,"rank":268,"coverage":0.75,"categories":{"coding":30.3,"reasoning":31.8,"math":33.9,"chat":33,"instructions":34.7}},"arena":{"text":{"rank":281,"date":"2026-10-28","rating":1273.5,"lo":1269.5,"hi":1277.4,"votes":79138,"pct":33,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":135,"date":"2026-10-19","rating":1088.3,"lo":1076.6,"hi":1100,"votes":16734,"pct":19.3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1266,"rank":289,"pct":30.3,"board_size":414},"math":{"rating":1269.5,"rank":268,"pct":33.9,"board_size":405},"creative_writing":{"rating":1272.2,"rank":247,"pct":40.9,"board_size":417},"instruction_following":{"rating":1253.5,"rank":274,"pct":34.7,"board_size":419},"hard_prompts":{"rating":1254.7,"rank":286,"pct":31.8,"board_size":419},"multi_turn":{"rating":1268.1,"rank":278,"pct":33.4,"board_size":417},"longer_query":{"rating":1290.5,"rank":258,"pct":35.1,"board_size":397},"non_english":{"rating":1264.3,"rank":266,"pct":36.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemini-1-5-pro-001"},{"slug":"gpt-4-turbo-2024-04-09","name":"GPT-4 Turbo (2024-04-09)","source_name":"GPT-4 Turbo (2024-04-09)","base":"GPT-4 Turbo","variant":"2024-04-09","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":24.4,"rank":301,"coverage":0.75,"categories":{"coding":31,"reasoning":25.4,"math":16.4,"chat":32.8,"instructions":33.7}},"arena":{"text":{"rank":282,"date":"2026-10-28","rating":1271.7,"lo":1267.8,"hi":1275.6,"votes":98114,"pct":32.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":133,"date":"2026-10-19","rating":1089.9,"lo":1078.3,"hi":1101.5,"votes":13391,"pct":20.5,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1268.1,"rank":286,"pct":31,"board_size":414},"math":{"rating":1271.6,"rank":265,"pct":34.7,"board_size":405},"creative_writing":{"rating":1268.2,"rank":255,"pct":38.9,"board_size":417},"instruction_following":{"rating":1249.3,"rank":278,"pct":33.7,"board_size":419},"hard_prompts":{"rating":1250.8,"rank":290,"pct":30.9,"board_size":419},"multi_turn":{"rating":1267,"rank":281,"pct":32.7,"board_size":417},"longer_query":{"rating":1253.5,"rank":288,"pct":27.5,"board_size":397},"non_english":{"rating":1245,"rank":284,"pct":32.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.4659,"stderr":0.0266,"tested_as":"gpt-4-turbo-2024-04-09","approx":false,"run_date":"2025-02-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FTaCoN7eyPQEfDWXqs2MpcF.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":19.9,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.0667,"stderr":0.024,"tested_as":"gpt-4-turbo-2024-04-09","approx":false,"run_date":"2025-02-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FMZABVPEY8VCPAyCZ4iir68.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":12.8,"tested_models":313},{"benchmark":"frontiermath","score":0.007,"stderr":0.005,"tested_as":"gpt-4-turbo-2024-04-09","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FbC2dbN4x2GWWmnnfseKxgQ.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":1.7,"tested_models":122}],"price":null,"url":"https://siscope.app/models/gpt-4-turbo-2024-04-09"},{"slug":"olmo-3-1-32b-think","name":"Olmo 3.1 32B Think","source_name":"Olmo 3.1 32B Think","base":"Olmo 3.1 32B Think","variant":null,"org":"allenai","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":35.3,"rank":252,"coverage":0.75,"categories":{"coding":35.6,"reasoning":36.4,"math":41.3,"chat":32.5,"instructions":32.3}},"arena":{"text":{"rank":283,"date":"2026-10-28","rating":1271.4,"lo":1264.1,"hi":1278.6,"votes":8299,"pct":32.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1290.9,"rank":267,"pct":35.6,"board_size":414},"math":{"rating":1304.7,"rank":238,"pct":41.3,"board_size":405},"creative_writing":{"rating":1226.7,"rank":295,"pct":29.3,"board_size":417},"instruction_following":{"rating":1246.2,"rank":284,"pct":32.3,"board_size":419},"hard_prompts":{"rating":1272.2,"rank":267,"pct":36.4,"board_size":419},"multi_turn":{"rating":1251,"rank":294,"pct":29.6,"board_size":417},"longer_query":{"rating":1271,"rank":276,"pct":30.6,"board_size":397},"non_english":{"rating":1209.1,"rank":304,"pct":27.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/olmo-3-1-32b-think"},{"slug":"deepseek-v2-5","name":"DeepSeek-V2.5","source_name":"DeepSeek-V2.5","base":"DeepSeek-V2.5","variant":null,"org":"deepseek","open_weights":true,"model_license":"DeepSeek","siscope":{"score":34.5,"rank":255,"coverage":0.75,"categories":{"coding":37,"reasoning":35.6,"math":34.2,"chat":32.3,"instructions":33.5}},"arena":{"text":{"rank":284,"date":"2026-10-28","rating":1271.2,"lo":1266.5,"hi":1275.9,"votes":24572,"pct":32.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1301,"rank":261,"pct":37,"board_size":414},"math":{"rating":1270.7,"rank":267,"pct":34.2,"board_size":405},"creative_writing":{"rating":1236.5,"rank":285,"pct":31.7,"board_size":417},"instruction_following":{"rating":1249,"rank":279,"pct":33.5,"board_size":419},"hard_prompts":{"rating":1270.2,"rank":270,"pct":35.6,"board_size":419},"multi_turn":{"rating":1260.7,"rank":284,"pct":32,"board_size":417},"longer_query":{"rating":1272.7,"rank":275,"pct":30.8,"board_size":397},"non_english":{"rating":1253.1,"rank":278,"pct":33.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/deepseek-v2-5"},{"slug":"qwen2-5-72b-instruct","name":"Qwen2.5 72B Instruct","source_name":"Qwen2.5-72B-Instruct","base":"Qwen2.5 72B Instruct","variant":null,"org":"alibaba","open_weights":true,"model_license":"Qwen","siscope":{"score":30.6,"rank":274,"coverage":0.75,"categories":{"coding":36.1,"reasoning":30.3,"math":26.4,"chat":32.1,"instructions":35.2}},"arena":{"text":{"rank":285,"date":"2026-10-28","rating":1269,"lo":1264.9,"hi":1273.1,"votes":39406,"pct":32.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1292.2,"rank":265,"pct":36.1,"board_size":414},"math":{"rating":1282.6,"rank":254,"pct":37.4,"board_size":405},"creative_writing":{"rating":1221,"rank":297,"pct":28.8,"board_size":417},"instruction_following":{"rating":1253.9,"rank":272,"pct":35.2,"board_size":419},"hard_prompts":{"rating":1270.5,"rank":269,"pct":35.9,"board_size":419},"multi_turn":{"rating":1271.8,"rank":275,"pct":34.1,"board_size":417},"longer_query":{"rating":1281.4,"rank":267,"pct":32.8,"board_size":397},"non_english":{"rating":1251.7,"rank":280,"pct":33.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.4915,"stderr":0.0269,"tested_as":"qwen2.5-72b-instruct","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FWtALgW6VSFdihDZWXRm2AZ.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":24.7,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.0806,"stderr":0.0261,"tested_as":"qwen2.5-72b-instruct","approx":false,"run_date":"2025-02-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F67YbVQfJh7sd77KH3zFgTn.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":15.4,"tested_models":313}],"price":{"openrouter_id":"qwen/qwen-2.5-72b-instruct","input_per_m":0.36,"output_per_m":0.4,"blended_per_m":0.37,"context_length":32768,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/qwen2-5-72b-instruct"},{"slug":"mistral-large-2-2407","name":"Mistral Large 2 (2407)","source_name":"Mistral Large 2 (2407)","base":"Mistral Large 2","variant":"2407","org":"mistral","open_weights":true,"model_license":"Mistral Research","siscope":{"score":32.2,"rank":262,"coverage":0.75,"categories":{"coding":32.9,"reasoning":32.3,"math":31.9,"chat":31.8,"instructions":32.5}},"arena":{"text":{"rank":286,"date":"2026-10-28","rating":1266.1,"lo":1262.2,"hi":1270,"votes":45459,"pct":31.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1276.3,"rank":278,"pct":32.9,"board_size":414},"math":{"rating":1261.5,"rank":276,"pct":31.9,"board_size":405},"creative_writing":{"rating":1242.5,"rank":277,"pct":33.7,"board_size":417},"instruction_following":{"rating":1247.6,"rank":282,"pct":32.5,"board_size":419},"hard_prompts":{"rating":1256.3,"rank":284,"pct":32.3,"board_size":419},"multi_turn":{"rating":1257.3,"rank":286,"pct":31.5,"board_size":417},"longer_query":{"rating":1257.2,"rank":285,"pct":28.3,"board_size":397},"non_english":{"rating":1236.4,"rank":289,"pct":31.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/mistral-large-2-2407"},{"slug":"mistral-large-2411","name":"Mistral Large (2411)","source_name":"Mistral Large (2411)","base":"Mistral Large","variant":"2411","org":"mistral","open_weights":true,"model_license":"MRL","siscope":{"score":32.1,"rank":264,"coverage":0.75,"categories":{"coding":32.4,"reasoning":32.8,"math":31.7,"chat":31.6,"instructions":33.3}},"arena":{"text":{"rank":287,"date":"2026-10-28","rating":1265.3,"lo":1260.9,"hi":1269.7,"votes":28073,"pct":31.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1275.2,"rank":280,"pct":32.4,"board_size":414},"math":{"rating":1261.1,"rank":277,"pct":31.7,"board_size":405},"creative_writing":{"rating":1241.5,"rank":279,"pct":33.2,"board_size":417},"instruction_following":{"rating":1248.6,"rank":280,"pct":33.3,"board_size":419},"hard_prompts":{"rating":1256.6,"rank":282,"pct":32.8,"board_size":419},"multi_turn":{"rating":1259.6,"rank":285,"pct":31.7,"board_size":417},"longer_query":{"rating":1261.2,"rank":281,"pct":29.3,"board_size":397},"non_english":{"rating":1235.1,"rank":293,"pct":30.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"mistralai/mistral-large","input_per_m":2,"output_per_m":6,"blended_per_m":3,"context_length":128000,"modalities_in":["text","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/mistral-large-2411"},{"slug":"athene-70b-0725","name":"Athene 70B (0725)","source_name":"Athene 70B (0725)","base":"Athene 70B","variant":"0725","org":"other","open_weights":true,"model_license":"CC-BY-NC-4.0","siscope":{"score":29.3,"rank":280,"coverage":0.75,"categories":{"coding":30.5,"reasoning":29.9,"math":27.7,"chat":31.3,"instructions":29.2}},"arena":{"text":{"rank":288,"date":"2026-10-28","rating":1265.1,"lo":1259.5,"hi":1270.8,"votes":19621,"pct":31.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1266.7,"rank":288,"pct":30.5,"board_size":414},"math":{"rating":1231.3,"rank":293,"pct":27.7,"board_size":405},"creative_writing":{"rating":1238,"rank":283,"pct":32.2,"board_size":417},"instruction_following":{"rating":1226.6,"rank":297,"pct":29.2,"board_size":419},"hard_prompts":{"rating":1243,"rank":294,"pct":29.9,"board_size":419},"multi_turn":{"rating":1257.2,"rank":287,"pct":31.2,"board_size":417},"longer_query":{"rating":1231.8,"rank":300,"pct":24.5,"board_size":397},"non_english":{"rating":1234.6,"rank":294,"pct":29.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/athene-70b-0725"},{"slug":"gpt-4-turbo-preview-1106","name":"GPT-4 Turbo Preview (1106)","source_name":"GPT-4 Turbo Preview (1106)","base":"GPT-4 Turbo Preview","variant":"1106","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":30.2,"rank":277,"coverage":0.75,"categories":{"coding":29.1,"reasoning":29.4,"math":33.7,"chat":31.1,"instructions":31.1}},"arena":{"text":{"rank":289,"date":"2026-10-28","rating":1263.4,"lo":1259.6,"hi":1267.3,"votes":100105,"pct":31.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1253.7,"rank":294,"pct":29.1,"board_size":414},"math":{"rating":1269.2,"rank":269,"pct":33.7,"board_size":405},"creative_writing":{"rating":1244,"rank":275,"pct":33.9,"board_size":417},"instruction_following":{"rating":1240.5,"rank":289,"pct":31.1,"board_size":419},"hard_prompts":{"rating":1241.1,"rank":295,"pct":29.4,"board_size":419},"multi_turn":{"rating":1256.7,"rank":288,"pct":31,"board_size":417},"longer_query":{"rating":1235.7,"rank":298,"pct":25,"board_size":397},"non_english":{"rating":1245.6,"rank":283,"pct":32.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gpt-4-turbo-preview-1106"},{"slug":"hunyuan-large-vision","name":"Hunyuan Large Vision","source_name":"Hunyuan Large Vision","base":"Hunyuan Large Vision","variant":null,"org":"tencent","open_weights":false,"model_license":"Proprietary","siscope":{"score":33.6,"rank":256,"coverage":0.75,"categories":{"coding":38.5,"reasoning":32.5,"math":33.2,"chat":30.9,"instructions":34}},"arena":{"text":{"rank":290,"date":"2026-10-28","rating":1262.9,"lo":1253.6,"hi":1272.1,"votes":5279,"pct":30.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":104,"date":"2026-10-19","rating":1179.9,"lo":1163.5,"hi":1196.3,"votes":1274,"pct":38,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1308,"rank":255,"pct":38.5,"board_size":414},"math":{"rating":1268,"rank":271,"pct":33.2,"board_size":405},"creative_writing":{"rating":1247.3,"rank":273,"pct":34.6,"board_size":417},"instruction_following":{"rating":1250.5,"rank":277,"pct":34,"board_size":419},"hard_prompts":{"rating":1256.4,"rank":283,"pct":32.5,"board_size":419},"multi_turn":{"rating":1253.2,"rank":291,"pct":30.3,"board_size":417},"longer_query":{"rating":1279.3,"rank":269,"pct":32.3,"board_size":397},"non_english":{"rating":1235.9,"rank":291,"pct":30.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/hunyuan-large-vision"},{"slug":"gpt-4-turbo-preview-0125","name":"GPT-4 Turbo Preview (0125)","source_name":"GPT-4 Turbo Preview (0125)","base":"GPT-4 Turbo Preview","variant":"0125","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":29.6,"rank":279,"coverage":0.75,"categories":{"coding":28.6,"reasoning":28.9,"math":32.9,"chat":30.6,"instructions":29.9}},"arena":{"text":{"rank":291,"date":"2026-10-28","rating":1262.2,"lo":1258.1,"hi":1266.3,"votes":93439,"pct":30.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1248.9,"rank":296,"pct":28.6,"board_size":414},"math":{"rating":1267.8,"rank":272,"pct":32.9,"board_size":405},"creative_writing":{"rating":1232.1,"rank":292,"pct":30,"board_size":417},"instruction_following":{"rating":1234.8,"rank":294,"pct":29.9,"board_size":419},"hard_prompts":{"rating":1238.4,"rank":298,"pct":28.9,"board_size":419},"multi_turn":{"rating":1250.4,"rank":295,"pct":29.3,"board_size":417},"longer_query":{"rating":1243.5,"rank":294,"pct":26,"board_size":397},"non_english":{"rating":1240.7,"rank":286,"pct":31.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gpt-4-turbo-preview-0125"},{"slug":"claude-3-opus-20240229","name":"Claude 3 Opus (2024-02-29)","source_name":"Claude 3 Opus (20240229)","base":"Claude 3 Opus","variant":"2024-02-29","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":23.9,"rank":304,"coverage":0.75,"categories":{"coding":30,"reasoning":18.5,"math":22.5,"chat":30.4,"instructions":33}},"arena":{"text":{"rank":292,"date":"2026-10-28","rating":1262,"lo":1258.9,"hi":1265,"votes":194909,"pct":30.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":144,"date":"2026-10-19","rating":1022.9,"lo":1012.6,"hi":1033.3,"votes":15565,"pct":13.9,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1263.9,"rank":290,"pct":30,"board_size":414},"math":{"rating":1272.5,"rank":263,"pct":35.1,"board_size":405},"creative_writing":{"rating":1234.5,"rank":288,"pct":31,"board_size":417},"instruction_following":{"rating":1248.1,"rank":281,"pct":33,"board_size":419},"hard_prompts":{"rating":1245.3,"rank":293,"pct":30.1,"board_size":419},"multi_turn":{"rating":1275.3,"rank":272,"pct":34.9,"board_size":417},"longer_query":{"rating":1258.8,"rank":284,"pct":28.5,"board_size":397},"non_english":{"rating":1257.6,"rank":273,"pct":34.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.4716,"stderr":0.0264,"tested_as":"claude-3-opus-20240229","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FhTnDa4gn8RYduCEYqoNywe.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":20.2,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.126,"stderr":0.0105,"tested_as":"claude-3-opus-20240229","approx":false,"run_date":"2026-08-31","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FNxVp4VF8uQbL5S6hx6HFRB.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":5.1,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.0472,"stderr":0.0196,"tested_as":"claude-3-opus-20240229","approx":false,"run_date":"2025-02-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FmYb9MGQD39RS8VdDyMqujr.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":9.9,"tested_models":313}],"price":null,"url":"https://siscope.app/models/claude-3-opus-20240229"},{"slug":"llama-3-1-70b-instruct","name":"Llama 3.1 70B Instruct","source_name":"Llama 3.1 70B Instruct","base":"Llama 3.1 70B Instruct","variant":null,"org":"meta","open_weights":true,"model_license":"Llama 3.1 Community","siscope":{"score":24.2,"rank":303,"coverage":0.75,"categories":{"coding":29.5,"reasoning":23.3,"math":19.2,"chat":30.1,"instructions":29.4}},"arena":{"text":{"rank":293,"date":"2026-10-28","rating":1260.9,"lo":1257.2,"hi":1264.6,"votes":55240,"pct":30.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1259.4,"rank":292,"pct":29.5,"board_size":414},"math":{"rating":1251.6,"rank":280,"pct":30.7,"board_size":405},"creative_writing":{"rating":1231.6,"rank":293,"pct":29.8,"board_size":417},"instruction_following":{"rating":1231.1,"rank":296,"pct":29.4,"board_size":419},"hard_prompts":{"rating":1241.1,"rank":296,"pct":29.4,"board_size":419},"multi_turn":{"rating":1256.1,"rank":289,"pct":30.8,"board_size":417},"longer_query":{"rating":1240.6,"rank":296,"pct":25.5,"board_size":397},"non_english":{"rating":1219.1,"rank":298,"pct":28.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.4419,"stderr":0.0245,"tested_as":"Llama-3.1-70B-Instruct","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FMEwMcmSV32JHrsNoAq4BFL.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":17.2,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.0361,"stderr":0.0169,"tested_as":"Llama-3.1-70B-Instruct","approx":false,"run_date":"2025-02-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FX2tQXGELXtEbc2VX6gARd7.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":7.7,"tested_models":313}],"price":{"openrouter_id":"meta-llama/llama-3.1-70b-instruct","input_per_m":0.72,"output_per_m":0.72,"blended_per_m":0.72,"context_length":131072,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/llama-3-1-70b-instruct"},{"slug":"amazon-nova-pro-1-0","name":"Amazon Nova Pro 1.0","source_name":"Amazon Nova Pro 1.0","base":"Amazon Nova Pro 1.0","variant":null,"org":"amazon","open_weights":false,"model_license":"Proprietary","siscope":{"score":30.7,"rank":273,"coverage":0.75,"categories":{"coding":32,"reasoning":30.4,"math":30.7,"chat":29.9,"instructions":30.1}},"arena":{"text":{"rank":294,"date":"2026-10-28","rating":1258.7,"lo":1254.1,"hi":1263.2,"votes":24745,"pct":29.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":155,"date":"2026-10-19","rating":980.5,"lo":966.6,"hi":994.3,"votes":2335,"pct":7.2,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1269.6,"rank":282,"pct":32,"board_size":414},"math":{"rating":1251.6,"rank":281,"pct":30.7,"board_size":405},"creative_writing":{"rating":1212,"rank":300,"pct":28.1,"board_size":417},"instruction_following":{"rating":1235.1,"rank":293,"pct":30.1,"board_size":419},"hard_prompts":{"rating":1245.4,"rank":292,"pct":30.4,"board_size":419},"multi_turn":{"rating":1245.5,"rank":296,"pct":29.1,"board_size":417},"longer_query":{"rating":1254.6,"rank":287,"pct":27.8,"board_size":397},"non_english":{"rating":1233.4,"rank":295,"pct":29.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/amazon-nova-pro-1-0"},{"slug":"llama-3-1-tulu-3-70b","name":"Llama 3.1 Tulu 3 70B","source_name":"Llama 3.1 Tulu 3 70B","base":"Llama 3.1 Tulu 3 70B","variant":null,"org":"allenai","open_weights":true,"model_license":"Llama 3.1","siscope":{"score":28.2,"rank":284,"coverage":0.75,"categories":{"coding":27.4,"reasoning":28.5,"math":29.2,"chat":29.7,"instructions":29.7}},"arena":{"text":{"rank":295,"date":"2026-10-28","rating":1255.7,"lo":1245.2,"hi":1266.2,"votes":2846,"pct":29.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1235.1,"rank":301,"pct":27.4,"board_size":414},"math":{"rating":1241.9,"rank":287,"pct":29.2,"board_size":405},"creative_writing":{"rating":1231,"rank":294,"pct":29.6,"board_size":417},"instruction_following":{"rating":1232.4,"rank":295,"pct":29.7,"board_size":419},"hard_prompts":{"rating":1219.9,"rank":300,"pct":28.5,"board_size":419},"multi_turn":{"rating":1251.6,"rank":293,"pct":29.8,"board_size":417},"longer_query":{"rating":1224,"rank":307,"pct":22.7,"board_size":397},"non_english":{"rating":1235.5,"rank":292,"pct":30.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/llama-3-1-tulu-3-70b"},{"slug":"claude-3-5-haiku-20241022","name":"Claude 3.5 Haiku (2024-10-22)","source_name":"Claude 3.5 Haiku (20241022)","base":"Claude 3.5 Haiku","variant":"2024-10-22","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":25.1,"rank":296,"coverage":0.75,"categories":{"coding":34.1,"reasoning":22,"math":19.1,"chat":29.4,"instructions":31.1}},"arena":{"text":{"rank":296,"date":"2026-10-28","rating":1255.4,"lo":1252.2,"hi":1258.6,"votes":69056,"pct":29.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":132,"date":"2026-10-19","rating":1092.5,"lo":1076.5,"hi":1108.6,"votes":1398,"pct":21.1,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1286.1,"rank":273,"pct":34.1,"board_size":414},"math":{"rating":1243.8,"rank":286,"pct":29.5,"board_size":405},"creative_writing":{"rating":1232.3,"rank":291,"pct":30.3,"board_size":417},"instruction_following":{"rating":1240.5,"rank":288,"pct":31.1,"board_size":419},"hard_prompts":{"rating":1250.8,"rank":289,"pct":30.9,"board_size":419},"multi_turn":{"rating":1265.1,"rank":283,"pct":32.2,"board_size":417},"longer_query":{"rating":1260.3,"rank":282,"pct":29,"board_size":397},"non_english":{"rating":1237.8,"rank":287,"pct":31.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.3813,"stderr":0.0264,"tested_as":"claude-3-5-haiku-20241022","approx":false,"run_date":"2025-03-12","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FJpLxrpvthx7A75sbaHZ9Et.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":13,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.0431,"stderr":0.0162,"tested_as":"claude-3-5-haiku-20241022","approx":false,"run_date":"2025-02-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FcqhrR5KnwpcuAVpHkZGQFd.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":8.7,"tested_models":313}],"price":null,"url":"https://siscope.app/models/claude-3-5-haiku-20241022"},{"slug":"magistral-medium-2506","name":"Magistral Medium (2506)","source_name":"Magistral Medium (2506)","base":"Magistral Medium","variant":"2506","org":"mistral","open_weights":false,"model_license":"Proprietary","siscope":{"score":33.6,"rank":257,"coverage":0.75,"categories":{"coding":40.9,"reasoning":34.7,"math":30,"chat":29.2,"instructions":34.7}},"arena":{"text":{"rank":297,"date":"2026-10-28","rating":1254.8,"lo":1248.4,"hi":1261.3,"votes":11513,"pct":29.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1318.8,"rank":245,"pct":40.9,"board_size":414},"math":{"rating":1249.9,"rank":284,"pct":30,"board_size":405},"creative_writing":{"rating":1244.8,"rank":274,"pct":34.4,"board_size":417},"instruction_following":{"rating":1253.5,"rank":273,"pct":34.7,"board_size":419},"hard_prompts":{"rating":1266.8,"rank":274,"pct":34.7,"board_size":419},"multi_turn":{"rating":1274.8,"rank":273,"pct":34.4,"board_size":417},"longer_query":{"rating":1294.1,"rank":255,"pct":35.9,"board_size":397},"non_english":{"rating":1232.1,"rank":296,"pct":29.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/magistral-medium-2506"},{"slug":"reka-core-20240904","name":"Reka Core (2024-09-04)","source_name":"Reka Core (20240904)","base":"Reka Core","variant":"2024-09-04","org":"other","open_weights":false,"model_license":"Proprietary","siscope":{"score":26.8,"rank":287,"coverage":0.75,"categories":{"coding":26.4,"reasoning":26.8,"math":26.5,"chat":28.9,"instructions":27.8}},"arena":{"text":{"rank":298,"date":"2026-10-28","rating":1248.4,"lo":1241.3,"hi":1255.5,"votes":7312,"pct":28.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1229.7,"rank":305,"pct":26.4,"board_size":414},"math":{"rating":1221.7,"rank":298,"pct":26.5,"board_size":405},"creative_writing":{"rating":1235.9,"rank":286,"pct":31.5,"board_size":417},"instruction_following":{"rating":1211.7,"rank":303,"pct":27.8,"board_size":419},"hard_prompts":{"rating":1210.8,"rank":307,"pct":26.8,"board_size":419},"multi_turn":{"rating":1226.6,"rank":301,"pct":27.9,"board_size":417},"longer_query":{"rating":1220.1,"rank":308,"pct":22.5,"board_size":397},"non_english":{"rating":1236.4,"rank":288,"pct":31.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/reka-core-20240904"},{"slug":"granite-4-0-h-small","name":"Granite 4.0 H-Small","source_name":"Granite-4.0-H-Small","base":"Granite 4.0 H-Small","variant":null,"org":"ibm","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":29,"rank":281,"coverage":0.75,"categories":{"coding":28.3,"reasoning":29.2,"math":31.2,"chat":28.7,"instructions":28.7}},"arena":{"text":{"rank":299,"date":"2026-10-28","rating":1241.3,"lo":1232.9,"hi":1249.7,"votes":5630,"pct":28.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1248.7,"rank":297,"pct":28.3,"board_size":414},"math":{"rating":1252.2,"rank":279,"pct":31.2,"board_size":405},"creative_writing":{"rating":1209.8,"rank":302,"pct":27.6,"board_size":417},"instruction_following":{"rating":1221.9,"rank":299,"pct":28.7,"board_size":419},"hard_prompts":{"rating":1240.4,"rank":297,"pct":29.2,"board_size":419},"multi_turn":{"rating":1242.7,"rank":297,"pct":28.8,"board_size":417},"longer_query":{"rating":1241.7,"rank":295,"pct":25.8,"board_size":397},"non_english":{"rating":1216.1,"rank":301,"pct":28.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/granite-4-0-h-small"},{"slug":"gemini-1-5-flash-001","name":"Gemini 1.5 Flash (001)","source_name":"Gemini 1.5 Flash (001)","base":"Gemini 1.5 Flash","variant":"001","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":27.5,"rank":285,"coverage":0.75,"categories":{"coding":27.6,"reasoning":27.8,"math":27,"chat":28.5,"instructions":28}},"arena":{"text":{"rank":300,"date":"2026-10-28","rating":1239.3,"lo":1234.8,"hi":1243.7,"votes":62833,"pct":28.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":147,"date":"2026-10-19","rating":1008,"lo":996.1,"hi":1019.8,"votes":13260,"pct":12,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1235.4,"rank":300,"pct":27.6,"board_size":414},"math":{"rating":1228.6,"rank":296,"pct":27,"board_size":405},"creative_writing":{"rating":1221.8,"rank":296,"pct":29.1,"board_size":417},"instruction_following":{"rating":1211.8,"rank":302,"pct":28,"board_size":419},"hard_prompts":{"rating":1219.5,"rank":302,"pct":27.8,"board_size":419},"multi_turn":{"rating":1227.5,"rank":298,"pct":28.6,"board_size":417},"longer_query":{"rating":1251.4,"rank":290,"pct":27,"board_size":397},"non_english":{"rating":1230.4,"rank":297,"pct":29.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemini-1-5-flash-001"},{"slug":"jamba-1-5-large","name":"Jamba 1.5 Large","source_name":"Jamba 1.5 Large","base":"Jamba 1.5 Large","variant":null,"org":"other","open_weights":true,"model_license":"Jamba Open","siscope":{"score":26.6,"rank":289,"coverage":0.75,"categories":{"coding":25.9,"reasoning":27.3,"math":26.2,"chat":28.2,"instructions":28.2}},"arena":{"text":{"rank":301,"date":"2026-10-28","rating":1237,"lo":1229.7,"hi":1244.3,"votes":8662,"pct":28.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1227.2,"rank":307,"pct":25.9,"board_size":414},"math":{"rating":1221,"rank":299,"pct":26.2,"board_size":405},"creative_writing":{"rating":1211.4,"rank":301,"pct":27.9,"board_size":417},"instruction_following":{"rating":1212.5,"rank":301,"pct":28.2,"board_size":419},"hard_prompts":{"rating":1217.5,"rank":305,"pct":27.3,"board_size":419},"multi_turn":{"rating":1219.9,"rank":306,"pct":26.7,"board_size":417},"longer_query":{"rating":1206.1,"rank":315,"pct":20.7,"board_size":397},"non_english":{"rating":1196.2,"rank":314,"pct":25.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/jamba-1-5-large"},{"slug":"mistral-small-24b-instruct-2501","name":"Mistral Small 24B Instruct (2501)","source_name":"Mistral Small 24B Instruct (2501)","base":"Mistral Small 24B Instruct","variant":"2501","org":"mistral","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":28.3,"rank":283,"coverage":0.75,"categories":{"coding":28.1,"reasoning":28.7,"math":28.7,"chat":28,"instructions":28.5}},"arena":{"text":{"rank":302,"date":"2026-10-28","rating":1233.5,"lo":1227.7,"hi":1239.4,"votes":14681,"pct":28,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1245.4,"rank":298,"pct":28.1,"board_size":414},"math":{"rating":1240.2,"rank":289,"pct":28.7,"board_size":405},"creative_writing":{"rating":1194.4,"rank":314,"pct":24.8,"board_size":417},"instruction_following":{"rating":1213.8,"rank":300,"pct":28.5,"board_size":419},"hard_prompts":{"rating":1233,"rank":299,"pct":28.7,"board_size":419},"multi_turn":{"rating":1216.6,"rank":309,"pct":26,"board_size":417},"longer_query":{"rating":1245.6,"rank":293,"pct":26.3,"board_size":397},"non_english":{"rating":1198,"rank":312,"pct":25.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/mistral-small-24b-instruct-2501"},{"slug":"gemma-2-27b-it","name":"Gemma 2 27B IT","source_name":"Gemma 2 27B IT","base":"Gemma 2 27B IT","variant":null,"org":"google","open_weights":true,"model_license":"Gemma license","siscope":{"score":19.6,"rank":321,"coverage":0.75,"categories":{"coding":24.7,"reasoning":18.4,"math":14,"chat":27.8,"instructions":27.5}},"arena":{"text":{"rank":303,"date":"2026-10-28","rating":1231.4,"lo":1228,"hi":1234.7,"votes":75754,"pct":27.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1210.6,"rank":312,"pct":24.7,"board_size":414},"math":{"rating":1212,"rank":306,"pct":24.5,"board_size":405},"creative_writing":{"rating":1240.3,"rank":281,"pct":32.7,"board_size":417},"instruction_following":{"rating":1205.9,"rank":304,"pct":27.5,"board_size":419},"hard_prompts":{"rating":1198.2,"rank":314,"pct":25.1,"board_size":419},"multi_turn":{"rating":1223.7,"rank":302,"pct":27.6,"board_size":417},"longer_query":{"rating":1230.2,"rank":301,"pct":24.2,"board_size":397},"non_english":{"rating":1216.9,"rank":299,"pct":28.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.3649,"stderr":0.0239,"tested_as":"gemma-2-27b-it","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FZUJxsJDpHnLXxNiDcvj22W.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":11.7,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.0139,"stderr":0.0091,"tested_as":"gemma-2-27b-it","approx":false,"run_date":"2025-03-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FjD6rJdvfNPErKEz9qkpssj.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":3.5,"tested_models":313}],"price":null,"url":"https://siscope.app/models/gemma-2-27b-it"},{"slug":"qwen2-5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","source_name":"Qwen2.5-Coder-32B-Instruct","base":"Qwen2.5 Coder 32B Instruct","variant":null,"org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":30,"rank":278,"coverage":0.75,"categories":{"coding":32.7,"reasoning":31.3,"math":30.2,"chat":27.5,"instructions":28.9}},"arena":{"text":{"rank":304,"date":"2026-10-28","rating":1230,"lo":1222,"hi":1238.1,"votes":5432,"pct":27.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1275.4,"rank":279,"pct":32.7,"board_size":414},"math":{"rating":1250.5,"rank":283,"pct":30.2,"board_size":405},"creative_writing":{"rating":1173.6,"rank":323,"pct":22.6,"board_size":417},"instruction_following":{"rating":1222.6,"rank":298,"pct":28.9,"board_size":419},"hard_prompts":{"rating":1251.1,"rank":288,"pct":31.3,"board_size":419},"multi_turn":{"rating":1222.3,"rank":304,"pct":27.2,"board_size":417},"longer_query":{"rating":1250.5,"rank":291,"pct":26.8,"board_size":397},"non_english":{"rating":1204.5,"rank":310,"pct":26.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"qwen/qwen-2.5-coder-32b-instruct","input_per_m":0.66,"output_per_m":1,"blended_per_m":0.745,"context_length":32768,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/qwen2-5-coder-32b-instruct"},{"slug":"command-r-08-2024","name":"Command R+ (08-2024)","source_name":"Command R+ (08-2024)","base":"Command R+","variant":"08-2024","org":"cohere","open_weights":true,"model_license":"CC-BY-NC-4.0","siscope":{"score":22.7,"rank":310,"coverage":0.75,"categories":{"coding":21.5,"reasoning":23.2,"math":22,"chat":27.3,"instructions":25.1}},"arena":{"text":{"rank":305,"date":"2026-10-28","rating":1228.9,"lo":1222.3,"hi":1235.4,"votes":9866,"pct":27.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1186.8,"rank":325,"pct":21.5,"board_size":414},"math":{"rating":1187.8,"rank":316,"pct":22,"board_size":405},"creative_writing":{"rating":1234.4,"rank":289,"pct":30.8,"board_size":417},"instruction_following":{"rating":1196.6,"rank":314,"pct":25.1,"board_size":419},"hard_prompts":{"rating":1185.4,"rank":322,"pct":23.2,"board_size":419},"multi_turn":{"rating":1212.7,"rank":311,"pct":25.5,"board_size":417},"longer_query":{"rating":1230,"rank":302,"pct":24,"board_size":397},"non_english":{"rating":1216.3,"rank":300,"pct":28.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"cohere/command-r-08-2024","input_per_m":0.15,"output_per_m":0.6,"blended_per_m":0.2625,"context_length":128000,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/command-r-08-2024"},{"slug":"amazon-nova-lite-1-0","name":"Amazon Nova Lite 1.0","source_name":"Amazon Nova Lite 1.0","base":"Amazon Nova Lite 1.0","variant":null,"org":"amazon","open_weights":false,"model_license":"Proprietary","siscope":{"score":27.3,"rank":286,"coverage":0.75,"categories":{"coding":27.8,"reasoning":28.2,"math":26.7,"chat":27,"instructions":27.3}},"arena":{"text":{"rank":306,"date":"2026-10-28","rating":1228.5,"lo":1223.3,"hi":1233.6,"votes":19372,"pct":27,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":152,"date":"2026-10-19","rating":990.4,"lo":975.5,"hi":1005.4,"votes":1854,"pct":9,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1238.5,"rank":299,"pct":27.8,"board_size":414},"math":{"rating":1226.6,"rank":297,"pct":26.7,"board_size":405},"creative_writing":{"rating":1196.6,"rank":313,"pct":25,"board_size":417},"instruction_following":{"rating":1204.9,"rank":305,"pct":27.3,"board_size":419},"hard_prompts":{"rating":1219.7,"rank":301,"pct":28.2,"board_size":419},"multi_turn":{"rating":1198.6,"rank":314,"pct":24.8,"board_size":417},"longer_query":{"rating":1233.5,"rank":299,"pct":24.7,"board_size":397},"non_english":{"rating":1208,"rank":305,"pct":27.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/amazon-nova-lite-1-0"},{"slug":"llama-3-1-nemotron-51b-instruct","name":"Llama 3.1 Nemotron 51B Instruct","source_name":"Llama 3.1 Nemotron 51B Instruct","base":"Llama 3.1 Nemotron 51B Instruct","variant":null,"org":"nvidia","open_weights":true,"model_license":"Llama 3.1","siscope":{"score":26.1,"rank":291,"coverage":0.75,"categories":{"coding":25.7,"reasoning":25.8,"math":27.2,"chat":26.8,"instructions":25.8}},"arena":{"text":{"rank":307,"date":"2026-10-28","rating":1228,"lo":1218,"hi":1237.9,"votes":3749,"pct":26.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1222.7,"rank":308,"pct":25.7,"board_size":414},"math":{"rating":1229.9,"rank":295,"pct":27.2,"board_size":405},"creative_writing":{"rating":1212.9,"rank":299,"pct":28.4,"board_size":417},"instruction_following":{"rating":1200.6,"rank":311,"pct":25.8,"board_size":419},"hard_prompts":{"rating":1203.3,"rank":311,"pct":25.8,"board_size":419},"multi_turn":{"rating":1226.9,"rank":299,"pct":28.4,"board_size":417},"longer_query":{"rating":1204.9,"rank":317,"pct":20.2,"board_size":397},"non_english":{"rating":1180.4,"rank":320,"pct":23.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/llama-3-1-nemotron-51b-instruct"},{"slug":"gemma-2-9b-it-simpo","name":"Gemma 2 9B IT SimPO","source_name":"Gemma 2 9B IT SimPO","base":"Gemma 2 9B IT SimPO","variant":null,"org":"other","open_weights":true,"model_license":"MIT","siscope":{"score":22.3,"rank":313,"coverage":0.75,"categories":{"coding":22.3,"reasoning":24.6,"math":19.8,"chat":26.6,"instructions":24.4}},"arena":{"text":{"rank":308,"date":"2026-10-28","rating":1227,"lo":1220.2,"hi":1233.9,"votes":10072,"pct":26.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1190.6,"rank":322,"pct":22.3,"board_size":414},"math":{"rating":1172.7,"rank":325,"pct":19.8,"board_size":405},"creative_writing":{"rating":1238.5,"rank":282,"pct":32.5,"board_size":417},"instruction_following":{"rating":1190.9,"rank":317,"pct":24.4,"board_size":419},"hard_prompts":{"rating":1196,"rank":316,"pct":24.6,"board_size":419},"multi_turn":{"rating":1219.7,"rank":307,"pct":26.4,"board_size":417},"longer_query":{"rating":1225.9,"rank":304,"pct":23.5,"board_size":397},"non_english":{"rating":1206.2,"rank":307,"pct":26.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemma-2-9b-it-simpo"},{"slug":"glm-4-0520","name":"GLM-4 (0520)","source_name":"GLM-4 (0520)","base":"GLM-4","variant":"0520","org":"zai","open_weights":false,"model_license":"Proprietary","siscope":{"score":26.3,"rank":290,"coverage":0.75,"categories":{"coding":26.2,"reasoning":27,"math":26,"chat":26.3,"instructions":26.8}},"arena":{"text":{"rank":309,"date":"2026-10-28","rating":1225.9,"lo":1219,"hi":1232.8,"votes":9788,"pct":26.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1227.3,"rank":306,"pct":26.2,"board_size":414},"math":{"rating":1218,"rank":300,"pct":26,"board_size":405},"creative_writing":{"rating":1197.6,"rank":312,"pct":25.2,"board_size":417},"instruction_following":{"rating":1202.6,"rank":307,"pct":26.8,"board_size":419},"hard_prompts":{"rating":1211.8,"rank":306,"pct":27,"board_size":419},"multi_turn":{"rating":1217.9,"rank":308,"pct":26.2,"board_size":417},"longer_query":{"rating":1206.4,"rank":314,"pct":21,"board_size":397},"non_english":{"rating":1199.5,"rank":311,"pct":25.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/glm-4-0520"},{"slug":"gemini-1-5-flash-8b-001","name":"Gemini 1.5 Flash-8B (001)","source_name":"Gemini 1.5 Flash-8B (001)","base":"Gemini 1.5 Flash-8B","variant":"001","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":25,"rank":297,"coverage":0.75,"categories":{"coding":24.9,"reasoning":26.6,"math":24,"chat":26.1,"instructions":25.4}},"arena":{"text":{"rank":310,"date":"2026-10-28","rating":1225.8,"lo":1221.6,"hi":1230.1,"votes":35558,"pct":26.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":143,"date":"2026-10-19","rating":1044.1,"lo":1033.5,"hi":1054.7,"votes":6243,"pct":14.5,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1217.3,"rank":311,"pct":24.9,"board_size":414},"math":{"rating":1206.6,"rank":308,"pct":24,"board_size":405},"creative_writing":{"rating":1217.2,"rank":298,"pct":28.6,"board_size":417},"instruction_following":{"rating":1198.9,"rank":313,"pct":25.4,"board_size":419},"hard_prompts":{"rating":1209.3,"rank":308,"pct":26.6,"board_size":419},"multi_turn":{"rating":1185.2,"rank":321,"pct":23.1,"board_size":417},"longer_query":{"rating":1218.3,"rank":310,"pct":22,"board_size":397},"non_english":{"rating":1214.5,"rank":302,"pct":28,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemini-1-5-flash-8b-001"},{"slug":"nemotron-4-340b-instruct","name":"Nemotron-4 340B Instruct","source_name":"Nemotron-4 340B Instruct","base":"Nemotron-4 340B Instruct","variant":null,"org":"nvidia","open_weights":true,"model_license":"NVIDIA Open Model","siscope":{"score":24.9,"rank":298,"coverage":0.75,"categories":{"coding":24.2,"reasoning":25.6,"math":25.2,"chat":25.8,"instructions":27}},"arena":{"text":{"rank":311,"date":"2026-10-28","rating":1224.8,"lo":1219.5,"hi":1230.1,"votes":19659,"pct":25.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1209,"rank":314,"pct":24.2,"board_size":414},"math":{"rating":1216,"rank":303,"pct":25.2,"board_size":405},"creative_writing":{"rating":1202.2,"rank":306,"pct":26.7,"board_size":417},"instruction_following":{"rating":1203,"rank":306,"pct":27,"board_size":419},"hard_prompts":{"rating":1201.4,"rank":312,"pct":25.6,"board_size":419},"multi_turn":{"rating":1213.7,"rank":310,"pct":25.7,"board_size":417},"longer_query":{"rating":1224.3,"rank":305,"pct":23.2,"board_size":397},"non_english":{"rating":1205.9,"rank":308,"pct":26.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/nemotron-4-340b-instruct"},{"slug":"aya-expanse-32b","name":"Aya Expanse 32B","source_name":"Aya Expanse 32B","base":"Aya Expanse 32B","variant":null,"org":"cohere","open_weights":true,"model_license":"CC-BY-NC-4.0","siscope":{"score":23.6,"rank":307,"coverage":0.75,"categories":{"coding":23,"reasoning":24.2,"math":23.3,"chat":25.6,"instructions":24.9}},"arena":{"text":{"rank":312,"date":"2026-10-28","rating":1224,"lo":1219.1,"hi":1228.8,"votes":27124,"pct":25.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1196.3,"rank":319,"pct":23,"board_size":414},"math":{"rating":1199.8,"rank":311,"pct":23.3,"board_size":405},"creative_writing":{"rating":1199.5,"rank":310,"pct":25.7,"board_size":417},"instruction_following":{"rating":1195.9,"rank":315,"pct":24.9,"board_size":419},"hard_prompts":{"rating":1193,"rank":318,"pct":24.2,"board_size":419},"multi_turn":{"rating":1190,"rank":318,"pct":23.8,"board_size":417},"longer_query":{"rating":1227.2,"rank":303,"pct":23.7,"board_size":397},"non_english":{"rating":1213.3,"rank":303,"pct":27.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/aya-expanse-32b"},{"slug":"llama-3-70b-instruct","name":"Llama 3 70B Instruct","source_name":"Llama 3 70B Instruct","base":"Llama 3 70B Instruct","variant":null,"org":"meta","open_weights":true,"model_license":"Llama 3 Community","siscope":{"score":24.4,"rank":302,"coverage":0.75,"categories":{"coding":23.7,"reasoning":24.4,"math":25.7,"chat":25.4,"instructions":24.6}},"arena":{"text":{"rank":313,"date":"2026-10-28","rating":1220.8,"lo":1217.2,"hi":1224.4,"votes":156876,"pct":25.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1205.8,"rank":316,"pct":23.7,"board_size":414},"math":{"rating":1217.9,"rank":301,"pct":25.7,"board_size":405},"creative_writing":{"rating":1209.4,"rank":303,"pct":27.4,"board_size":417},"instruction_following":{"rating":1194,"rank":316,"pct":24.6,"board_size":419},"hard_prompts":{"rating":1194.7,"rank":317,"pct":24.4,"board_size":419},"multi_turn":{"rating":1222.9,"rank":303,"pct":27.4,"board_size":417},"longer_query":{"rating":1173.7,"rank":330,"pct":16.9,"board_size":397},"non_english":{"rating":1141.6,"rank":336,"pct":19.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/llama-3-70b-instruct"},{"slug":"claude-3-sonnet-20240229","name":"Claude 3 Sonnet (2024-02-29)","source_name":"Claude 3 Sonnet (20240229)","base":"Claude 3 Sonnet","variant":"2024-02-29","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":20.2,"rank":319,"coverage":0.75,"categories":{"coding":25.4,"reasoning":19.7,"math":15.3,"chat":25.1,"instructions":25.6}},"arena":{"text":{"rank":314,"date":"2026-10-28","rating":1218,"lo":1214.1,"hi":1222,"votes":109284,"pct":25.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":154,"date":"2026-10-19","rating":983.9,"lo":972.5,"hi":995.3,"votes":12314,"pct":7.8,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1222.4,"rank":309,"pct":25.4,"board_size":414},"math":{"rating":1213.4,"rank":305,"pct":24.8,"board_size":405},"creative_writing":{"rating":1185.9,"rank":318,"pct":23.8,"board_size":417},"instruction_following":{"rating":1199.2,"rank":312,"pct":25.6,"board_size":419},"hard_prompts":{"rating":1196.9,"rank":315,"pct":24.9,"board_size":419},"multi_turn":{"rating":1226.8,"rank":300,"pct":28.1,"board_size":417},"longer_query":{"rating":1210.7,"rank":313,"pct":21.2,"board_size":397},"non_english":{"rating":1205,"rank":309,"pct":26.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.4059,"stderr":0.0239,"tested_as":"claude-3-sonnet-20240229","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FQLejPZXhjX6SQCQgzjNvCG.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":14.5,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.025,"stderr":0.0195,"tested_as":"claude-3-sonnet-20240229","approx":false,"run_date":"2025-02-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FAeRCEiG87bMFpxbxbmjCyn.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":5.8,"tested_models":313}],"price":null,"url":"https://siscope.app/models/claude-3-sonnet-20240229"},{"slug":"olmo-2-32b-instruct-0325","name":"OLMo 2 32B Instruct (0325)","source_name":"OLMo 2 32B Instruct (0325)","base":"OLMo 2 32B Instruct","variant":"0325","org":"allenai","open_weights":true,"model_license":"Apache-2.0","siscope":{"score":24.7,"rank":300,"coverage":0.75,"categories":{"coding":24.5,"reasoning":26.3,"math":24.3,"chat":24.6,"instructions":23.9}},"arena":{"text":{"rank":315,"date":"2026-10-28","rating":1217.9,"lo":1207.1,"hi":1228.7,"votes":3334,"pct":24.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1209.8,"rank":313,"pct":24.5,"board_size":414},"math":{"rating":1207.6,"rank":307,"pct":24.3,"board_size":405},"creative_writing":{"rating":1198.2,"rank":311,"pct":25.5,"board_size":417},"instruction_following":{"rating":1185.8,"rank":319,"pct":23.9,"board_size":419},"hard_prompts":{"rating":1207.6,"rank":309,"pct":26.3,"board_size":419},"multi_turn":{"rating":1221.2,"rank":305,"pct":26.9,"board_size":417},"longer_query":{"rating":1193.8,"rank":321,"pct":19.2,"board_size":397},"non_english":{"rating":1160.1,"rank":329,"pct":21.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/olmo-2-32b-instruct-0325"},{"slug":"reka-flash-20240904","name":"Reka Flash (2024-09-04)","source_name":"Reka Flash (20240904)","base":"Reka Flash","variant":"2024-09-04","org":"other","open_weights":false,"model_license":"Proprietary","siscope":{"score":22.7,"rank":309,"coverage":0.75,"categories":{"coding":22,"reasoning":23,"math":23,"chat":24.6,"instructions":23.7}},"arena":{"text":{"rank":316,"date":"2026-10-28","rating":1217.9,"lo":1211,"hi":1224.8,"votes":7536,"pct":24.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1189.7,"rank":323,"pct":22,"board_size":414},"math":{"rating":1195.3,"rank":312,"pct":23,"board_size":405},"creative_writing":{"rating":1201.9,"rank":307,"pct":26.4,"board_size":417},"instruction_following":{"rating":1185.2,"rank":320,"pct":23.7,"board_size":419},"hard_prompts":{"rating":1181.3,"rank":323,"pct":23,"board_size":419},"multi_turn":{"rating":1188.8,"rank":320,"pct":23.3,"board_size":417},"longer_query":{"rating":1191.4,"rank":323,"pct":18.7,"board_size":397},"non_english":{"rating":1207,"rank":306,"pct":27,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/reka-flash-20240904"},{"slug":"phi-4","name":"Phi-4","source_name":"Phi-4","base":"Phi-4","variant":null,"org":"microsoft","open_weights":true,"model_license":"MIT","siscope":{"score":25.7,"rank":295,"coverage":0.75,"categories":{"coding":27.1,"reasoning":28.8,"math":23.5,"chat":24.4,"instructions":26.3}},"arena":{"text":{"rank":317,"date":"2026-10-28","rating":1216.7,"lo":1212.1,"hi":1221.2,"votes":24126,"pct":24.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1231,"rank":302,"pct":27.1,"board_size":414},"math":{"rating":1245.8,"rank":285,"pct":29.7,"board_size":405},"creative_writing":{"rating":1181.3,"rank":319,"pct":23.6,"board_size":417},"instruction_following":{"rating":1201.1,"rank":309,"pct":26.3,"board_size":419},"hard_prompts":{"rating":1219.5,"rank":303,"pct":27.8,"board_size":419},"multi_turn":{"rating":1205.9,"rank":313,"pct":25,"board_size":417},"longer_query":{"rating":1217,"rank":311,"pct":21.7,"board_size":397},"non_english":{"rating":1196.6,"rank":313,"pct":25.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.5606,"stderr":0.0259,"tested_as":"phi-4","approx":false,"run_date":"2025-01-31","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FRAwuPRwJedy7P2KeQhEmr8.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":29.8,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.1375,"stderr":0.037,"tested_as":"phi-4","approx":false,"run_date":"2025-02-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F5mmrBSQb7hVSJ9VYtNm46i.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":17.3,"tested_models":313}],"price":{"openrouter_id":"microsoft/phi-4","input_per_m":0.07,"output_per_m":0.14,"blended_per_m":0.0875,"context_length":16384,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/phi-4"},{"slug":"amazon-nova-micro-1-0","name":"Amazon Nova Micro 1.0","source_name":"Amazon Nova Micro 1.0","base":"Amazon Nova Micro 1.0","variant":null,"org":"amazon","open_weights":false,"model_license":"Proprietary","siscope":{"score":23.7,"rank":306,"coverage":0.75,"categories":{"coding":25.2,"reasoning":23.7,"math":23.8,"chat":24.2,"instructions":22.2}},"arena":{"text":{"rank":318,"date":"2026-10-28","rating":1208.4,"lo":1203.2,"hi":1213.6,"votes":19364,"pct":24.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1217.4,"rank":310,"pct":25.2,"board_size":414},"math":{"rating":1206.1,"rank":309,"pct":23.8,"board_size":405},"creative_writing":{"rating":1171.5,"rank":324,"pct":22.4,"board_size":417},"instruction_following":{"rating":1174,"rank":326,"pct":22.2,"board_size":419},"hard_prompts":{"rating":1191,"rank":320,"pct":23.7,"board_size":419},"multi_turn":{"rating":1177.9,"rank":323,"pct":22.6,"board_size":417},"longer_query":{"rating":1205.2,"rank":316,"pct":20.5,"board_size":397},"non_english":{"rating":1186.2,"rank":318,"pct":24.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/amazon-nova-micro-1-0"},{"slug":"gemma-2-9b-it","name":"Gemma 2 9B IT","source_name":"Gemma 2 9B IT","base":"Gemma 2 9B IT","variant":null,"org":"google","open_weights":true,"model_license":"Gemma license","siscope":{"score":15.7,"rank":339,"coverage":0.75,"categories":{"coding":20.1,"reasoning":13.3,"math":11.2,"chat":23.9,"instructions":22.7}},"arena":{"text":{"rank":319,"date":"2026-10-28","rating":1207.4,"lo":1203.6,"hi":1211.2,"votes":54611,"pct":23.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1173.2,"rank":331,"pct":20.1,"board_size":414},"math":{"rating":1183.2,"rank":319,"pct":21.3,"board_size":405},"creative_writing":{"rating":1205.3,"rank":305,"pct":26.9,"board_size":417},"instruction_following":{"rating":1178,"rank":324,"pct":22.7,"board_size":419},"hard_prompts":{"rating":1171.3,"rank":328,"pct":21.8,"board_size":419},"multi_turn":{"rating":1193.4,"rank":316,"pct":24.3,"board_size":417},"longer_query":{"rating":1196.3,"rank":320,"pct":19.4,"board_size":397},"non_english":{"rating":1187.7,"rank":317,"pct":24.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.2746,"stderr":0.023,"tested_as":"gemma-2-9b-it","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FfQjoHKyUEPAuwdrBGfL8SG.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":4.8,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.0056,"stderr":0.0039,"tested_as":"gemma-2-9b-it","approx":false,"run_date":"2025-03-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FWNE7cveVN8rsi7DmsFsFVy.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":1,"tested_models":313}],"price":null,"url":"https://siscope.app/models/gemma-2-9b-it"},{"slug":"gpt-4-0314","name":"GPT-4 (0314)","source_name":"GPT-4 (0314)","base":"GPT-4","variant":"0314","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":24.8,"rank":299,"coverage":0.75,"categories":{"coding":24,"reasoning":25.4,"math":27.5,"chat":23.7,"instructions":26.1}},"arena":{"text":{"rank":320,"date":"2026-10-28","rating":1206,"lo":1201.3,"hi":1210.7,"votes":54173,"pct":23.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1208.4,"rank":315,"pct":24,"board_size":414},"math":{"rating":1230.1,"rank":294,"pct":27.5,"board_size":405},"creative_writing":{"rating":1189.9,"rank":316,"pct":24.3,"board_size":417},"instruction_following":{"rating":1200.9,"rank":310,"pct":26.1,"board_size":419},"hard_prompts":{"rating":1200,"rank":313,"pct":25.4,"board_size":419},"multi_turn":{"rating":1205.9,"rank":312,"pct":25,"board_size":417},"longer_query":{"rating":1190,"rank":326,"pct":17.9,"board_size":397},"non_english":{"rating":1194.1,"rank":315,"pct":24.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gpt-4-0314"},{"slug":"command-r","name":"Command R+","source_name":"Command R+","base":"Command R+","variant":null,"org":"cohere","open_weights":true,"model_license":"CC-BY-NC-4.0","siscope":{"score":20.3,"rank":318,"coverage":0.75,"categories":{"coding":19.9,"reasoning":20.8,"math":19.1,"chat":23.4,"instructions":23}},"arena":{"text":{"rank":321,"date":"2026-10-28","rating":1203.8,"lo":1199.5,"hi":1208.1,"votes":77554,"pct":23.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1171.5,"rank":332,"pct":19.9,"board_size":414},"math":{"rating":1164.4,"rank":328,"pct":19.1,"board_size":405},"creative_writing":{"rating":1200.7,"rank":308,"pct":26.2,"board_size":417},"instruction_following":{"rating":1179.5,"rank":323,"pct":23,"board_size":419},"hard_prompts":{"rating":1166.4,"rank":332,"pct":20.8,"board_size":419},"multi_turn":{"rating":1192.2,"rank":317,"pct":24,"board_size":417},"longer_query":{"rating":1201.3,"rank":318,"pct":19.9,"board_size":397},"non_english":{"rating":1189.4,"rank":316,"pct":24.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"cohere/command-r-08-2024","input_per_m":0.15,"output_per_m":0.6,"blended_per_m":0.2625,"context_length":128000,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/command-r"},{"slug":"qwen2-72b-instruct","name":"Qwen2 72B Instruct","source_name":"Qwen2-72B-Instruct","base":"Qwen2 72B Instruct","variant":null,"org":"alibaba","open_weights":true,"model_license":"Qianwen LICENSE","siscope":{"score":22,"rank":314,"coverage":0.75,"categories":{"coding":22.8,"reasoning":19.1,"math":28.2,"chat":23.2,"instructions":23.4}},"arena":{"text":{"rank":322,"date":"2026-10-28","rating":1203.2,"lo":1198.3,"hi":1208.2,"votes":37325,"pct":23.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1195.5,"rank":320,"pct":22.8,"board_size":414},"math":{"rating":1234.8,"rank":291,"pct":28.2,"board_size":405},"creative_writing":{"rating":1180.6,"rank":321,"pct":23.1,"board_size":417},"instruction_following":{"rating":1181,"rank":321,"pct":23.4,"board_size":419},"hard_prompts":{"rating":1190.5,"rank":321,"pct":23.4,"board_size":419},"multi_turn":{"rating":1195.5,"rank":315,"pct":24.5,"board_size":417},"longer_query":{"rating":1192,"rank":322,"pct":18.9,"board_size":397},"non_english":{"rating":1175.8,"rank":324,"pct":22.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.4078,"stderr":0.0257,"tested_as":"qwen2-72b-instruct","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FPex6SpYJX8ZPySncfNNy7H.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":14.8,"tested_models":333}],"price":null,"url":"https://siscope.app/models/qwen2-72b-instruct"},{"slug":"hunyuan-standard-256k","name":"Hunyuan Standard 256K","source_name":"Hunyuan Standard 256K","base":"Hunyuan Standard 256K","variant":null,"org":"tencent","open_weights":false,"model_license":"Proprietary","siscope":{"score":25.8,"rank":293,"coverage":0.75,"categories":{"coding":26.9,"reasoning":27.5,"math":28,"chat":23,"instructions":26.6}},"arena":{"text":{"rank":323,"date":"2026-10-28","rating":1201.9,"lo":1190.3,"hi":1213.5,"votes":2728,"pct":23,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1230.4,"rank":303,"pct":26.9,"board_size":414},"math":{"rating":1234.6,"rank":292,"pct":28,"board_size":405},"creative_writing":{"rating":1164.8,"rank":327,"pct":21.6,"board_size":417},"instruction_following":{"rating":1201.7,"rank":308,"pct":26.6,"board_size":419},"hard_prompts":{"rating":1218,"rank":304,"pct":27.5,"board_size":419},"multi_turn":{"rating":1174.7,"rank":325,"pct":22.1,"board_size":417},"longer_query":{"rating":1224.2,"rank":306,"pct":23,"board_size":397},"non_english":{"rating":1178.4,"rank":322,"pct":23.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/hunyuan-standard-256k"},{"slug":"claude-3-haiku-20240307","name":"Claude 3 Haiku (2024-03-07)","source_name":"Claude 3 Haiku (20240307)","base":"Claude 3 Haiku","variant":"2024-03-07","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":17.8,"rank":330,"coverage":0.75,"categories":{"coding":23.2,"reasoning":16.7,"math":13.3,"chat":22.7,"instructions":22}},"arena":{"text":{"rank":324,"date":"2026-10-28","rating":1194.7,"lo":1190.9,"hi":1198.4,"votes":117701,"pct":22.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":159,"date":"2026-10-19","rating":950.2,"lo":937.6,"hi":962.7,"votes":13380,"pct":4.8,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1198.7,"rank":318,"pct":23.2,"board_size":414},"math":{"rating":1188,"rank":315,"pct":22.3,"board_size":405},"creative_writing":{"rating":1157,"rank":331,"pct":20.7,"board_size":417},"instruction_following":{"rating":1173.2,"rank":327,"pct":22,"board_size":419},"hard_prompts":{"rating":1173.8,"rank":327,"pct":22,"board_size":419},"multi_turn":{"rating":1189.9,"rank":319,"pct":23.6,"board_size":417},"longer_query":{"rating":1190.1,"rank":325,"pct":18.2,"board_size":397},"non_english":{"rating":1177.4,"rank":323,"pct":23,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.363,"stderr":0.0242,"tested_as":"claude-3-haiku-20240307","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FT3FWdCCWBryVjxwTcoY5bK.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":11.4,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.0181,"stderr":0.0081,"tested_as":"claude-3-haiku-20240307","approx":false,"run_date":"2025-02-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FThMd6DNDTtyWxhPcb9Kq4y.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":4.2,"tested_models":313}],"price":null,"url":"https://siscope.app/models/claude-3-haiku-20240307"},{"slug":"llama-3-1-tulu-3-8b","name":"Llama 3.1 Tulu 3 8B","source_name":"Llama 3.1 Tulu 3 8B","base":"Llama 3.1 Tulu 3 8B","variant":null,"org":"allenai","open_weights":true,"model_license":"Llama 3.1","siscope":{"score":21.6,"rank":315,"coverage":0.75,"categories":{"coding":20.8,"reasoning":22.2,"math":22.8,"chat":22.5,"instructions":22.2}},"arena":{"text":{"rank":325,"date":"2026-10-28","rating":1193.3,"lo":1182.8,"hi":1203.8,"votes":2896,"pct":22.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1183.1,"rank":328,"pct":20.8,"board_size":414},"math":{"rating":1194.7,"rank":313,"pct":22.8,"board_size":405},"creative_writing":{"rating":1181.2,"rank":320,"pct":23.3,"board_size":417},"instruction_following":{"rating":1174,"rank":325,"pct":22.2,"board_size":419},"hard_prompts":{"rating":1174.1,"rank":326,"pct":22.2,"board_size":419},"multi_turn":{"rating":1153.6,"rank":334,"pct":20,"board_size":417},"longer_query":{"rating":1180.4,"rank":329,"pct":17.2,"board_size":397},"non_english":{"rating":1168.9,"rank":326,"pct":22.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/llama-3-1-tulu-3-8b"},{"slug":"deepseek-coder-v2","name":"DeepSeek-Coder-V2","source_name":"DeepSeek-Coder-V2","base":"DeepSeek-Coder-V2","variant":null,"org":"deepseek","open_weights":true,"model_license":"DeepSeek License","siscope":{"score":25.7,"rank":294,"coverage":0.75,"categories":{"coding":28.8,"reasoning":26.1,"math":29,"chat":22.2,"instructions":23.2}},"arena":{"text":{"rank":326,"date":"2026-10-28","rating":1191.2,"lo":1184.8,"hi":1197.5,"votes":15147,"pct":22.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1250.7,"rank":295,"pct":28.8,"board_size":414},"math":{"rating":1241.3,"rank":288,"pct":29,"board_size":405},"creative_writing":{"rating":1120,"rank":349,"pct":16.3,"board_size":417},"instruction_following":{"rating":1180.2,"rank":322,"pct":23.2,"board_size":419},"hard_prompts":{"rating":1206.7,"rank":310,"pct":26.1,"board_size":419},"multi_turn":{"rating":1176.5,"rank":324,"pct":22.4,"board_size":417},"longer_query":{"rating":1218.7,"rank":309,"pct":22.2,"board_size":397},"non_english":{"rating":1181.9,"rank":319,"pct":23.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/deepseek-coder-v2"},{"slug":"ministral-8b-2410","name":"Ministral 8B (2410)","source_name":"Ministral 8B (2410)","base":"Ministral 8B","variant":"2410","org":"mistral","open_weights":true,"model_license":"MRL","siscope":{"score":22.6,"rank":311,"coverage":0.75,"categories":{"coding":23.5,"reasoning":23.9,"math":22.5,"chat":22,"instructions":21.3}},"arena":{"text":{"rank":327,"date":"2026-10-28","rating":1190.9,"lo":1181.9,"hi":1199.9,"votes":4781,"pct":22,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1201.6,"rank":317,"pct":23.5,"board_size":414},"math":{"rating":1188.2,"rank":314,"pct":22.5,"board_size":405},"creative_writing":{"rating":1174.5,"rank":322,"pct":22.8,"board_size":417},"instruction_following":{"rating":1160.4,"rank":330,"pct":21.3,"board_size":419},"hard_prompts":{"rating":1191.1,"rank":319,"pct":23.9,"board_size":419},"multi_turn":{"rating":1166.3,"rank":328,"pct":21.4,"board_size":417},"longer_query":{"rating":1211.6,"rank":312,"pct":21.5,"board_size":397},"non_english":{"rating":1164.9,"rank":327,"pct":22,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/ministral-8b-2410"},{"slug":"command-r-08-2024-2","name":"Command R (08-2024)","source_name":"Command R (08-2024)","base":"Command R","variant":"08-2024","org":"cohere","open_weights":true,"model_license":"CC-BY-NC-4.0","siscope":{"score":19.3,"rank":323,"coverage":0.75,"categories":{"coding":19.6,"reasoning":20.6,"math":17.6,"chat":21.8,"instructions":21.5}},"arena":{"text":{"rank":328,"date":"2026-10-28","rating":1187.3,"lo":1180.8,"hi":1193.9,"votes":10140,"pct":21.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1169.1,"rank":333,"pct":19.6,"board_size":414},"math":{"rating":1154.8,"rank":334,"pct":17.6,"board_size":405},"creative_writing":{"rating":1169.6,"rank":325,"pct":22.1,"board_size":417},"instruction_following":{"rating":1166.9,"rank":329,"pct":21.5,"board_size":419},"hard_prompts":{"rating":1164.1,"rank":333,"pct":20.6,"board_size":419},"multi_turn":{"rating":1163,"rank":329,"pct":21.2,"board_size":417},"longer_query":{"rating":1197.3,"rank":319,"pct":19.7,"board_size":397},"non_english":{"rating":1174.2,"rank":325,"pct":22.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"cohere/command-r-08-2024","input_per_m":0.15,"output_per_m":0.6,"blended_per_m":0.2625,"context_length":128000,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/command-r-08-2024-2"},{"slug":"jamba-1-5-mini","name":"Jamba 1.5 Mini","source_name":"Jamba 1.5 Mini","base":"Jamba 1.5 Mini","variant":null,"org":"other","open_weights":true,"model_license":"Jamba Open","siscope":{"score":19.9,"rank":320,"coverage":0.75,"categories":{"coding":20.3,"reasoning":21.1,"math":18.6,"chat":21.5,"instructions":19.9}},"arena":{"text":{"rank":329,"date":"2026-10-28","rating":1186.7,"lo":1179.5,"hi":1193.8,"votes":8858,"pct":21.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1178,"rank":330,"pct":20.3,"board_size":414},"math":{"rating":1160.2,"rank":330,"pct":18.6,"board_size":405},"creative_writing":{"rating":1164.1,"rank":328,"pct":21.4,"board_size":417},"instruction_following":{"rating":1147.9,"rank":336,"pct":19.9,"board_size":419},"hard_prompts":{"rating":1166.7,"rank":331,"pct":21.1,"board_size":419},"multi_turn":{"rating":1156.9,"rank":333,"pct":20.2,"board_size":417},"longer_query":{"rating":1156.4,"rank":337,"pct":15.2,"board_size":397},"non_english":{"rating":1134.6,"rank":339,"pct":19.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/jamba-1-5-mini"},{"slug":"llama-3-1-8b-instruct","name":"Llama 3.1 8B Instruct","source_name":"Llama 3.1 8B Instruct","base":"Llama 3.1 8B Instruct","variant":null,"org":"meta","open_weights":true,"model_license":"Llama 3.1 Community","siscope":{"score":16.3,"rank":336,"coverage":0.75,"categories":{"coding":22.5,"reasoning":13.3,"math":12.1,"chat":21.3,"instructions":21.1}},"arena":{"text":{"rank":330,"date":"2026-10-28","rating":1186.6,"lo":1182.5,"hi":1190.7,"votes":49605,"pct":21.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1194.5,"rank":321,"pct":22.5,"board_size":414},"math":{"rating":1179.2,"rank":323,"pct":20.3,"board_size":405},"creative_writing":{"rating":1154,"rank":332,"pct":20.2,"board_size":417},"instruction_following":{"rating":1158.8,"rank":331,"pct":21.1,"board_size":419},"hard_prompts":{"rating":1174.6,"rank":324,"pct":22.7,"board_size":419},"multi_turn":{"rating":1172,"rank":327,"pct":21.6,"board_size":417},"longer_query":{"rating":1181.3,"rank":328,"pct":17.4,"board_size":397},"non_english":{"rating":1147.9,"rank":331,"pct":21.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.2696,"stderr":0.0186,"tested_as":"Llama-3.1-8B-Instruct","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FfxwRTtt8bLV4DNutwtMEox.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":3.9,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.0167,"stderr":0.0094,"tested_as":"Llama-3.1-8B-Instruct","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F6YAzFq89fwWiJ3uJdptCMr.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":3.8,"tested_models":313}],"price":{"openrouter_id":"meta-llama/llama-3.1-8b-instruct","input_per_m":0.05,"output_per_m":0.08,"blended_per_m":0.0575,"context_length":131072,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/llama-3-1-8b-instruct"},{"slug":"gpt-4-0613","name":"GPT-4 (0613)","source_name":"GPT-4 (0613)","base":"GPT-4","variant":"0613","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":22.4,"rank":312,"coverage":0.75,"categories":{"coding":21.8,"reasoning":22.5,"math":25.5,"chat":21.1,"instructions":24.2}},"arena":{"text":{"rank":331,"date":"2026-10-28","rating":1186,"lo":1182,"hi":1190,"votes":88723,"pct":21.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1187.1,"rank":324,"pct":21.8,"board_size":414},"math":{"rating":1217,"rank":302,"pct":25.5,"board_size":405},"creative_writing":{"rating":1191.1,"rank":315,"pct":24.5,"board_size":417},"instruction_following":{"rating":1188.4,"rank":318,"pct":24.2,"board_size":419},"hard_prompts":{"rating":1174.2,"rank":325,"pct":22.5,"board_size":419},"multi_turn":{"rating":1184.7,"rank":322,"pct":22.8,"board_size":417},"longer_query":{"rating":1187.6,"rank":327,"pct":17.7,"board_size":397},"non_english":{"rating":1160.4,"rank":328,"pct":21.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gpt-4-0613"},{"slug":"aya-expanse-8b","name":"Aya Expanse 8B","source_name":"Aya Expanse 8B","base":"Aya Expanse 8B","variant":null,"org":"cohere","open_weights":true,"model_license":"CC-BY-NC-4.0","siscope":{"score":19.1,"rank":325,"coverage":0.75,"categories":{"coding":18.2,"reasoning":19.6,"math":19.6,"chat":20.8,"instructions":20.3}},"arena":{"text":{"rank":332,"date":"2026-10-28","rating":1185.1,"lo":1178.2,"hi":1192,"votes":9818,"pct":20.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1160.2,"rank":339,"pct":18.2,"board_size":414},"math":{"rating":1168.1,"rank":326,"pct":19.6,"board_size":405},"creative_writing":{"rating":1167.8,"rank":326,"pct":21.9,"board_size":417},"instruction_following":{"rating":1154.7,"rank":334,"pct":20.3,"board_size":419},"hard_prompts":{"rating":1155.8,"rank":337,"pct":19.6,"board_size":419},"multi_turn":{"rating":1159.6,"rank":332,"pct":20.4,"board_size":417},"longer_query":{"rating":1191.1,"rank":324,"pct":18.4,"board_size":397},"non_english":{"rating":1179.9,"rank":321,"pct":23.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/aya-expanse-8b"},{"slug":"mistral-large-2402","name":"Mistral Large (2402)","source_name":"Mistral Large (2402)","base":"Mistral Large","variant":"2402","org":"mistral","open_weights":false,"model_license":"Proprietary","siscope":{"score":21.2,"rank":316,"coverage":0.75,"categories":{"coding":20.6,"reasoning":21.3,"math":23.3,"chat":20.6,"instructions":21.8}},"arena":{"text":{"rank":333,"date":"2026-10-28","rating":1176.5,"lo":1171.8,"hi":1181.1,"votes":62436,"pct":20.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1182.7,"rank":329,"pct":20.6,"board_size":414},"math":{"rating":1199.8,"rank":310,"pct":23.3,"board_size":405},"creative_writing":{"rating":1160.8,"rank":329,"pct":21.2,"board_size":417},"instruction_following":{"rating":1169.1,"rank":328,"pct":21.8,"board_size":419},"hard_prompts":{"rating":1167,"rank":330,"pct":21.3,"board_size":419},"multi_turn":{"rating":1172,"rank":326,"pct":21.6,"board_size":417},"longer_query":{"rating":1172.8,"rank":331,"pct":16.7,"board_size":397},"non_english":{"rating":1142,"rank":334,"pct":20.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"mistralai/mistral-large","input_per_m":2,"output_per_m":6,"blended_per_m":3,"context_length":128000,"modalities_in":["text","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/mistral-large-2402"},{"slug":"qwen1-5-110b-chat","name":"Qwen1.5 110B Chat","source_name":"Qwen1.5-110B-Chat","base":"Qwen1.5 110B Chat","variant":null,"org":"alibaba","open_weights":true,"model_license":"Qianwen LICENSE","siscope":{"score":21,"rank":317,"coverage":0.75,"categories":{"coding":21.1,"reasoning":21.5,"math":21.8,"chat":20.3,"instructions":20.8}},"arena":{"text":{"rank":334,"date":"2026-10-28","rating":1174.5,"lo":1169,"hi":1180.1,"votes":26195,"pct":20.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1183.6,"rank":327,"pct":21.1,"board_size":414},"math":{"rating":1185.4,"rank":317,"pct":21.8,"board_size":405},"creative_writing":{"rating":1147.6,"rank":336,"pct":19.5,"board_size":417},"instruction_following":{"rating":1157.7,"rank":332,"pct":20.8,"board_size":419},"hard_prompts":{"rating":1167.8,"rank":329,"pct":21.5,"board_size":419},"multi_turn":{"rating":1159.7,"rank":331,"pct":20.7,"board_size":417},"longer_query":{"rating":1156.8,"rank":335,"pct":15.7,"board_size":397},"non_english":{"rating":1141.8,"rank":335,"pct":20.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen1-5-110b-chat"},{"slug":"yi-1-5-34b-chat","name":"Yi 1.5 34B Chat","source_name":"Yi 1.5 34B Chat","base":"Yi 1.5 34B Chat","variant":null,"org":"other","open_weights":true,"model_license":"Apache-2.0","siscope":{"score":17.3,"rank":333,"coverage":0.75,"categories":{"coding":19.4,"reasoning":14.1,"math":21,"chat":20.1,"instructions":19.1}},"arena":{"text":{"rank":335,"date":"2026-10-28","rating":1172.9,"lo":1167.9,"hi":1177.9,"votes":24146,"pct":20.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1169,"rank":334,"pct":19.4,"board_size":414},"math":{"rating":1182,"rank":320,"pct":21,"board_size":405},"creative_writing":{"rating":1134.8,"rank":340,"pct":18.5,"board_size":417},"instruction_following":{"rating":1139.1,"rank":339,"pct":19.1,"board_size":419},"hard_prompts":{"rating":1159.7,"rank":335,"pct":20.1,"board_size":419},"multi_turn":{"rating":1153.1,"rank":335,"pct":19.7,"board_size":417},"longer_query":{"rating":1143.2,"rank":343,"pct":13.6,"board_size":397},"non_english":{"rating":1120.9,"rank":343,"pct":18.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.3198,"stderr":0.02,"tested_as":"Yi-1.5-34B-Chat","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FJwi8JTeeTxJuJY8qidxngw.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":8.1,"tested_models":333}],"price":null,"url":"https://siscope.app/models/yi-1-5-34b-chat"},{"slug":"reka-flash-21b-online-20240226","name":"Reka Flash 21B (Online, 2024-02-26)","source_name":"Reka Flash 21B (Online, 20240226)","base":"Reka Flash 21B","variant":"Online, 2024-02-26","org":"other","open_weights":false,"model_license":"Proprietary","siscope":{"score":18.6,"rank":328,"coverage":0.75,"categories":{"coding":18.6,"reasoning":18.2,"math":19.3,"chat":19.9,"instructions":18.4}},"arena":{"text":{"rank":336,"date":"2026-10-28","rating":1170.4,"lo":1163.1,"hi":1177.7,"votes":15450,"pct":19.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1164.2,"rank":337,"pct":18.6,"board_size":414},"math":{"rating":1168,"rank":327,"pct":19.3,"board_size":405},"creative_writing":{"rating":1130.2,"rank":342,"pct":18,"board_size":417},"instruction_following":{"rating":1129.3,"rank":342,"pct":18.4,"board_size":419},"hard_prompts":{"rating":1136.8,"rank":343,"pct":18.2,"board_size":419},"multi_turn":{"rating":1151,"rank":337,"pct":19.2,"board_size":417},"longer_query":{"rating":1139,"rank":345,"pct":13.1,"board_size":397},"non_english":{"rating":1154.9,"rank":330,"pct":21.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/reka-flash-21b-online-20240226"},{"slug":"qwen1-5-72b-chat","name":"Qwen1.5 72B Chat","source_name":"Qwen1.5-72B-Chat","base":"Qwen1.5 72B Chat","variant":null,"org":"alibaba","open_weights":true,"model_license":"Qianwen LICENSE","siscope":{"score":16.1,"rank":337,"coverage":0.75,"categories":{"coding":18.9,"reasoning":12.5,"math":18.8,"chat":19.6,"instructions":19.4}},"arena":{"text":{"rank":337,"date":"2026-10-28","rating":1166.1,"lo":1160.9,"hi":1171.3,"votes":39302,"pct":19.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1165.1,"rank":336,"pct":18.9,"board_size":414},"math":{"rating":1163.7,"rank":329,"pct":18.8,"board_size":405},"creative_writing":{"rating":1136.8,"rank":339,"pct":18.8,"board_size":417},"instruction_following":{"rating":1141.2,"rank":338,"pct":19.4,"board_size":419},"hard_prompts":{"rating":1147.7,"rank":340,"pct":18.9,"board_size":419},"multi_turn":{"rating":1159.9,"rank":330,"pct":20.9,"board_size":417},"longer_query":{"rating":1156.7,"rank":336,"pct":15.4,"board_size":397},"non_english":{"rating":1134.9,"rank":338,"pct":19.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.2882,"stderr":0.0199,"tested_as":"qwen1.5-72b-chat","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FNeqeQSxHmdUNLk9Ytpo6qo.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":6,"tested_models":333}],"price":null,"url":"https://siscope.app/models/qwen1-5-72b-chat"},{"slug":"llama-3-8b-instruct","name":"Llama 3 8B Instruct","source_name":"Llama 3 8B Instruct","base":"Llama 3 8B Instruct","variant":null,"org":"meta","open_weights":true,"model_license":"Llama 3 Community","siscope":{"score":17.3,"rank":332,"coverage":0.75,"categories":{"coding":16.9,"reasoning":17.7,"math":16.8,"chat":19.4,"instructions":18.2}},"arena":{"text":{"rank":338,"date":"2026-10-28","rating":1165.6,"lo":1161.9,"hi":1169.3,"votes":104642,"pct":19.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1151.3,"rank":344,"pct":16.9,"board_size":414},"math":{"rating":1151.2,"rank":337,"pct":16.8,"board_size":405},"creative_writing":{"rating":1149.5,"rank":334,"pct":20,"board_size":417},"instruction_following":{"rating":1127,"rank":343,"pct":18.2,"board_size":419},"hard_prompts":{"rating":1133.1,"rank":345,"pct":17.7,"board_size":419},"multi_turn":{"rating":1152.4,"rank":336,"pct":19.5,"board_size":417},"longer_query":{"rating":1127.4,"rank":348,"pct":12.4,"board_size":397},"non_english":{"rating":1097.4,"rank":350,"pct":16.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/llama-3-8b-instruct"},{"slug":"mistral-medium","name":"Mistral Medium","source_name":"Mistral Medium","base":"Mistral Medium","variant":null,"org":"mistral","open_weights":false,"model_license":"Proprietary","siscope":{"score":19.1,"rank":326,"coverage":0.75,"categories":{"coding":18.4,"reasoning":19.1,"math":20.8,"chat":19.1,"instructions":20.1}},"arena":{"text":{"rank":339,"date":"2026-10-28","rating":1165.1,"lo":1159.7,"hi":1170.5,"votes":34550,"pct":19.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1161.8,"rank":338,"pct":18.4,"board_size":414},"math":{"rating":1179.8,"rank":321,"pct":20.8,"board_size":405},"creative_writing":{"rating":1157.4,"rank":330,"pct":20.9,"board_size":417},"instruction_following":{"rating":1151.6,"rank":335,"pct":20.1,"board_size":419},"hard_prompts":{"rating":1149.1,"rank":339,"pct":19.1,"board_size":419},"multi_turn":{"rating":1147.2,"rank":339,"pct":18.8,"board_size":417},"longer_query":{"rating":1153.2,"rank":339,"pct":14.6,"board_size":397},"non_english":{"rating":1128.5,"rank":341,"pct":18.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/mistral-medium"},{"slug":"reka-flash-21b-20240226","name":"Reka Flash 21B (2024-02-26)","source_name":"Reka Flash 21B (20240226)","base":"Reka Flash 21B","variant":"2024-02-26","org":"other","open_weights":false,"model_license":"Proprietary","siscope":{"score":17.7,"rank":331,"coverage":0.75,"categories":{"coding":17.2,"reasoning":17.9,"math":18.1,"chat":18.9,"instructions":17.7}},"arena":{"text":{"rank":340,"date":"2026-10-28","rating":1165,"lo":1159.1,"hi":1170.9,"votes":24806,"pct":18.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1153.4,"rank":343,"pct":17.2,"board_size":414},"math":{"rating":1155.5,"rank":332,"pct":18.1,"board_size":405},"creative_writing":{"rating":1123.5,"rank":347,"pct":16.8,"board_size":417},"instruction_following":{"rating":1121.3,"rank":345,"pct":17.7,"board_size":419},"hard_prompts":{"rating":1136.4,"rank":344,"pct":17.9,"board_size":419},"multi_turn":{"rating":1141.5,"rank":340,"pct":18.5,"board_size":417},"longer_query":{"rating":1140.5,"rank":344,"pct":13.4,"board_size":397},"non_english":{"rating":1145.7,"rank":332,"pct":20.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/reka-flash-21b-20240226"},{"slug":"command-r-2","name":"Command R","source_name":"Command R","base":"Command R","variant":null,"org":"cohere","open_weights":true,"model_license":"CC-BY-NC-4.0","siscope":{"score":15.1,"rank":344,"coverage":0.75,"categories":{"coding":15,"reasoning":16.3,"math":13.4,"chat":18.7,"instructions":17.9}},"arena":{"text":{"rank":341,"date":"2026-10-28","rating":1163.1,"lo":1158.4,"hi":1167.8,"votes":54036,"pct":18.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1127.4,"rank":352,"pct":15,"board_size":414},"math":{"rating":1120,"rank":351,"pct":13.4,"board_size":405},"creative_writing":{"rating":1154,"rank":333,"pct":20.2,"board_size":417},"instruction_following":{"rating":1124.5,"rank":344,"pct":17.9,"board_size":419},"hard_prompts":{"rating":1114.6,"rank":350,"pct":16.3,"board_size":419},"multi_turn":{"rating":1147.5,"rank":338,"pct":19,"board_size":417},"longer_query":{"rating":1157.3,"rank":334,"pct":15.9,"board_size":397},"non_english":{"rating":1143.4,"rank":333,"pct":20.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"cohere/command-r-08-2024","input_per_m":0.15,"output_per_m":0.6,"blended_per_m":0.2625,"context_length":128000,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/command-r-2"},{"slug":"mixtral-8x22b-instruct-v0-1","name":"Mixtral 8x22B Instruct v0.1","source_name":"Mixtral 8x22B Instruct v0.1","base":"Mixtral 8x22B Instruct v0.1","variant":null,"org":"mistral","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":19.3,"rank":324,"coverage":0.75,"categories":{"coding":19.1,"reasoning":19.4,"math":21.5,"chat":18.4,"instructions":19.6}},"arena":{"text":{"rank":342,"date":"2026-10-28","rating":1162,"lo":1157.4,"hi":1166.5,"votes":51416,"pct":18.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1165.3,"rank":335,"pct":19.1,"board_size":414},"math":{"rating":1184.3,"rank":318,"pct":21.5,"board_size":405},"creative_writing":{"rating":1141.1,"rank":338,"pct":19,"board_size":417},"instruction_following":{"rating":1147,"rank":337,"pct":19.6,"board_size":419},"hard_prompts":{"rating":1149.6,"rank":338,"pct":19.4,"board_size":419},"multi_turn":{"rating":1130.1,"rank":345,"pct":17.3,"board_size":417},"longer_query":{"rating":1143.5,"rank":342,"pct":13.9,"board_size":397},"non_english":{"rating":1128.1,"rank":342,"pct":18.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/mixtral-8x22b-instruct-v0-1"},{"slug":"qwq-32b-preview","name":"QwQ-32B-Preview","source_name":"QwQ-32B-Preview","base":"QwQ-32B-Preview","variant":null,"org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":19.5,"rank":322,"coverage":0.75,"categories":{"coding":17.7,"reasoning":20.3,"math":25,"chat":18.2,"instructions":20.6}},"arena":{"text":{"rank":343,"date":"2026-10-28","rating":1161.8,"lo":1150.4,"hi":1173.1,"votes":3231,"pct":18.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1154.9,"rank":341,"pct":17.7,"board_size":414},"math":{"rating":1213.5,"rank":304,"pct":25,"board_size":405},"creative_writing":{"rating":1133.4,"rank":341,"pct":18.3,"board_size":417},"instruction_following":{"rating":1155.8,"rank":333,"pct":20.6,"board_size":419},"hard_prompts":{"rating":1162.4,"rank":334,"pct":20.3,"board_size":419},"multi_turn":{"rating":1140.7,"rank":341,"pct":18.3,"board_size":417},"longer_query":{"rating":1166.5,"rank":332,"pct":16.4,"board_size":397},"non_english":{"rating":1129.5,"rank":340,"pct":18.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwq-32b-preview"},{"slug":"internlm2-5-20b-chat","name":"InternLM2.5 20B Chat","source_name":"InternLM2.5 20B Chat","base":"InternLM2.5 20B Chat","variant":null,"org":"other","open_weights":true,"model_license":"Other","siscope":{"score":18.7,"rank":327,"coverage":0.75,"categories":{"coding":17.9,"reasoning":19.9,"math":20.5,"chat":17.9,"instructions":18.9}},"arena":{"text":{"rank":344,"date":"2026-10-28","rating":1158.4,"lo":1151.4,"hi":1165.5,"votes":9901,"pct":17.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1158.7,"rank":340,"pct":17.9,"board_size":414},"math":{"rating":1179.7,"rank":322,"pct":20.5,"board_size":405},"creative_writing":{"rating":1122.4,"rank":348,"pct":16.6,"board_size":417},"instruction_following":{"rating":1134.9,"rank":340,"pct":18.9,"board_size":419},"hard_prompts":{"rating":1157.9,"rank":336,"pct":19.9,"board_size":419},"multi_turn":{"rating":1135.5,"rank":344,"pct":17.5,"board_size":417},"longer_query":{"rating":1148.9,"rank":340,"pct":14.4,"board_size":397},"non_english":{"rating":1104.2,"rank":347,"pct":17.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/internlm2-5-20b-chat"},{"slug":"gemma-2-2b-it","name":"Gemma 2 2B IT","source_name":"Gemma 2 2B IT","base":"Gemma 2 2B IT","variant":null,"org":"google","open_weights":true,"model_license":"Gemma license","siscope":{"score":14.8,"rank":346,"coverage":0.75,"categories":{"coding":13.6,"reasoning":15.6,"math":14.9,"chat":17.7,"instructions":17}},"arena":{"text":{"rank":345,"date":"2026-10-28","rating":1155.8,"lo":1151.7,"hi":1159.8,"votes":46616,"pct":17.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1112,"rank":358,"pct":13.6,"board_size":414},"math":{"rating":1134.5,"rank":345,"pct":14.9,"board_size":405},"creative_writing":{"rating":1146.5,"rank":337,"pct":19.2,"board_size":417},"instruction_following":{"rating":1117.5,"rank":348,"pct":17,"board_size":419},"hard_prompts":{"rating":1112.4,"rank":354,"pct":15.6,"board_size":419},"multi_turn":{"rating":1118,"rank":347,"pct":16.8,"board_size":417},"longer_query":{"rating":1129.7,"rank":347,"pct":12.6,"board_size":397},"non_english":{"rating":1120.6,"rank":344,"pct":17.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemma-2-2b-it"},{"slug":"granite-3-1-8b-instruct","name":"Granite 3.1 8B Instruct","source_name":"Granite 3.1 8B Instruct","base":"Granite 3.1 8B Instruct","variant":null,"org":"ibm","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":18.6,"rank":329,"coverage":0.75,"categories":{"coding":21.3,"reasoning":18.7,"math":17.1,"chat":17.5,"instructions":18.7}},"arena":{"text":{"rank":346,"date":"2026-10-28","rating":1149.5,"lo":1138.6,"hi":1160.4,"votes":3090,"pct":17.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1186.1,"rank":326,"pct":21.3,"board_size":414},"math":{"rating":1151.5,"rank":336,"pct":17.1,"board_size":405},"creative_writing":{"rating":1128.6,"rank":344,"pct":17.5,"board_size":417},"instruction_following":{"rating":1130.6,"rank":341,"pct":18.7,"board_size":419},"hard_prompts":{"rating":1145.3,"rank":341,"pct":18.7,"board_size":419},"multi_turn":{"rating":1108.1,"rank":355,"pct":14.9,"board_size":417},"longer_query":{"rating":1161.5,"rank":333,"pct":16.2,"board_size":397},"non_english":{"rating":1099.1,"rank":348,"pct":17,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/granite-3-1-8b-instruct"},{"slug":"gemini-pro-dev-api","name":"Gemini Pro (Dev API)","source_name":"Gemini Pro (Dev API)","base":"Gemini Pro","variant":"Dev API","org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":14.1,"rank":347,"coverage":0.75,"categories":{"coding":12.6,"reasoning":15.3,"math":14.6,"chat":17.2,"instructions":16.3}},"arena":{"text":{"rank":347,"date":"2026-10-28","rating":1148.8,"lo":1141.6,"hi":1156,"votes":18354,"pct":17.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1103.7,"rank":362,"pct":12.6,"board_size":414},"math":{"rating":1132,"rank":346,"pct":14.6,"board_size":405},"creative_writing":{"rating":1130.1,"rank":343,"pct":17.8,"board_size":417},"instruction_following":{"rating":1114,"rank":351,"pct":16.3,"board_size":419},"hard_prompts":{"rating":1109.2,"rank":355,"pct":15.3,"board_size":419},"multi_turn":{"rating":1124.2,"rank":346,"pct":17.1,"board_size":417},"longer_query":{"rating":1131.4,"rank":346,"pct":12.9,"board_size":397},"non_english":{"rating":1137.9,"rank":337,"pct":19.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemini-pro-dev-api"},{"slug":"zephyr-orpo-141b-a35b-v0-1","name":"Zephyr ORPO 141B A35B v0.1","source_name":"Zephyr ORPO 141B A35B v0.1","base":"Zephyr ORPO 141B A35B v0.1","variant":null,"org":"other","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":16,"rank":338,"coverage":0.75,"categories":{"coding":15.3,"reasoning":16.7,"math":16.3,"chat":17,"instructions":17.2}},"arena":{"text":{"rank":348,"date":"2026-10-28","rating":1143.7,"lo":1133,"hi":1154.4,"votes":4652,"pct":17,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1128.9,"rank":351,"pct":15.3,"board_size":414},"math":{"rating":1147.8,"rank":339,"pct":16.3,"board_size":405},"creative_writing":{"rating":1112.8,"rank":351,"pct":15.9,"board_size":417},"instruction_following":{"rating":1117.6,"rank":347,"pct":17.2,"board_size":419},"hard_prompts":{"rating":1115.6,"rank":349,"pct":16.7,"board_size":419},"multi_turn":{"rating":1099.6,"rank":357,"pct":14.4,"board_size":417},"longer_query":{"rating":1104.6,"rank":355,"pct":10.6,"board_size":397},"non_english":{"rating":1098,"rank":349,"pct":16.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/zephyr-orpo-141b-a35b-v0-1"},{"slug":"phi-3-medium-4k-instruct","name":"Phi-3 Medium 4K Instruct","source_name":"Phi-3 Medium 4K Instruct","base":"Phi-3 Medium 4K Instruct","variant":null,"org":"microsoft","open_weights":true,"model_license":"MIT","siscope":{"score":16.7,"rank":335,"coverage":0.75,"categories":{"coding":15.5,"reasoning":17.2,"math":20,"chat":16.7,"instructions":16}},"arena":{"text":{"rank":349,"date":"2026-10-28","rating":1137.5,"lo":1132.4,"hi":1142.6,"votes":25055,"pct":16.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1129.8,"rank":350,"pct":15.5,"board_size":414},"math":{"rating":1173.4,"rank":324,"pct":20,"board_size":405},"creative_writing":{"rating":1106.2,"rank":354,"pct":15.1,"board_size":417},"instruction_following":{"rating":1113.3,"rank":352,"pct":16,"board_size":419},"hard_prompts":{"rating":1126.4,"rank":347,"pct":17.2,"board_size":419},"multi_turn":{"rating":1088,"rank":361,"pct":13.5,"board_size":417},"longer_query":{"rating":1119.8,"rank":351,"pct":11.6,"board_size":397},"non_english":{"rating":1093.8,"rank":353,"pct":15.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/phi-3-medium-4k-instruct"},{"slug":"qwen1-5-32b-chat","name":"Qwen1.5 32B Chat","source_name":"Qwen1.5-32B-Chat","base":"Qwen1.5 32B Chat","variant":null,"org":"alibaba","open_weights":true,"model_license":"Qianwen LICENSE","siscope":{"score":15.2,"rank":342,"coverage":0.75,"categories":{"coding":17.4,"reasoning":12.7,"math":17.8,"chat":16.5,"instructions":16.5}},"arena":{"text":{"rank":350,"date":"2026-10-28","rating":1137.2,"lo":1131.1,"hi":1143.2,"votes":21741,"pct":16.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1154.4,"rank":342,"pct":17.4,"board_size":414},"math":{"rating":1155.1,"rank":333,"pct":17.8,"board_size":405},"creative_writing":{"rating":1082.6,"rank":372,"pct":10.8,"board_size":417},"instruction_following":{"rating":1115.4,"rank":350,"pct":16.5,"board_size":419},"hard_prompts":{"rating":1130.3,"rank":346,"pct":17.5,"board_size":419},"multi_turn":{"rating":1139.7,"rank":342,"pct":18,"board_size":417},"longer_query":{"rating":1145.7,"rank":341,"pct":14.1,"board_size":397},"non_english":{"rating":1106.3,"rank":346,"pct":17.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.3074,"stderr":0.0202,"tested_as":"qwen1.5-32b-chat","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F9K6c9b6v9zQrQYtw827BDn.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":7.8,"tested_models":333}],"price":null,"url":"https://siscope.app/models/qwen1-5-32b-chat"},{"slug":"starling-lm-7b-beta","name":"Starling LM 7B Beta","source_name":"Starling LM 7B Beta","base":"Starling LM 7B Beta","variant":null,"org":"other","open_weights":true,"model_license":"Apache-2.0","siscope":{"score":15.3,"rank":341,"coverage":0.75,"categories":{"coding":16.5,"reasoning":17,"math":13.6,"chat":16.3,"instructions":14.6}},"arena":{"text":{"rank":351,"date":"2026-10-28","rating":1132,"lo":1124.7,"hi":1139.3,"votes":16056,"pct":16.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1142.4,"rank":346,"pct":16.5,"board_size":414},"math":{"rating":1124.4,"rank":350,"pct":13.6,"board_size":405},"creative_writing":{"rating":1095.4,"rank":362,"pct":13.2,"board_size":417},"instruction_following":{"rating":1095.6,"rank":358,"pct":14.6,"board_size":419},"hard_prompts":{"rating":1118.3,"rank":348,"pct":17,"board_size":419},"multi_turn":{"rating":1111.2,"rank":351,"pct":15.9,"board_size":417},"longer_query":{"rating":1103.8,"rank":356,"pct":10.4,"board_size":397},"non_english":{"rating":1096.9,"rank":351,"pct":16.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/starling-lm-7b-beta"},{"slug":"mixtral-8x7b-instruct-v0-1","name":"Mixtral 8x7B Instruct v0.1","source_name":"Mixtral 8x7B Instruct v0.1","base":"Mixtral 8x7B Instruct v0.1","variant":null,"org":"mistral","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":13.7,"rank":349,"coverage":0.75,"categories":{"coding":14.8,"reasoning":11.6,"math":16.1,"chat":16,"instructions":15.1}},"arena":{"text":{"rank":352,"date":"2026-10-28","rating":1131.5,"lo":1127.3,"hi":1135.8,"votes":73503,"pct":16,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1126.1,"rank":353,"pct":14.8,"board_size":414},"math":{"rating":1147.1,"rank":340,"pct":16.1,"board_size":405},"creative_writing":{"rating":1108.5,"rank":352,"pct":15.6,"board_size":417},"instruction_following":{"rating":1109.2,"rank":356,"pct":15.1,"board_size":419},"hard_prompts":{"rating":1114.6,"rank":351,"pct":16.3,"board_size":419},"multi_turn":{"rating":1114.6,"rank":349,"pct":16.3,"board_size":417},"longer_query":{"rating":1102.5,"rank":357,"pct":10.1,"board_size":397},"non_english":{"rating":1076.8,"rank":357,"pct":14.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.3059,"stderr":0.0194,"tested_as":"Mixtral-8x7B-Instruct-v0.1","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FSn2qbB2HiySe7NcG28jnyM.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":6.9,"tested_models":333}],"price":null,"url":"https://siscope.app/models/mixtral-8x7b-instruct-v0-1"},{"slug":"gemini-pro","name":"Gemini Pro","source_name":"Gemini Pro","base":"Gemini Pro","variant":null,"org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":13.8,"rank":348,"coverage":0.75,"categories":{"coding":13.1,"reasoning":13.6,"math":14.4,"chat":15.8,"instructions":15.3}},"arena":{"text":{"rank":353,"date":"2026-10-28","rating":1130.5,"lo":1119.1,"hi":1141.9,"votes":6390,"pct":15.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1107.6,"rank":360,"pct":13.1,"board_size":414},"math":{"rating":1128.9,"rank":347,"pct":14.4,"board_size":405},"creative_writing":{"rating":1103.6,"rank":357,"pct":14.4,"board_size":417},"instruction_following":{"rating":1109.8,"rank":355,"pct":15.3,"board_size":419},"hard_prompts":{"rating":1093.7,"rank":362,"pct":13.6,"board_size":419},"multi_turn":{"rating":1139.4,"rank":343,"pct":17.8,"board_size":417},"non_english":{"rating":1093.7,"rank":354,"pct":15.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemini-pro"},{"slug":"yi-34b-chat","name":"Yi 34B Chat","source_name":"Yi 34B Chat","base":"Yi 34B Chat","variant":null,"org":"other","open_weights":true,"model_license":"Yi License","siscope":{"score":11,"rank":360,"coverage":0.75,"categories":{"coding":13.3,"reasoning":7.8,"math":12.6,"chat":15.6,"instructions":13.9}},"arena":{"text":{"rank":354,"date":"2026-10-28","rating":1128.4,"lo":1121.7,"hi":1135.2,"votes":15483,"pct":15.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1111.5,"rank":359,"pct":13.3,"board_size":414},"math":{"rating":1113.6,"rank":354,"pct":12.6,"board_size":405},"creative_writing":{"rating":1107.7,"rank":353,"pct":15.4,"board_size":417},"instruction_following":{"rating":1090.7,"rank":361,"pct":13.9,"board_size":419},"hard_prompts":{"rating":1103.4,"rank":358,"pct":14.6,"board_size":419},"multi_turn":{"rating":1112.8,"rank":350,"pct":16.1,"board_size":417},"longer_query":{"rating":1093.4,"rank":360,"pct":9.3,"board_size":397},"non_english":{"rating":1079.1,"rank":355,"pct":15.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.1474,"stderr":0.0114,"tested_as":"Yi-34B-Chat","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FWxMpEBcTf8qPFPz4BrF86B.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":0.9,"tested_models":333}],"price":null,"url":"https://siscope.app/models/yi-34b-chat"},{"slug":"qwen1-5-14b-chat","name":"Qwen1.5 14B Chat","source_name":"Qwen1.5-14B-Chat","base":"Qwen1.5 14B Chat","variant":null,"org":"alibaba","open_weights":true,"model_license":"Qianwen LICENSE","siscope":{"score":15.1,"rank":345,"coverage":0.75,"categories":{"coding":16.2,"reasoning":16,"math":13.9,"chat":15.3,"instructions":14.8}},"arena":{"text":{"rank":355,"date":"2026-10-28","rating":1127.7,"lo":1120.6,"hi":1134.7,"votes":17839,"pct":15.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1137.5,"rank":347,"pct":16.2,"board_size":414},"math":{"rating":1125.4,"rank":349,"pct":13.9,"board_size":405},"creative_writing":{"rating":1090.2,"rank":366,"pct":12,"board_size":417},"instruction_following":{"rating":1101.5,"rank":357,"pct":14.8,"board_size":419},"hard_prompts":{"rating":1113.1,"rank":352,"pct":16,"board_size":419},"multi_turn":{"rating":1109.8,"rank":353,"pct":15.4,"board_size":417},"longer_query":{"rating":1112.5,"rank":352,"pct":11.4,"board_size":397},"non_english":{"rating":1094.5,"rank":352,"pct":16,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen1-5-14b-chat"},{"slug":"granite-3-1-2b-instruct","name":"Granite 3.1 2B Instruct","source_name":"Granite 3.1 2B Instruct","base":"Granite 3.1 2B Instruct","variant":null,"org":"ibm","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":16.7,"rank":334,"coverage":0.75,"categories":{"coding":16.7,"reasoning":18.4,"math":18.3,"chat":15.1,"instructions":16.7}},"arena":{"text":{"rank":356,"date":"2026-10-28","rating":1127.4,"lo":1116.3,"hi":1138.4,"votes":3188,"pct":15.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1149,"rank":345,"pct":16.7,"board_size":414},"math":{"rating":1159.2,"rank":331,"pct":18.3,"board_size":405},"creative_writing":{"rating":1115.7,"rank":350,"pct":16.1,"board_size":417},"instruction_following":{"rating":1115.8,"rank":349,"pct":16.7,"board_size":419},"hard_prompts":{"rating":1137.9,"rank":342,"pct":18.4,"board_size":419},"multi_turn":{"rating":1099.4,"rank":358,"pct":14.2,"board_size":417},"longer_query":{"rating":1154.7,"rank":338,"pct":14.9,"board_size":397},"non_english":{"rating":1068.1,"rank":363,"pct":13.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/granite-3-1-2b-instruct"},{"slug":"gpt-3-5-turbo-0125","name":"GPT-3.5 Turbo (0125)","source_name":"GPT-3.5 Turbo (0125)","base":"GPT-3.5 Turbo","variant":"0125","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":15.4,"rank":340,"coverage":0.75,"categories":{"coding":16,"reasoning":15.1,"math":15.3,"chat":14.8,"instructions":17.5}},"arena":{"text":{"rank":357,"date":"2026-10-28","rating":1124.9,"lo":1120.2,"hi":1129.6,"votes":66207,"pct":14.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1136.1,"rank":348,"pct":16,"board_size":414},"math":{"rating":1141.7,"rank":343,"pct":15.3,"board_size":405},"creative_writing":{"rating":1092.1,"rank":365,"pct":12.5,"board_size":417},"instruction_following":{"rating":1118.5,"rank":346,"pct":17.5,"board_size":419},"hard_prompts":{"rating":1107.8,"rank":356,"pct":15.1,"board_size":419},"multi_turn":{"rating":1116.8,"rank":348,"pct":16.6,"board_size":417},"longer_query":{"rating":1120.5,"rank":350,"pct":11.9,"board_size":397},"non_english":{"rating":1107.6,"rank":345,"pct":17.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gpt-3-5-turbo-0125"},{"slug":"tulu-2-dpo-70b","name":"Tulu 2 DPO 70B","source_name":"Tulu 2 DPO 70B","base":"Tulu 2 DPO 70B","variant":null,"org":"other","open_weights":true,"model_license":"AI2 ImpACT Low-risk","siscope":{"score":13.5,"rank":351,"coverage":0.75,"categories":{"coding":14.5,"reasoning":14.8,"math":11.6,"chat":14.6,"instructions":15.6}},"arena":{"text":{"rank":358,"date":"2026-10-28","rating":1121,"lo":1111.3,"hi":1130.7,"votes":6535,"pct":14.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1115.9,"rank":354,"pct":14.5,"board_size":414},"math":{"rating":1107.2,"rank":358,"pct":11.6,"board_size":405},"creative_writing":{"rating":1104.7,"rank":355,"pct":14.9,"board_size":417},"instruction_following":{"rating":1110.2,"rank":354,"pct":15.6,"board_size":419},"hard_prompts":{"rating":1104.3,"rank":357,"pct":14.8,"board_size":419},"multi_turn":{"rating":1085.4,"rank":362,"pct":13.2,"board_size":417},"longer_query":{"rating":1105.6,"rank":354,"pct":10.9,"board_size":397},"non_english":{"rating":1067.8,"rank":364,"pct":13.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/tulu-2-dpo-70b"},{"slug":"wizardlm-70b","name":"WizardLM 70B","source_name":"WizardLM 70B","base":"WizardLM 70B","variant":null,"org":"microsoft","open_weights":true,"model_license":"Llama 2 Community","siscope":{"score":11.6,"rank":357,"coverage":0.75,"categories":{"coding":9.9,"reasoning":12.7,"math":12.9,"chat":14.4,"instructions":14.4}},"arena":{"text":{"rank":359,"date":"2026-10-28","rating":1119.5,"lo":1110.2,"hi":1128.8,"votes":8214,"pct":14.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1080.9,"rank":373,"pct":9.9,"board_size":414},"math":{"rating":1116,"rank":353,"pct":12.9,"board_size":405},"creative_writing":{"rating":1148.9,"rank":335,"pct":19.7,"board_size":417},"instruction_following":{"rating":1092.9,"rank":359,"pct":14.4,"board_size":419},"hard_prompts":{"rating":1079,"rank":366,"pct":12.7,"board_size":419},"multi_turn":{"rating":1108.3,"rank":354,"pct":15.1,"board_size":417},"longer_query":{"rating":1096.8,"rank":359,"pct":9.6,"board_size":397},"non_english":{"rating":1077.4,"rank":356,"pct":15.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/wizardlm-70b"},{"slug":"dbrx-instruct-preview","name":"DBRX Instruct Preview","source_name":"DBRX Instruct Preview","base":"DBRX Instruct Preview","variant":null,"org":"other","open_weights":true,"model_license":"DBRX LICENSE","siscope":{"score":15.2,"rank":343,"coverage":0.75,"categories":{"coding":15.7,"reasoning":15.8,"math":15.8,"chat":14.1,"instructions":15.8}},"arena":{"text":{"rank":360,"date":"2026-10-28","rating":1118.8,"lo":1112.8,"hi":1124.9,"votes":32191,"pct":14.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1131.5,"rank":349,"pct":15.7,"board_size":414},"math":{"rating":1145,"rank":341,"pct":15.8,"board_size":405},"creative_writing":{"rating":1103.9,"rank":356,"pct":14.7,"board_size":417},"instruction_following":{"rating":1111.4,"rank":353,"pct":15.8,"board_size":419},"hard_prompts":{"rating":1112.9,"rank":353,"pct":15.8,"board_size":419},"multi_turn":{"rating":1111,"rank":352,"pct":15.6,"board_size":417},"longer_query":{"rating":1111.3,"rank":353,"pct":11.1,"board_size":397},"non_english":{"rating":1071.1,"rank":362,"pct":13.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/dbrx-instruct-preview"},{"slug":"llama-2-70b-chat","name":"Llama 2 70B Chat","source_name":"Llama 2 70B Chat","base":"Llama 2 70B Chat","variant":null,"org":"meta","open_weights":true,"model_license":"Llama 2 Community","siscope":{"score":10.7,"rank":362,"coverage":0.75,"categories":{"coding":9.4,"reasoning":12,"math":10.4,"chat":13.9,"instructions":12.4}},"arena":{"text":{"rank":361,"date":"2026-10-28","rating":1115.2,"lo":1109.8,"hi":1120.6,"votes":38492,"pct":13.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1078.5,"rank":375,"pct":9.4,"board_size":414},"math":{"rating":1091.2,"rank":363,"pct":10.4,"board_size":405},"creative_writing":{"rating":1074.6,"rank":376,"pct":9.9,"board_size":417},"instruction_following":{"rating":1070.7,"rank":367,"pct":12.4,"board_size":419},"hard_prompts":{"rating":1072.9,"rank":369,"pct":12,"board_size":419},"multi_turn":{"rating":1088,"rank":360,"pct":13.5,"board_size":417},"longer_query":{"rating":1061.7,"rank":370,"pct":6.8,"board_size":397},"non_english":{"rating":1045.1,"rank":373,"pct":11,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/llama-2-70b-chat"},{"slug":"nous-hermes-2-mixtral-8x7b-dpo","name":"Nous Hermes 2 Mixtral 8x7B DPO","source_name":"Nous Hermes 2 Mixtral 8x7B DPO","base":"Nous Hermes 2 Mixtral 8x7B DPO","variant":null,"org":"other","open_weights":true,"model_license":"Apache-2.0","siscope":{"score":8.9,"rank":370,"coverage":0.75,"categories":{"coding":9.7,"reasoning":9.1,"math":6.9,"chat":13.6,"instructions":9.8}},"arena":{"text":{"rank":362,"date":"2026-10-28","rating":1112,"lo":1100.2,"hi":1123.8,"votes":3777,"pct":13.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1079.4,"rank":374,"pct":9.7,"board_size":414},"math":{"rating":1060.6,"rank":377,"pct":6.9,"board_size":405},"creative_writing":{"rating":1101.4,"rank":359,"pct":13.9,"board_size":417},"instruction_following":{"rating":1055.8,"rank":378,"pct":9.8,"board_size":419},"hard_prompts":{"rating":1053.3,"rank":381,"pct":9.1,"board_size":419},"multi_turn":{"rating":1081.1,"rank":366,"pct":12.3,"board_size":417},"longer_query":{"rating":1045.5,"rank":378,"pct":4.8,"board_size":397},"non_english":{"rating":1048.8,"rank":372,"pct":11.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/nous-hermes-2-mixtral-8x7b-dpo"},{"slug":"phi-3-small-8k-instruct","name":"Phi-3 Small 8K Instruct","source_name":"Phi-3 Small 8K Instruct","base":"Phi-3 Small 8K Instruct","variant":null,"org":"microsoft","open_weights":true,"model_license":"MIT","siscope":{"score":13.5,"rank":350,"coverage":0.75,"categories":{"coding":12.3,"reasoning":14.4,"math":16.6,"chat":13.4,"instructions":13.2}},"arena":{"text":{"rank":363,"date":"2026-10-28","rating":1109.8,"lo":1104,"hi":1115.6,"votes":17766,"pct":13.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1101.1,"rank":363,"pct":12.3,"board_size":414},"math":{"rating":1150.7,"rank":338,"pct":16.6,"board_size":405},"creative_writing":{"rating":1082.5,"rank":373,"pct":10.6,"board_size":417},"instruction_following":{"rating":1086.5,"rank":364,"pct":13.2,"board_size":419},"hard_prompts":{"rating":1100.2,"rank":359,"pct":14.4,"board_size":419},"multi_turn":{"rating":1068.4,"rank":370,"pct":11.3,"board_size":417},"longer_query":{"rating":1087.3,"rank":364,"pct":8.3,"board_size":397},"non_english":{"rating":1057.8,"rank":368,"pct":12.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/phi-3-small-8k-instruct"},{"slug":"llama-3-2-3b-instruct","name":"Llama 3.2 3B Instruct","source_name":"Llama 3.2 3B Instruct","base":"Llama 3.2 3B Instruct","variant":null,"org":"meta","open_weights":true,"model_license":"Llama 3.2","siscope":{"score":12.9,"rank":354,"coverage":0.75,"categories":{"coding":12.1,"reasoning":13.9,"math":14.1,"chat":13.2,"instructions":13.6}},"arena":{"text":{"rank":364,"date":"2026-10-28","rating":1109.5,"lo":1102,"hi":1117.1,"votes":7936,"pct":13.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1097.4,"rank":364,"pct":12.1,"board_size":414},"math":{"rating":1125.9,"rank":348,"pct":14.1,"board_size":405},"creative_writing":{"rating":1093.9,"rank":363,"pct":13,"board_size":417},"instruction_following":{"rating":1088.7,"rank":362,"pct":13.6,"board_size":419},"hard_prompts":{"rating":1094.5,"rank":361,"pct":13.9,"board_size":419},"multi_turn":{"rating":1105.1,"rank":356,"pct":14.7,"board_size":417},"longer_query":{"rating":1100.2,"rank":358,"pct":9.8,"board_size":397},"non_english":{"rating":1018.7,"rank":382,"pct":8.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"meta-llama/llama-3.2-3b-instruct","input_per_m":0.0509,"output_per_m":0.335,"blended_per_m":0.1219,"context_length":131072,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/llama-3-2-3b-instruct"},{"slug":"starling-lm-7b-alpha","name":"Starling LM 7B Alpha","source_name":"Starling LM 7B Alpha","base":"Starling LM 7B Alpha","variant":null,"org":"other","open_weights":true,"model_license":"CC-BY-NC-4.0","siscope":{"score":11.1,"rank":359,"coverage":0.75,"categories":{"coding":11.9,"reasoning":12.4,"math":9.4,"chat":12.9,"instructions":11.7}},"arena":{"text":{"rank":365,"date":"2026-10-28","rating":1107.6,"lo":1099.7,"hi":1115.5,"votes":10224,"pct":12.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1097.2,"rank":365,"pct":11.9,"board_size":414},"math":{"rating":1081.5,"rank":367,"pct":9.4,"board_size":405},"creative_writing":{"rating":1098.9,"rank":360,"pct":13.7,"board_size":417},"instruction_following":{"rating":1069.8,"rank":370,"pct":11.7,"board_size":419},"hard_prompts":{"rating":1075.2,"rank":367,"pct":12.4,"board_size":419},"multi_turn":{"rating":1085,"rank":364,"pct":12.7,"board_size":417},"longer_query":{"rating":1080.8,"rank":366,"pct":7.8,"board_size":397},"non_english":{"rating":1055.5,"rank":369,"pct":12,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/starling-lm-7b-alpha"},{"slug":"openchat-3-5-0106","name":"OpenChat 3.5 (0106)","source_name":"OpenChat 3.5 (0106)","base":"OpenChat 3.5","variant":"0106","org":"other","open_weights":true,"model_license":"Apache-2.0","siscope":{"score":12.4,"rank":355,"coverage":0.75,"categories":{"coding":14,"reasoning":12.9,"math":11.1,"chat":12.7,"instructions":12.7}},"arena":{"text":{"rank":366,"date":"2026-10-28","rating":1106.6,"lo":1098.7,"hi":1114.5,"votes":12637,"pct":12.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1112.6,"rank":356,"pct":14,"board_size":414},"math":{"rating":1106.6,"rank":360,"pct":11.1,"board_size":405},"creative_writing":{"rating":1092.2,"rank":364,"pct":12.7,"board_size":417},"instruction_following":{"rating":1076.3,"rank":366,"pct":12.7,"board_size":419},"hard_prompts":{"rating":1084.8,"rank":365,"pct":12.9,"board_size":419},"multi_turn":{"rating":1090.8,"rank":359,"pct":13.9,"board_size":417},"longer_query":{"rating":1085.4,"rank":365,"pct":8.1,"board_size":397},"non_english":{"rating":1072,"rank":361,"pct":13.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/openchat-3-5-0106"},{"slug":"vicuna-33b","name":"Vicuna 33B","source_name":"Vicuna 33B","base":"Vicuna 33B","variant":null,"org":"other","open_weights":true,"model_license":"Non-commercial","siscope":{"score":9.4,"rank":368,"coverage":0.75,"categories":{"coding":9.2,"reasoning":10.3,"math":8.2,"chat":12.4,"instructions":11.2}},"arena":{"text":{"rank":367,"date":"2026-10-28","rating":1105.2,"lo":1099.1,"hi":1111.3,"votes":22479,"pct":12.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1078,"rank":376,"pct":9.2,"board_size":414},"math":{"rating":1070.6,"rank":372,"pct":8.2,"board_size":405},"creative_writing":{"rating":1124.4,"rank":346,"pct":17.1,"board_size":417},"instruction_following":{"rating":1064.8,"rank":372,"pct":11.2,"board_size":419},"hard_prompts":{"rating":1066.7,"rank":376,"pct":10.3,"board_size":419},"multi_turn":{"rating":1080.5,"rank":367,"pct":12,"board_size":417},"longer_query":{"rating":1028.3,"rank":383,"pct":3.5,"board_size":397},"non_english":{"rating":1054.8,"rank":370,"pct":11.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/vicuna-33b"},{"slug":"deepseek-llm-67b-chat","name":"DeepSeek LLM 67B Chat","source_name":"DeepSeek LLM 67B Chat","base":"DeepSeek LLM 67B Chat","variant":null,"org":"deepseek","open_weights":true,"model_license":"DeepSeek License","siscope":{"score":8.8,"rank":371,"coverage":0.75,"categories":{"coding":11.6,"reasoning":6.8,"math":6.9,"chat":12.2,"instructions":12.9}},"arena":{"text":{"rank":368,"date":"2026-10-28","rating":1105,"lo":1093.5,"hi":1116.5,"votes":4932,"pct":12.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1095.3,"rank":366,"pct":11.6,"board_size":414},"math":{"rating":1107.6,"rank":357,"pct":11.9,"board_size":405},"creative_writing":{"rating":1067.1,"rank":381,"pct":8.7,"board_size":417},"instruction_following":{"rating":1078.9,"rank":365,"pct":12.9,"board_size":419},"hard_prompts":{"rating":1069.7,"rank":374,"pct":10.8,"board_size":419},"multi_turn":{"rating":1081.9,"rank":365,"pct":12.5,"board_size":417},"longer_query":{"rating":1091.7,"rank":362,"pct":8.8,"board_size":397},"non_english":{"rating":1072.8,"rank":360,"pct":14.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.2462,"stderr":0.0136,"tested_as":"deepseek-llm-67b-chat","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F82RTgqgiC2UuM5M37L3WWM.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":2.7,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.0083,"stderr":0.0047,"tested_as":"deepseek-llm-67b-chat","approx":false,"run_date":"2026-08-28","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FY5rC5REnP83Q7mAoMtjiRq.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":1.9,"tested_models":313}],"price":null,"url":"https://siscope.app/models/deepseek-llm-67b-chat"},{"slug":"snowflake-arctic-instruct","name":"Snowflake Arctic Instruct","source_name":"Snowflake Arctic Instruct","base":"Snowflake Arctic Instruct","variant":null,"org":"other","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":11.2,"rank":358,"coverage":0.75,"categories":{"coding":10.7,"reasoning":11.2,"math":12.1,"chat":12,"instructions":11.5}},"arena":{"text":{"rank":369,"date":"2026-10-28","rating":1101,"lo":1095.1,"hi":1106.8,"votes":32832,"pct":12,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1089.1,"rank":370,"pct":10.7,"board_size":414},"math":{"rating":1108.7,"rank":356,"pct":12.1,"board_size":405},"creative_writing":{"rating":1080.6,"rank":374,"pct":10.3,"board_size":417},"instruction_following":{"rating":1066,"rank":371,"pct":11.5,"board_size":419},"hard_prompts":{"rating":1071.4,"rank":372,"pct":11.2,"board_size":419},"multi_turn":{"rating":1072.2,"rank":369,"pct":11.5,"board_size":417},"longer_query":{"rating":999,"rank":390,"pct":1.8,"board_size":397},"non_english":{"rating":1074.1,"rank":358,"pct":14.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/snowflake-arctic-instruct"},{"slug":"llama-2-70b-steerlm-chat","name":"Llama 2 70B SteerLM Chat","source_name":"Llama 2 70B SteerLM Chat","base":"Llama 2 70B SteerLM Chat","variant":null,"org":"nvidia","open_weights":true,"model_license":"Llama 2 Community","siscope":{"score":7.2,"rank":375,"coverage":0.75,"categories":{"coding":5.1,"reasoning":7.9,"math":8.7,"chat":11.7,"instructions":11}},"arena":{"text":{"rank":370,"date":"2026-10-28","rating":1098.1,"lo":1085.6,"hi":1110.5,"votes":3585,"pct":11.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1024.5,"rank":393,"pct":5.1,"board_size":414},"math":{"rating":1071.8,"rank":370,"pct":8.7,"board_size":405},"creative_writing":{"rating":1090.2,"rank":367,"pct":12,"board_size":417},"instruction_following":{"rating":1060.3,"rank":373,"pct":11,"board_size":419},"hard_prompts":{"rating":1046.6,"rank":386,"pct":7.9,"board_size":419},"multi_turn":{"rating":1057.9,"rank":375,"pct":10.1,"board_size":417},"longer_query":{"rating":997.5,"rank":392,"pct":1.3,"board_size":397},"non_english":{"rating":1063.4,"rank":366,"pct":12.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/llama-2-70b-steerlm-chat"},{"slug":"openchat-3-5","name":"OpenChat 3.5","source_name":"OpenChat 3.5","base":"OpenChat 3.5","variant":null,"org":"other","open_weights":true,"model_license":"Apache-2.0","siscope":{"score":9.3,"rank":369,"coverage":0.75,"categories":{"coding":9,"reasoning":9.8,"math":8.4,"chat":11.5,"instructions":12}},"arena":{"text":{"rank":371,"date":"2026-10-28","rating":1097,"lo":1087.4,"hi":1106.6,"votes":7968,"pct":11.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1073.9,"rank":377,"pct":9,"board_size":414},"math":{"rating":1070.7,"rank":371,"pct":8.4,"board_size":405},"creative_writing":{"rating":1125.3,"rank":345,"pct":17.3,"board_size":417},"instruction_following":{"rating":1070,"rank":369,"pct":12,"board_size":419},"hard_prompts":{"rating":1065.3,"rank":377,"pct":9.8,"board_size":419},"multi_turn":{"rating":1085.3,"rank":363,"pct":13,"board_size":417},"longer_query":{"rating":1092.6,"rank":361,"pct":9.1,"board_size":397},"non_english":{"rating":1066.7,"rank":365,"pct":12.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/openchat-3-5"},{"slug":"granite-3-0-8b-instruct","name":"Granite 3.0 8B Instruct","source_name":"Granite 3.0 8B Instruct","base":"Granite 3.0 8B Instruct","variant":null,"org":"ibm","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":13.1,"rank":353,"coverage":0.75,"categories":{"coding":13.8,"reasoning":13.4,"math":15.6,"chat":11.2,"instructions":13.4}},"arena":{"text":{"rank":372,"date":"2026-10-28","rating":1096.4,"lo":1087.9,"hi":1105,"votes":6638,"pct":11.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1112.2,"rank":357,"pct":13.8,"board_size":414},"math":{"rating":1143.3,"rank":342,"pct":15.6,"board_size":405},"creative_writing":{"rating":1070.4,"rank":378,"pct":9.4,"board_size":417},"instruction_following":{"rating":1087.9,"rank":363,"pct":13.4,"board_size":419},"hard_prompts":{"rating":1091.6,"rank":363,"pct":13.4,"board_size":419},"multi_turn":{"rating":1062.8,"rank":372,"pct":10.8,"board_size":417},"longer_query":{"rating":1121.7,"rank":349,"pct":12.1,"board_size":397},"non_english":{"rating":1036.5,"rank":375,"pct":10.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/granite-3-0-8b-instruct"},{"slug":"gpt-3-5-turbo-1106","name":"GPT-3.5 Turbo (1106)","source_name":"GPT-3.5 Turbo (1106)","base":"GPT-3.5 Turbo","variant":"1106","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":13.2,"rank":352,"coverage":0.75,"categories":{"coding":14.3,"reasoning":14.1,"math":15.1,"chat":11,"instructions":14.1}},"arena":{"text":{"rank":373,"date":"2026-10-28","rating":1094.1,"lo":1085.4,"hi":1102.8,"votes":16619,"pct":11,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1115.5,"rank":355,"pct":14.3,"board_size":414},"math":{"rating":1141.2,"rank":344,"pct":15.1,"board_size":405},"creative_writing":{"rating":1034.8,"rank":388,"pct":7,"board_size":417},"instruction_following":{"rating":1092.5,"rank":360,"pct":14.1,"board_size":419},"hard_prompts":{"rating":1098.4,"rank":360,"pct":14.1,"board_size":419},"multi_turn":{"rating":1077.9,"rank":368,"pct":11.8,"board_size":417},"longer_query":{"rating":1069.4,"rank":368,"pct":7.3,"board_size":397},"non_english":{"rating":1074.1,"rank":359,"pct":14.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gpt-3-5-turbo-1106"},{"slug":"gemma-1-1-7b-it","name":"Gemma 1.1 7B IT","source_name":"Gemma 1.1 7B IT","base":"Gemma 1.1 7B IT","variant":null,"org":"google","open_weights":true,"model_license":"Gemma license","siscope":{"score":10.6,"rank":363,"coverage":0.75,"categories":{"coding":10.4,"reasoning":11,"math":11.4,"chat":10.8,"instructions":10}},"arena":{"text":{"rank":374,"date":"2026-10-28","rating":1093.9,"lo":1087.9,"hi":1099.9,"votes":23893,"pct":10.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1083.5,"rank":371,"pct":10.4,"board_size":414},"math":{"rating":1106.8,"rank":359,"pct":11.4,"board_size":405},"creative_writing":{"rating":1059.1,"rank":382,"pct":8.4,"board_size":417},"instruction_following":{"rating":1056.7,"rank":377,"pct":10,"board_size":419},"hard_prompts":{"rating":1070.5,"rank":373,"pct":11,"board_size":419},"multi_turn":{"rating":1039.8,"rank":382,"pct":8.4,"board_size":417},"longer_query":{"rating":1055.4,"rank":373,"pct":6.1,"board_size":397},"non_english":{"rating":1051.4,"rank":371,"pct":11.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemma-1-1-7b-it"},{"slug":"openhermes-2-5-mistral-7b","name":"OpenHermes 2.5 Mistral 7B","source_name":"OpenHermes 2.5 Mistral 7B","base":"OpenHermes 2.5 Mistral 7B","variant":null,"org":"other","open_weights":true,"model_license":"Apache-2.0","siscope":{"score":9.6,"rank":367,"coverage":0.75,"categories":{"coding":8,"reasoning":11.5,"math":10.6,"chat":10.5,"instructions":12.2}},"arena":{"text":{"rank":375,"date":"2026-10-28","rating":1092.5,"lo":1082.2,"hi":1102.8,"votes":5006,"pct":10.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1064.1,"rank":381,"pct":8,"board_size":414},"math":{"rating":1097.6,"rank":362,"pct":10.6,"board_size":405},"creative_writing":{"rating":1096.9,"rank":361,"pct":13.5,"board_size":417},"instruction_following":{"rating":1070.1,"rank":368,"pct":12.2,"board_size":419},"hard_prompts":{"rating":1071.5,"rank":371,"pct":11.5,"board_size":419},"multi_turn":{"rating":1064.4,"rank":371,"pct":11.1,"board_size":417},"longer_query":{"rating":1053.9,"rank":374,"pct":5.8,"board_size":397},"non_english":{"rating":1024.2,"rank":379,"pct":9.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/openhermes-2-5-mistral-7b"},{"slug":"mistral-7b-instruct-v0-2","name":"Mistral 7B Instruct v0.2","source_name":"Mistral 7B Instruct v0.2","base":"Mistral 7B Instruct v0.2","variant":null,"org":"mistral","open_weights":true,"model_license":"Apache-2.0","siscope":{"score":10.1,"rank":366,"coverage":0.75,"categories":{"coding":10.2,"reasoning":10.5,"math":9.7,"chat":10.3,"instructions":10.8}},"arena":{"text":{"rank":376,"date":"2026-10-28","rating":1089.5,"lo":1083,"hi":1096.1,"votes":19402,"pct":10.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1081.4,"rank":372,"pct":10.2,"board_size":414},"math":{"rating":1085.4,"rank":366,"pct":9.7,"board_size":405},"creative_writing":{"rating":1067.4,"rank":380,"pct":8.9,"board_size":417},"instruction_following":{"rating":1059.8,"rank":374,"pct":10.8,"board_size":419},"hard_prompts":{"rating":1067,"rank":375,"pct":10.5,"board_size":419},"multi_turn":{"rating":1062.4,"rank":373,"pct":10.6,"board_size":417},"longer_query":{"rating":1060,"rank":371,"pct":6.6,"board_size":397},"non_english":{"rating":1011.7,"rank":386,"pct":7.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/mistral-7b-instruct-v0-2"},{"slug":"llama-2-13b-chat","name":"Llama 2 13B Chat","source_name":"Llama 2 13B Chat","base":"Llama 2 13B Chat","variant":null,"org":"meta","open_weights":true,"model_license":"Llama 2 Community","siscope":{"score":7.9,"rank":373,"coverage":0.75,"categories":{"coding":7.7,"reasoning":8.1,"math":7.4,"chat":10,"instructions":7.9}},"arena":{"text":{"rank":377,"date":"2026-10-28","rating":1084.4,"lo":1077.8,"hi":1091.1,"votes":19174,"pct":10,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1062,"rank":382,"pct":7.7,"board_size":414},"math":{"rating":1064.9,"rank":375,"pct":7.4,"board_size":405},"creative_writing":{"rating":1046.6,"rank":384,"pct":7.9,"board_size":417},"instruction_following":{"rating":1045.2,"rank":386,"pct":7.9,"board_size":419},"hard_prompts":{"rating":1050.8,"rank":385,"pct":8.1,"board_size":419},"multi_turn":{"rating":1050.1,"rank":378,"pct":9.4,"board_size":417},"longer_query":{"rating":1063.9,"rank":369,"pct":7.1,"board_size":397},"non_english":{"rating":1023.8,"rank":380,"pct":9.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/llama-2-13b-chat"},{"slug":"qwen1-5-7b-chat","name":"Qwen1.5 7B Chat","source_name":"Qwen1.5-7B-Chat","base":"Qwen1.5 7B Chat","variant":null,"org":"alibaba","open_weights":true,"model_license":"Qianwen LICENSE","siscope":{"score":10.3,"rank":365,"coverage":0.75,"categories":{"coding":12.8,"reasoning":9.8,"math":9.2,"chat":9.8,"instructions":10.5}},"arena":{"text":{"rank":378,"date":"2026-10-28","rating":1083.4,"lo":1073.7,"hi":1093.1,"votes":4737,"pct":9.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1107,"rank":361,"pct":12.8,"board_size":414},"math":{"rating":1079.7,"rank":368,"pct":9.2,"board_size":405},"creative_writing":{"rating":1034.2,"rank":389,"pct":6.7,"board_size":417},"instruction_following":{"rating":1058.1,"rank":375,"pct":10.5,"board_size":419},"hard_prompts":{"rating":1065.3,"rank":378,"pct":9.8,"board_size":419},"multi_turn":{"rating":1061.5,"rank":374,"pct":10.3,"board_size":417},"longer_query":{"rating":1089.9,"rank":363,"pct":8.6,"board_size":397},"non_english":{"rating":1058.3,"rank":367,"pct":12.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen1-5-7b-chat"},{"slug":"solar-10-7b-instruct-v1-0","name":"SOLAR 10.7B Instruct v1.0","source_name":"SOLAR 10.7B Instruct v1.0","base":"SOLAR 10.7B Instruct v1.0","variant":null,"org":"upstage","open_weights":true,"model_license":"CC-BY-NC-4.0","siscope":{"score":8.2,"rank":372,"coverage":0.75,"categories":{"coding":8.2,"reasoning":9.6,"math":7.2,"chat":9.6,"instructions":8.1}},"arena":{"text":{"rank":379,"date":"2026-10-28","rating":1083.1,"lo":1070,"hi":1096.1,"votes":4155,"pct":9.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1066.5,"rank":380,"pct":8.2,"board_size":414},"math":{"rating":1063.9,"rank":376,"pct":7.2,"board_size":405},"creative_writing":{"rating":1089.1,"rank":369,"pct":11.5,"board_size":417},"instruction_following":{"rating":1046.3,"rank":385,"pct":8.1,"board_size":419},"hard_prompts":{"rating":1061.9,"rank":379,"pct":9.6,"board_size":419},"multi_turn":{"rating":1045.1,"rank":381,"pct":8.7,"board_size":417},"non_english":{"rating":1013.9,"rank":383,"pct":8.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/solar-10-7b-instruct-v1-0"},{"slug":"dolphin-2-2-1-mistral-7b","name":"Dolphin 2.2.1 Mistral 7B","source_name":"Dolphin 2.2.1 Mistral 7B","base":"Dolphin 2.2.1 Mistral 7B","variant":null,"org":"other","open_weights":true,"model_license":"Apache-2.0","siscope":{"score":null,"rank":null,"coverage":0.5,"categories":{"reasoning":9.3,"math":8.9,"chat":9.3,"instructions":9.1}},"arena":{"text":{"rank":380,"date":"2026-10-28","rating":1080.9,"lo":1065.7,"hi":1096.2,"votes":1679,"pct":9.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"math":{"rating":1076.6,"rank":369,"pct":8.9,"board_size":405},"creative_writing":{"rating":1085.4,"rank":371,"pct":11.1,"board_size":417},"instruction_following":{"rating":1053.2,"rank":381,"pct":9.1,"board_size":419},"hard_prompts":{"rating":1054.4,"rank":380,"pct":9.3,"board_size":419},"multi_turn":{"rating":1020.6,"rank":388,"pct":7,"board_size":417},"non_english":{"rating":1012.3,"rank":385,"pct":8.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/dolphin-2-2-1-mistral-7b"},{"slug":"phi-3-mini-4k-instruct-june-2024","name":"Phi-3 Mini 4K Instruct (June 2024)","source_name":"Phi-3 Mini 4K Instruct (June 2024)","base":"Phi-3 Mini 4K Instruct","variant":"June 2024","org":"microsoft","open_weights":true,"model_license":"MIT","siscope":{"score":11.8,"rank":356,"coverage":0.75,"categories":{"coding":11.4,"reasoning":13.2,"math":17.3,"chat":9.1,"instructions":10.3}},"arena":{"text":{"rank":381,"date":"2026-10-28","rating":1079.9,"lo":1073.6,"hi":1086.3,"votes":12297,"pct":9.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1092.8,"rank":367,"pct":11.4,"board_size":414},"math":{"rating":1152,"rank":335,"pct":17.3,"board_size":405},"creative_writing":{"rating":1044.3,"rank":386,"pct":7.5,"board_size":417},"instruction_following":{"rating":1057.6,"rank":376,"pct":10.3,"board_size":419},"hard_prompts":{"rating":1087.3,"rank":364,"pct":13.2,"board_size":419},"multi_turn":{"rating":1049.1,"rank":379,"pct":9.1,"board_size":417},"longer_query":{"rating":1041.2,"rank":381,"pct":4,"board_size":397},"non_english":{"rating":1012.5,"rank":384,"pct":8.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/phi-3-mini-4k-instruct-june-2024"},{"slug":"granite-3-0-2b-instruct","name":"Granite 3.0 2B Instruct","source_name":"Granite 3.0 2B Instruct","base":"Granite 3.0 2B Instruct","variant":null,"org":"ibm","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":10.7,"rank":361,"coverage":0.75,"categories":{"coding":10.9,"reasoning":12.2,"math":13.1,"chat":8.9,"instructions":9.6}},"arena":{"text":{"rank":382,"date":"2026-10-28","rating":1079.8,"lo":1071.6,"hi":1088,"votes":6837,"pct":8.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1090.1,"rank":369,"pct":10.9,"board_size":414},"math":{"rating":1116.9,"rank":352,"pct":13.1,"board_size":405},"creative_writing":{"rating":1045.9,"rank":385,"pct":7.7,"board_size":417},"instruction_following":{"rating":1055.5,"rank":379,"pct":9.6,"board_size":419},"hard_prompts":{"rating":1073.1,"rank":368,"pct":12.2,"board_size":419},"multi_turn":{"rating":1052.9,"rank":377,"pct":9.6,"board_size":417},"longer_query":{"rating":1070,"rank":367,"pct":7.6,"board_size":397},"non_english":{"rating":1032.4,"rank":377,"pct":10,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/granite-3-0-2b-instruct"},{"slug":"wizardlm-13b","name":"WizardLM 13B","source_name":"WizardLM 13B","base":"WizardLM 13B","variant":null,"org":"microsoft","open_weights":true,"model_license":"Llama 2 Community","siscope":{"score":5.3,"rank":384,"coverage":0.75,"categories":{"coding":5.6,"reasoning":5.7,"math":3.7,"chat":8.6,"instructions":8.6}},"arena":{"text":{"rank":383,"date":"2026-10-28","rating":1076.5,"lo":1067.3,"hi":1085.7,"votes":7044,"pct":8.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1034.6,"rank":391,"pct":5.6,"board_size":414},"math":{"rating":1017.1,"rank":390,"pct":3.7,"board_size":405},"creative_writing":{"rating":1090.1,"rank":368,"pct":11.8,"board_size":417},"instruction_following":{"rating":1048.3,"rank":383,"pct":8.6,"board_size":419},"hard_prompts":{"rating":1017.5,"rank":395,"pct":5.7,"board_size":419},"multi_turn":{"rating":1047,"rank":380,"pct":8.9,"board_size":417},"longer_query":{"rating":1053.3,"rank":375,"pct":5.6,"board_size":397},"non_english":{"rating":1034.2,"rank":376,"pct":10.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/wizardlm-13b"},{"slug":"phi-3-mini-4k-instruct","name":"Phi-3 Mini 4K Instruct","source_name":"Phi-3 Mini 4K Instruct","base":"Phi-3 Mini 4K Instruct","variant":null,"org":"microsoft","open_weights":true,"model_license":"MIT","siscope":{"score":10.4,"rank":364,"coverage":0.75,"categories":{"coding":11.1,"reasoning":11.7,"math":12.4,"chat":8.4,"instructions":8.9}},"arena":{"text":{"rank":384,"date":"2026-10-28","rating":1073.3,"lo":1067,"hi":1079.6,"votes":20118,"pct":8.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1092.3,"rank":368,"pct":11.1,"board_size":414},"math":{"rating":1111.4,"rank":355,"pct":12.4,"board_size":405},"creative_writing":{"rating":1036.6,"rank":387,"pct":7.2,"board_size":417},"instruction_following":{"rating":1053.1,"rank":382,"pct":8.9,"board_size":419},"hard_prompts":{"rating":1072.1,"rank":370,"pct":11.7,"board_size":419},"multi_turn":{"rating":1018.2,"rank":389,"pct":6.7,"board_size":417},"longer_query":{"rating":1043.7,"rank":379,"pct":4.5,"board_size":397},"non_english":{"rating":1020.5,"rank":381,"pct":9.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/phi-3-mini-4k-instruct"},{"slug":"zephyr-7b-beta","name":"Zephyr 7B Beta","source_name":"Zephyr 7B Beta","base":"Zephyr 7B Beta","variant":null,"org":"other","open_weights":true,"model_license":"MIT","siscope":{"score":6.3,"rank":381,"coverage":0.75,"categories":{"coding":6.5,"reasoning":6.5,"math":5.4,"chat":8.1,"instructions":7.2}},"arena":{"text":{"rank":385,"date":"2026-10-28","rating":1069.4,"lo":1060.7,"hi":1078.1,"votes":11118,"pct":8.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1044.3,"rank":387,"pct":6.5,"board_size":414},"math":{"rating":1040.9,"rank":383,"pct":5.4,"board_size":405},"creative_writing":{"rating":1102,"rank":358,"pct":14.2,"board_size":417},"instruction_following":{"rating":1031.4,"rank":389,"pct":7.2,"board_size":419},"hard_prompts":{"rating":1026.5,"rank":392,"pct":6.5,"board_size":419},"multi_turn":{"rating":1037.9,"rank":383,"pct":8.2,"board_size":417},"longer_query":{"rating":1041.3,"rank":380,"pct":4.3,"board_size":397},"non_english":{"rating":987.5,"rank":396,"pct":5.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/zephyr-7b-beta"},{"slug":"mpt-30b-chat","name":"MPT 30B Chat","source_name":"MPT 30B Chat","base":"MPT 30B Chat","variant":null,"org":"other","open_weights":true,"model_license":"CC-BY-NC-SA-4.0","siscope":{"score":6.7,"rank":379,"coverage":0.75,"categories":{"coding":5.8,"reasoning":8.4,"math":5.9,"chat":7.9,"instructions":9.3}},"arena":{"text":{"rank":386,"date":"2026-10-28","rating":1068.6,"lo":1056.5,"hi":1080.7,"votes":2572,"pct":7.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1039,"rank":390,"pct":5.8,"board_size":414},"math":{"rating":1046.6,"rank":381,"pct":5.9,"board_size":405},"creative_writing":{"rating":1073.7,"rank":377,"pct":9.6,"board_size":417},"instruction_following":{"rating":1053.8,"rank":380,"pct":9.3,"board_size":419},"hard_prompts":{"rating":1051.4,"rank":384,"pct":8.4,"board_size":419},"multi_turn":{"rating":1054.5,"rank":376,"pct":9.9,"board_size":417},"non_english":{"rating":990.4,"rank":393,"pct":6.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/mpt-30b-chat"},{"slug":"code-llama-34b-instruct","name":"Code Llama 34B Instruct","source_name":"Code Llama 34B Instruct","base":"Code Llama 34B Instruct","variant":null,"org":"meta","open_weights":true,"model_license":"Llama 2 Community","siscope":{"score":6.8,"rank":378,"coverage":0.75,"categories":{"coding":6.8,"reasoning":7.2,"math":6.7,"chat":7.7,"instructions":6.2}},"arena":{"text":{"rank":387,"date":"2026-10-28","rating":1065.5,"lo":1056.7,"hi":1074.2,"votes":7366,"pct":7.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1045.5,"rank":386,"pct":6.8,"board_size":414},"math":{"rating":1056.4,"rank":378,"pct":6.7,"board_size":405},"creative_writing":{"rating":1031.3,"rank":392,"pct":6,"board_size":417},"instruction_following":{"rating":1027.8,"rank":393,"pct":6.2,"board_size":419},"hard_prompts":{"rating":1032,"rank":389,"pct":7.2,"board_size":419},"multi_turn":{"rating":1015.4,"rank":391,"pct":6.2,"board_size":417},"longer_query":{"rating":1013.1,"rank":386,"pct":2.8,"board_size":397},"non_english":{"rating":1010.5,"rank":387,"pct":7.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/code-llama-34b-instruct"},{"slug":"zephyr-7b-alpha","name":"Zephyr 7B Alpha","source_name":"Zephyr 7B Alpha","base":"Zephyr 7B Alpha","variant":null,"org":"other","open_weights":true,"model_license":"MIT","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"coding":7.5,"reasoning":6.2,"chat":7.4,"instructions":7.4}},"arena":{"text":{"rank":388,"date":"2026-10-28","rating":1058.3,"lo":1042.7,"hi":1074,"votes":1785,"pct":7.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1052.5,"rank":383,"pct":7.5,"board_size":414},"creative_writing":{"rating":1068.4,"rank":379,"pct":9.1,"board_size":417},"instruction_following":{"rating":1034.2,"rank":388,"pct":7.4,"board_size":419},"hard_prompts":{"rating":1023.7,"rank":393,"pct":6.2,"board_size":419},"multi_turn":{"rating":1017.6,"rank":390,"pct":6.5,"board_size":417},"non_english":{"rating":987.7,"rank":395,"pct":5.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/zephyr-7b-alpha"},{"slug":"vicuna-13b","name":"Vicuna 13B","source_name":"Vicuna 13B","base":"Vicuna 13B","variant":null,"org":"other","open_weights":true,"model_license":"Llama 2 Community","siscope":{"score":5.8,"rank":383,"coverage":0.75,"categories":{"coding":6.3,"reasoning":6,"math":4.7,"chat":7.2,"instructions":7.7}},"arena":{"text":{"rank":389,"date":"2026-10-28","rating":1057.6,"lo":1051.1,"hi":1064.2,"votes":19367,"pct":7.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1040.4,"rank":388,"pct":6.3,"board_size":414},"math":{"rating":1030.4,"rank":386,"pct":4.7,"board_size":405},"creative_writing":{"rating":1057.8,"rank":383,"pct":8.2,"board_size":417},"instruction_following":{"rating":1035,"rank":387,"pct":7.7,"board_size":419},"hard_prompts":{"rating":1023.4,"rank":394,"pct":6,"board_size":419},"multi_turn":{"rating":1030.8,"rank":384,"pct":7.9,"board_size":417},"longer_query":{"rating":1047,"rank":377,"pct":5.1,"board_size":397},"non_english":{"rating":1027.1,"rank":378,"pct":9.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/vicuna-13b"},{"slug":"code-llama-70b-instruct","name":"Code Llama 70B Instruct","source_name":"Code Llama 70B Instruct","base":"Code Llama 70B Instruct","variant":null,"org":"meta","open_weights":true,"model_license":"Llama 2 Community","siscope":{"score":null,"rank":null,"coverage":0.35,"categories":{"reasoning":8.6,"chat":6.9,"instructions":6}},"arena":{"text":{"rank":390,"date":"2026-10-28","rating":1057.2,"lo":1039.2,"hi":1075.2,"votes":1143,"pct":6.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"instruction_following":{"rating":1023.5,"rank":394,"pct":6,"board_size":419},"hard_prompts":{"rating":1052,"rank":383,"pct":8.6,"board_size":419},"non_english":{"rating":992.2,"rank":392,"pct":6.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/code-llama-70b-instruct"},{"slug":"gemma-7b-it","name":"Gemma 7B IT","source_name":"Gemma 7B IT","base":"Gemma 7B IT","variant":null,"org":"google","open_weights":true,"model_license":"Gemma license","siscope":{"score":6.8,"rank":377,"coverage":0.75,"categories":{"coding":7.3,"reasoning":7.4,"math":7.7,"chat":6.7,"instructions":5.5}},"arena":{"text":{"rank":391,"date":"2026-10-28","rating":1056.1,"lo":1046.6,"hi":1065.7,"votes":8925,"pct":6.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1047.8,"rank":384,"pct":7.3,"board_size":414},"math":{"rating":1066.3,"rank":374,"pct":7.7,"board_size":405},"creative_writing":{"rating":1023.2,"rank":398,"pct":4.6,"board_size":417},"instruction_following":{"rating":1016.9,"rank":396,"pct":5.5,"board_size":419},"hard_prompts":{"rating":1041.5,"rank":388,"pct":7.4,"board_size":419},"multi_turn":{"rating":963.2,"rank":402,"pct":3.6,"board_size":417},"longer_query":{"rating":1021.4,"rank":385,"pct":3,"board_size":397},"non_english":{"rating":998.5,"rank":391,"pct":6.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemma-7b-it"},{"slug":"llama-3-2-1b-instruct","name":"Llama 3.2 1B Instruct","source_name":"Llama 3.2 1B Instruct","base":"Llama 3.2 1B Instruct","variant":null,"org":"meta","open_weights":true,"model_license":"Llama 3.2","siscope":{"score":6.1,"rank":382,"coverage":0.75,"categories":{"coding":8.5,"reasoning":4.9,"math":5.5,"chat":6.5,"instructions":6.7}},"arena":{"text":{"rank":392,"date":"2026-10-28","rating":1054.6,"lo":1046.9,"hi":1062.3,"votes":8045,"pct":6.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1070.2,"rank":379,"pct":8.5,"board_size":414},"math":{"rating":1085.7,"rank":365,"pct":9.9,"board_size":405},"creative_writing":{"rating":1032.5,"rank":391,"pct":6.2,"board_size":417},"instruction_following":{"rating":1030.9,"rank":391,"pct":6.7,"board_size":419},"hard_prompts":{"rating":1044.1,"rank":387,"pct":7.7,"board_size":419},"multi_turn":{"rating":1029.8,"rank":385,"pct":7.7,"board_size":417},"longer_query":{"rating":1049.5,"rank":376,"pct":5.3,"board_size":397},"non_english":{"rating":973.2,"rank":401,"pct":4.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.2393,"stderr":0.0163,"tested_as":"Llama-3.2-1B-Instruct","approx":false,"run_date":"2026-08-30","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FFGEsLTxzZ7fE9aq7DhdqZb.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":2.1,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.0056,"stderr":0.0039,"tested_as":"Llama-3.2-1B-Instruct","approx":false,"run_date":"2026-08-30","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F8qwT2CF9U5zV99PFirnVsp.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":1,"tested_models":313}],"price":{"openrouter_id":"meta-llama/llama-3.2-1b-instruct","input_per_m":0.027,"output_per_m":0.201,"blended_per_m":0.0705,"context_length":60000,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/llama-3-2-1b-instruct"},{"slug":"falcon-180b-chat","name":"Falcon 180B Chat","source_name":"Falcon 180B Chat","base":"Falcon 180B Chat","variant":null,"org":"other","open_weights":true,"model_license":"Falcon-180B TII License","siscope":{"score":null,"rank":null,"coverage":0.35,"categories":{"reasoning":5.3,"chat":6.2,"instructions":8.4}},"arena":{"text":{"rank":393,"date":"2026-10-28","rating":1054.3,"lo":1037.3,"hi":1071.3,"votes":1295,"pct":6.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"creative_writing":{"rating":1088.2,"rank":370,"pct":11.3,"board_size":417},"instruction_following":{"rating":1046.4,"rank":384,"pct":8.4,"board_size":419},"hard_prompts":{"rating":1007.1,"rank":397,"pct":5.3,"board_size":419},"multi_turn":{"rating":1012.9,"rank":392,"pct":6,"board_size":417},"non_english":{"rating":999.6,"rank":390,"pct":6.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/falcon-180b-chat"},{"slug":"llama-2-7b-chat","name":"Llama 2 7B Chat","source_name":"Llama 2 7B Chat","base":"Llama 2 7B Chat","variant":null,"org":"meta","open_weights":true,"model_license":"Llama 2 Community","siscope":{"score":4.7,"rank":385,"coverage":0.75,"categories":{"coding":3.9,"reasoning":5.5,"math":5.7,"chat":5.7,"instructions":4.8}},"arena":{"text":{"rank":394,"date":"2026-10-28","rating":1053.4,"lo":1046.4,"hi":1060.3,"votes":14148,"pct":5.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1001.6,"rank":398,"pct":3.9,"board_size":414},"math":{"rating":1041.9,"rank":382,"pct":5.7,"board_size":405},"creative_writing":{"rating":1032.9,"rank":390,"pct":6.5,"board_size":417},"instruction_following":{"rating":1005.7,"rank":399,"pct":4.8,"board_size":419},"hard_prompts":{"rating":1009.1,"rank":396,"pct":5.5,"board_size":419},"multi_turn":{"rating":1029.1,"rank":386,"pct":7.5,"board_size":417},"longer_query":{"rating":998.8,"rank":391,"pct":1.5,"board_size":397},"non_english":{"rating":972.7,"rank":402,"pct":4.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/llama-2-7b-chat"},{"slug":"guanaco-33b","name":"Guanaco 33B","source_name":"Guanaco 33B","base":"Guanaco 33B","variant":null,"org":"other","open_weights":true,"model_license":"Non-commercial","siscope":{"score":4.1,"rank":389,"coverage":0.75,"categories":{"coding":3.1,"reasoning":5,"math":5,"chat":5.7,"instructions":3.8}},"arena":{"text":{"rank":395,"date":"2026-10-28","rating":1053.4,"lo":1041.4,"hi":1065.3,"votes":2921,"pct":5.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":995.2,"rank":401,"pct":3.1,"board_size":414},"math":{"rating":1032.6,"rank":385,"pct":5,"board_size":405},"creative_writing":{"rating":1079.7,"rank":375,"pct":10.1,"board_size":417},"instruction_following":{"rating":991.2,"rank":403,"pct":3.8,"board_size":419},"hard_prompts":{"rating":1004.9,"rank":398,"pct":5,"board_size":419},"multi_turn":{"rating":1006,"rank":396,"pct":5,"board_size":417},"non_english":{"rating":987.4,"rank":397,"pct":5.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/guanaco-33b"},{"slug":"qwen-14b-chat","name":"Qwen-14B-Chat","source_name":"Qwen-14B-Chat","base":"Qwen-14B-Chat","variant":null,"org":"alibaba","open_weights":true,"model_license":"Qianwen LICENSE","siscope":{"score":7,"rank":376,"coverage":0.75,"categories":{"coding":8.7,"reasoning":6.7,"math":7.9,"chat":5.5,"instructions":6.9}},"arena":{"text":{"rank":396,"date":"2026-10-28","rating":1051,"lo":1040.1,"hi":1061.9,"votes":4964,"pct":5.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1071.2,"rank":378,"pct":8.7,"board_size":414},"math":{"rating":1067.7,"rank":373,"pct":7.9,"board_size":405},"creative_writing":{"rating":1027.4,"rank":396,"pct":5,"board_size":417},"instruction_following":{"rating":1031.2,"rank":390,"pct":6.9,"board_size":419},"hard_prompts":{"rating":1026.9,"rank":391,"pct":6.7,"board_size":419},"multi_turn":{"rating":1022.1,"rank":387,"pct":7.2,"board_size":417},"longer_query":{"rating":1028.2,"rank":384,"pct":3.3,"board_size":397},"non_english":{"rating":1041.4,"rank":374,"pct":10.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen-14b-chat"},{"slug":"phi-3-mini-128k-instruct","name":"Phi-3 Mini 128K Instruct","source_name":"Phi-3 Mini 128K Instruct","base":"Phi-3 Mini 128K Instruct","variant":null,"org":"microsoft","open_weights":true,"model_license":"MIT","siscope":{"score":6.6,"rank":380,"coverage":0.75,"categories":{"coding":6.1,"reasoning":6.9,"math":10.1,"chat":5.3,"instructions":5.7}},"arena":{"text":{"rank":397,"date":"2026-10-28","rating":1050.4,"lo":1043.1,"hi":1057.6,"votes":20685,"pct":5.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1039.2,"rank":389,"pct":6.1,"board_size":414},"math":{"rating":1089,"rank":364,"pct":10.1,"board_size":405},"creative_writing":{"rating":1023.9,"rank":397,"pct":4.8,"board_size":417},"instruction_following":{"rating":1022.7,"rank":395,"pct":5.7,"board_size":419},"hard_prompts":{"rating":1027.9,"rank":390,"pct":6.9,"board_size":419},"multi_turn":{"rating":988.9,"rank":399,"pct":4.3,"board_size":417},"longer_query":{"rating":995.4,"rank":393,"pct":1,"board_size":397},"non_english":{"rating":1000.3,"rank":389,"pct":7.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/phi-3-mini-128k-instruct"},{"slug":"smollm2-1-7b-instruct","name":"SmolLM2 1.7B Instruct","source_name":"SmolLM2 1.7B Instruct","base":"SmolLM2 1.7B Instruct","variant":null,"org":"other","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":7.2,"rank":374,"coverage":0.75,"categories":{"coding":7,"reasoning":8.9,"math":10.9,"chat":5,"instructions":6.5}},"arena":{"text":{"rank":398,"date":"2026-10-28","rating":1042,"lo":1027.9,"hi":1056.1,"votes":2199,"pct":5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1047.6,"rank":385,"pct":7,"board_size":414},"math":{"rating":1104.7,"rank":361,"pct":10.9,"board_size":405},"creative_writing":{"rating":1031.1,"rank":393,"pct":5.8,"board_size":417},"instruction_following":{"rating":1029,"rank":392,"pct":6.5,"board_size":419},"hard_prompts":{"rating":1053,"rank":382,"pct":8.9,"board_size":419},"multi_turn":{"rating":993,"rank":398,"pct":4.6,"board_size":417},"longer_query":{"rating":1056,"rank":372,"pct":6.3,"board_size":397},"non_english":{"rating":984.7,"rank":398,"pct":5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/smollm2-1-7b-instruct"},{"slug":"stripedhyena-nous-7b","name":"StripedHyena Nous 7B","source_name":"StripedHyena Nous 7B","base":"StripedHyena Nous 7B","variant":null,"org":"other","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":4.1,"rank":388,"coverage":0.75,"categories":{"coding":3.6,"reasoning":4.1,"math":5.2,"chat":4.8,"instructions":5.3}},"arena":{"text":{"rank":399,"date":"2026-10-28","rating":1038.4,"lo":1027.5,"hi":1049.4,"votes":5182,"pct":4.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1000.8,"rank":399,"pct":3.6,"board_size":414},"math":{"rating":1033,"rank":384,"pct":5.2,"board_size":405},"creative_writing":{"rating":1029,"rank":394,"pct":5.5,"board_size":417},"instruction_following":{"rating":1010.2,"rank":397,"pct":5.3,"board_size":419},"hard_prompts":{"rating":998.1,"rank":402,"pct":4.1,"board_size":419},"multi_turn":{"rating":1007.6,"rank":394,"pct":5.5,"board_size":417},"longer_query":{"rating":982.2,"rank":395,"pct":0.5,"board_size":397},"non_english":{"rating":970,"rank":403,"pct":3.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/stripedhyena-nous-7b"},{"slug":"olmo-7b-instruct","name":"OLMo 7B Instruct","source_name":"OLMo 7B Instruct","base":"OLMo 7B Instruct","variant":null,"org":"allenai","open_weights":true,"model_license":"Apache-2.0","siscope":{"score":3.9,"rank":391,"coverage":0.75,"categories":{"coding":4.6,"reasoning":3.6,"math":4,"chat":4.5,"instructions":3.3}},"arena":{"text":{"rank":400,"date":"2026-10-28","rating":1031.8,"lo":1020.8,"hi":1042.8,"votes":6328,"pct":4.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1015.4,"rank":395,"pct":4.6,"board_size":414},"math":{"rating":1017.7,"rank":389,"pct":4,"board_size":405},"creative_writing":{"rating":989.4,"rank":402,"pct":3.6,"board_size":417},"instruction_following":{"rating":978.1,"rank":405,"pct":3.3,"board_size":419},"hard_prompts":{"rating":992.7,"rank":404,"pct":3.6,"board_size":419},"multi_turn":{"rating":1007,"rank":395,"pct":5.3,"board_size":417},"non_english":{"rating":977.2,"rank":400,"pct":4.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/olmo-7b-instruct"},{"slug":"vicuna-7b","name":"Vicuna 7B","source_name":"Vicuna 7B","base":"Vicuna 7B","variant":null,"org":"other","open_weights":true,"model_license":"Llama 2 Community","siscope":{"score":3.8,"rank":392,"coverage":0.75,"categories":{"coding":4.4,"reasoning":3.8,"math":3.2,"chat":4.3,"instructions":4.3}},"arena":{"text":{"rank":401,"date":"2026-10-28","rating":1030.9,"lo":1021.9,"hi":1040,"votes":6923,"pct":4.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1009.7,"rank":396,"pct":4.4,"board_size":414},"math":{"rating":993.8,"rank":392,"pct":3.2,"board_size":405},"creative_writing":{"rating":1020.8,"rank":399,"pct":4.3,"board_size":417},"instruction_following":{"rating":993.6,"rank":401,"pct":4.3,"board_size":419},"hard_prompts":{"rating":994.8,"rank":403,"pct":3.8,"board_size":419},"multi_turn":{"rating":987.8,"rank":400,"pct":4.1,"board_size":417},"longer_query":{"rating":1035.2,"rank":382,"pct":3.8,"board_size":397},"non_english":{"rating":1002.8,"rank":388,"pct":7.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/vicuna-7b"},{"slug":"palm-2","name":"PaLM 2","source_name":"PaLM 2","base":"PaLM 2","variant":null,"org":"google","open_weights":false,"model_license":"Proprietary","siscope":{"score":4,"rank":390,"coverage":0.75,"categories":{"coding":2.9,"reasoning":4.5,"math":6.4,"chat":4.1,"instructions":5}},"arena":{"text":{"rank":402,"date":"2026-10-28","rating":1027.2,"lo":1018,"hi":1036.4,"votes":8554,"pct":4.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":994.2,"rank":402,"pct":2.9,"board_size":414},"math":{"rating":1048.8,"rank":379,"pct":6.4,"board_size":405},"creative_writing":{"rating":991.1,"rank":401,"pct":3.8,"board_size":417},"instruction_following":{"rating":1009.9,"rank":398,"pct":5,"board_size":419},"hard_prompts":{"rating":1004.8,"rank":400,"pct":4.5,"board_size":419},"multi_turn":{"rating":994.3,"rank":397,"pct":4.8,"board_size":417},"longer_query":{"rating":1009.4,"rank":387,"pct":2.5,"board_size":397},"non_english":{"rating":915.9,"rank":409,"pct":2.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/palm-2"},{"slug":"mistral-7b-instruct","name":"Mistral 7B Instruct","source_name":"Mistral 7B Instruct","base":"Mistral 7B Instruct","variant":null,"org":"mistral","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":4.3,"rank":387,"coverage":0.75,"categories":{"coding":4.8,"reasoning":4.3,"math":4.5,"chat":3.8,"instructions":4.5}},"arena":{"text":{"rank":403,"date":"2026-10-28","rating":1023.5,"lo":1014.3,"hi":1032.6,"votes":8977,"pct":3.8,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1018.2,"rank":394,"pct":4.8,"board_size":414},"math":{"rating":1027.4,"rank":387,"pct":4.5,"board_size":405},"creative_writing":{"rating":1028.1,"rank":395,"pct":5.3,"board_size":417},"instruction_following":{"rating":1003.1,"rank":400,"pct":4.5,"board_size":419},"hard_prompts":{"rating":1001.4,"rank":401,"pct":4.3,"board_size":419},"multi_turn":{"rating":1008.1,"rank":393,"pct":5.8,"board_size":417},"longer_query":{"rating":1000.3,"rank":389,"pct":2,"board_size":397},"non_english":{"rating":943.5,"rank":405,"pct":3.3,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/mistral-7b-instruct"},{"slug":"gemma-1-1-2b-it","name":"Gemma 1.1 2B IT","source_name":"Gemma 1.1 2B IT","base":"Gemma 1.1 2B IT","variant":null,"org":"google","open_weights":true,"model_license":"Gemma license","siscope":{"score":4.6,"rank":386,"coverage":0.75,"categories":{"coding":5.3,"reasoning":4.5,"math":6.2,"chat":3.6,"instructions":4.1}},"arena":{"text":{"rank":404,"date":"2026-10-28","rating":1022.2,"lo":1014.5,"hi":1029.9,"votes":10854,"pct":3.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1033.9,"rank":392,"pct":5.3,"board_size":414},"math":{"rating":1047.2,"rank":380,"pct":6.2,"board_size":405},"creative_writing":{"rating":997.7,"rank":400,"pct":4.1,"board_size":417},"instruction_following":{"rating":991.7,"rank":402,"pct":4.1,"board_size":419},"hard_prompts":{"rating":1004.8,"rank":399,"pct":4.5,"board_size":419},"multi_turn":{"rating":958.5,"rank":404,"pct":3.1,"board_size":417},"longer_query":{"rating":1002.4,"rank":388,"pct":2.3,"board_size":397},"non_english":{"rating":988.3,"rank":394,"pct":6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemma-1-1-2b-it"},{"slug":"gemma-2b-it","name":"Gemma 2B IT","source_name":"Gemma 2B IT","base":"Gemma 2B IT","variant":null,"org":"google","open_weights":true,"model_license":"Gemma license","siscope":{"score":3.5,"rank":393,"coverage":0.75,"categories":{"coding":4.1,"reasoning":3.3,"math":3.5,"chat":3.3,"instructions":3.1}},"arena":{"text":{"rank":405,"date":"2026-10-28","rating":1002.1,"lo":990.7,"hi":1013.6,"votes":4780,"pct":3.3,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":1009.3,"rank":397,"pct":4.1,"board_size":414},"math":{"rating":1008.7,"rank":391,"pct":3.5,"board_size":405},"creative_writing":{"rating":986.1,"rank":403,"pct":3.4,"board_size":417},"instruction_following":{"rating":970.3,"rank":406,"pct":3.1,"board_size":419},"hard_prompts":{"rating":988.6,"rank":405,"pct":3.3,"board_size":419},"multi_turn":{"rating":944.8,"rank":405,"pct":2.9,"board_size":417},"longer_query":{"rating":980.4,"rank":396,"pct":0.3,"board_size":397},"non_english":{"rating":957.8,"rank":404,"pct":3.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gemma-2b-it"},{"slug":"qwen1-5-4b-chat","name":"Qwen1.5 4B Chat","source_name":"Qwen1.5-4B-Chat","base":"Qwen1.5 4B Chat","variant":null,"org":"alibaba","open_weights":true,"model_license":"Qianwen LICENSE","siscope":{"score":3.4,"rank":394,"coverage":0.75,"categories":{"coding":3.4,"reasoning":3.1,"math":4.2,"chat":3.1,"instructions":3.6}},"arena":{"text":{"rank":406,"date":"2026-10-28","rating":997.2,"lo":988,"hi":1006.4,"votes":7597,"pct":3.1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":998.5,"rank":400,"pct":3.4,"board_size":414},"math":{"rating":1025.9,"rank":388,"pct":4.2,"board_size":405},"creative_writing":{"rating":968.9,"rank":407,"pct":2.4,"board_size":417},"instruction_following":{"rating":978.3,"rank":404,"pct":3.6,"board_size":419},"hard_prompts":{"rating":976.1,"rank":406,"pct":3.1,"board_size":419},"multi_turn":{"rating":977.5,"rank":401,"pct":3.8,"board_size":417},"longer_query":{"rating":987.4,"rank":394,"pct":0.8,"board_size":397},"non_english":{"rating":979.2,"rank":399,"pct":4.8,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen1-5-4b-chat"},{"slug":"koala-13b","name":"Koala 13B","source_name":"Koala 13B","base":"Koala 13B","variant":null,"org":"other","open_weights":true,"model_license":"Non-commercial","siscope":{"score":2.5,"rank":396,"coverage":0.75,"categories":{"coding":2.4,"reasoning":2.4,"math":2.5,"chat":2.9,"instructions":2.4}},"arena":{"text":{"rank":407,"date":"2026-10-28","rating":989.6,"lo":979.9,"hi":999.3,"votes":6965,"pct":2.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":944.6,"rank":404,"pct":2.4,"board_size":414},"math":{"rating":932.4,"rank":395,"pct":2.5,"board_size":405},"creative_writing":{"rating":972.7,"rank":404,"pct":3.1,"board_size":417},"instruction_following":{"rating":943.5,"rank":409,"pct":2.4,"board_size":419},"hard_prompts":{"rating":930.3,"rank":409,"pct":2.4,"board_size":419},"multi_turn":{"rating":923.4,"rank":407,"pct":2.4,"board_size":417},"non_english":{"rating":916.1,"rank":408,"pct":2.6,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/koala-13b"},{"slug":"chatglm3-6b","name":"ChatGLM3 6B","source_name":"ChatGLM3 6B","base":"ChatGLM3 6B","variant":null,"org":"other","open_weights":true,"model_license":"Apache-2.0","siscope":{"score":2.8,"rank":395,"coverage":0.75,"categories":{"coding":2.7,"reasoning":2.9,"math":3,"chat":2.6,"instructions":2.9}},"arena":{"text":{"rank":408,"date":"2026-10-28","rating":972,"lo":960.5,"hi":983.6,"votes":4658,"pct":2.6,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":963.9,"rank":403,"pct":2.7,"board_size":414},"math":{"rating":989.1,"rank":393,"pct":3,"board_size":405},"creative_writing":{"rating":969.7,"rank":406,"pct":2.6,"board_size":417},"instruction_following":{"rating":953.9,"rank":407,"pct":2.9,"board_size":419},"hard_prompts":{"rating":953,"rank":407,"pct":2.9,"board_size":419},"multi_turn":{"rating":961.8,"rank":403,"pct":3.4,"board_size":417},"longer_query":{"rating":951.6,"rank":397,"pct":0,"board_size":397},"non_english":{"rating":917.6,"rank":407,"pct":2.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/chatglm3-6b"},{"slug":"gpt4all-13b-snoozy","name":"GPT4All 13B Snoozy","source_name":"GPT4All 13B Snoozy","base":"GPT4All 13B Snoozy","variant":null,"org":"other","open_weights":true,"model_license":"Non-commercial","siscope":{"score":null,"rank":null,"coverage":0.5,"categories":{"reasoning":2.6,"math":2.7,"chat":2.4,"instructions":2.6}},"arena":{"text":{"rank":409,"date":"2026-10-28","rating":956.2,"lo":941.2,"hi":971.2,"votes":1743,"pct":2.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"math":{"rating":940.8,"rank":394,"pct":2.7,"board_size":405},"creative_writing":{"rating":971.7,"rank":405,"pct":2.9,"board_size":417},"instruction_following":{"rating":945.3,"rank":408,"pct":2.6,"board_size":419},"hard_prompts":{"rating":936.1,"rank":408,"pct":2.6,"board_size":419},"multi_turn":{"rating":926.6,"rank":406,"pct":2.6,"board_size":417},"non_english":{"rating":879.7,"rank":412,"pct":1.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/gpt4all-13b-snoozy"},{"slug":"mpt-7b-chat","name":"MPT 7B Chat","source_name":"MPT 7B Chat","base":"MPT 7B Chat","variant":null,"org":"other","open_weights":true,"model_license":"CC-BY-NC-SA-4.0","siscope":{"score":1.6,"rank":400,"coverage":0.75,"categories":{"coding":1.7,"reasoning":1.4,"math":1.7,"chat":2.2,"instructions":2.2}},"arena":{"text":{"rank":410,"date":"2026-10-28","rating":955.2,"lo":943.5,"hi":966.9,"votes":3924,"pct":2.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":912.8,"rank":407,"pct":1.7,"board_size":414},"math":{"rating":919.2,"rank":398,"pct":1.7,"board_size":405},"creative_writing":{"rating":957.4,"rank":409,"pct":1.9,"board_size":417},"instruction_following":{"rating":906.6,"rank":410,"pct":2.2,"board_size":419},"hard_prompts":{"rating":895.4,"rank":413,"pct":1.4,"board_size":419},"multi_turn":{"rating":901.5,"rank":409,"pct":1.9,"board_size":417},"non_english":{"rating":912.2,"rank":410,"pct":2.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/mpt-7b-chat"},{"slug":"rwkv-4-raven-14b","name":"RWKV-4 Raven 14B","source_name":"RWKV-4 Raven 14B","base":"RWKV-4 Raven 14B","variant":null,"org":"other","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":1.7,"rank":398,"coverage":0.75,"categories":{"coding":2.2,"reasoning":1.7,"math":2,"chat":1.9,"instructions":1}},"arena":{"text":{"rank":411,"date":"2026-10-28","rating":948.4,"lo":937.1,"hi":959.6,"votes":4845,"pct":1.9,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":927.6,"rank":405,"pct":2.2,"board_size":414},"math":{"rating":921.9,"rank":397,"pct":2,"board_size":405},"creative_writing":{"rating":933.5,"rank":411,"pct":1.4,"board_size":417},"instruction_following":{"rating":882.4,"rank":415,"pct":1,"board_size":419},"hard_prompts":{"rating":896,"rank":412,"pct":1.7,"board_size":419},"multi_turn":{"rating":893.7,"rank":410,"pct":1.7,"board_size":417},"non_english":{"rating":924.7,"rank":406,"pct":3.1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/rwkv-4-raven-14b"},{"slug":"chatglm2-6b","name":"ChatGLM2 6B","source_name":"ChatGLM2 6B","base":"ChatGLM2 6B","variant":null,"org":"other","open_weights":true,"model_license":"Apache-2.0","siscope":{"score":1.7,"rank":399,"coverage":0.75,"categories":{"coding":1.5,"reasoning":2.2,"math":1.5,"chat":1.7,"instructions":1.9}},"arena":{"text":{"rank":412,"date":"2026-10-28","rating":938.6,"lo":925.2,"hi":952,"votes":2658,"pct":1.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":901.6,"rank":408,"pct":1.5,"board_size":414},"math":{"rating":915.1,"rank":399,"pct":1.5,"board_size":405},"creative_writing":{"rating":940.8,"rank":410,"pct":1.7,"board_size":417},"instruction_following":{"rating":902,"rank":411,"pct":1.9,"board_size":419},"hard_prompts":{"rating":916.9,"rank":410,"pct":2.2,"board_size":419},"multi_turn":{"rating":902,"rank":408,"pct":2.2,"board_size":417},"non_english":{"rating":857.2,"rank":414,"pct":1.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/chatglm2-6b"},{"slug":"alpaca-13b","name":"Alpaca 13B","source_name":"Alpaca 13B","base":"Alpaca 13B","variant":null,"org":"other","open_weights":true,"model_license":"Non-commercial","siscope":{"score":0.9,"rank":402,"coverage":0.75,"categories":{"coding":0.7,"reasoning":0.7,"math":1.2,"chat":1.4,"instructions":1.4}},"arena":{"text":{"rank":413,"date":"2026-10-28","rating":932.8,"lo":921.5,"hi":944,"votes":5745,"pct":1.4,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":798.5,"rank":411,"pct":0.7,"board_size":414},"math":{"rating":908.1,"rank":400,"pct":1.2,"board_size":405},"creative_writing":{"rating":967.3,"rank":408,"pct":2.2,"board_size":417},"instruction_following":{"rating":891.1,"rank":413,"pct":1.4,"board_size":419},"hard_prompts":{"rating":825.6,"rank":416,"pct":0.7,"board_size":419},"multi_turn":{"rating":884.3,"rank":411,"pct":1.4,"board_size":417},"non_english":{"rating":874.6,"rank":413,"pct":1.4,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/alpaca-13b"},{"slug":"chatglm-6b","name":"ChatGLM 6B","source_name":"ChatGLM 6B","base":"ChatGLM 6B","variant":null,"org":"other","open_weights":true,"model_license":"Non-commercial","siscope":{"score":1.7,"rank":397,"coverage":0.75,"categories":{"coding":1.9,"reasoning":1.9,"math":2.2,"chat":1.2,"instructions":1.7}},"arena":{"text":{"rank":414,"date":"2026-10-28","rating":918.4,"lo":906.2,"hi":930.7,"votes":4914,"pct":1.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":919.1,"rank":406,"pct":1.9,"board_size":414},"math":{"rating":925.7,"rank":396,"pct":2.2,"board_size":405},"creative_writing":{"rating":899.8,"rank":414,"pct":0.7,"board_size":417},"instruction_following":{"rating":901.7,"rank":412,"pct":1.7,"board_size":419},"hard_prompts":{"rating":900.9,"rank":411,"pct":1.9,"board_size":419},"multi_turn":{"rating":856.4,"rank":413,"pct":1,"board_size":417},"non_english":{"rating":904.7,"rank":411,"pct":1.9,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/chatglm-6b"},{"slug":"openassistant-pythia-12b","name":"OpenAssistant Pythia 12B","source_name":"OpenAssistant Pythia 12B","base":"OpenAssistant Pythia 12B","variant":null,"org":"other","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":1.1,"rank":401,"coverage":0.75,"categories":{"coding":1.2,"reasoning":1.2,"math":1,"chat":1,"instructions":1.2}},"arena":{"text":{"rank":415,"date":"2026-10-28","rating":916,"lo":905.4,"hi":926.7,"votes":6310,"pct":1,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":900,"rank":409,"pct":1.2,"board_size":414},"math":{"rating":891.9,"rank":401,"pct":1,"board_size":405},"creative_writing":{"rating":923,"rank":412,"pct":1.2,"board_size":417},"instruction_following":{"rating":887.2,"rank":414,"pct":1.2,"board_size":419},"hard_prompts":{"rating":884.5,"rank":414,"pct":1.2,"board_size":419},"multi_turn":{"rating":869.2,"rank":412,"pct":1.2,"board_size":417},"non_english":{"rating":848,"rank":415,"pct":1,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/openassistant-pythia-12b"},{"slug":"fastchat-t5-3b","name":"FastChat-T5 3B","source_name":"FastChat-T5 3B","base":"FastChat-T5 3B","variant":null,"org":"other","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":0.4,"rank":404,"coverage":0.75,"categories":{"coding":0.2,"reasoning":0.5,"math":0.5,"chat":0.7,"instructions":0.7}},"arena":{"text":{"rank":416,"date":"2026-10-28","rating":894.4,"lo":882.2,"hi":906.6,"votes":4203,"pct":0.7,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":763.6,"rank":413,"pct":0.2,"board_size":414},"math":{"rating":861.8,"rank":403,"pct":0.5,"board_size":405},"creative_writing":{"rating":901.8,"rank":413,"pct":1,"board_size":417},"instruction_following":{"rating":857.9,"rank":416,"pct":0.7,"board_size":419},"hard_prompts":{"rating":814.1,"rank":417,"pct":0.5,"board_size":419},"multi_turn":{"rating":853,"rank":414,"pct":0.7,"board_size":417},"non_english":{"rating":781.2,"rank":419,"pct":0,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/fastchat-t5-3b"},{"slug":"stablelm-tuned-alpha-7b","name":"StableLM Tuned Alpha 7B","source_name":"StableLM Tuned Alpha 7B","base":"StableLM Tuned Alpha 7B","variant":null,"org":"other","open_weights":true,"model_license":"CC-BY-NC-SA-4.0","siscope":{"score":0.6,"rank":403,"coverage":0.75,"categories":{"coding":1,"reasoning":1,"math":0.2,"chat":0.5,"instructions":0.5}},"arena":{"text":{"rank":417,"date":"2026-10-28","rating":866.5,"lo":854,"hi":879.1,"votes":3287,"pct":0.5,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":885.7,"rank":410,"pct":1,"board_size":414},"math":{"rating":839,"rank":404,"pct":0.2,"board_size":405},"creative_writing":{"rating":867.6,"rank":415,"pct":0.5,"board_size":417},"instruction_following":{"rating":830.9,"rank":417,"pct":0.5,"board_size":419},"hard_prompts":{"rating":835,"rank":415,"pct":1,"board_size":419},"multi_turn":{"rating":820.6,"rank":415,"pct":0.5,"board_size":417},"non_english":{"rating":814.5,"rank":418,"pct":0.2,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/stablelm-tuned-alpha-7b"},{"slug":"dolly-2-0-12b","name":"Dolly 2.0 12B","source_name":"Dolly 2.0 12B","base":"Dolly 2.0 12B","variant":null,"org":"other","open_weights":true,"model_license":"MIT","siscope":{"score":0.4,"rank":405,"coverage":0.75,"categories":{"coding":0.5,"reasoning":0.2,"math":0.7,"chat":0.2,"instructions":0.2}},"arena":{"text":{"rank":418,"date":"2026-10-28","rating":851.1,"lo":837.9,"hi":864.3,"votes":3412,"pct":0.2,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":776,"rank":412,"pct":0.5,"board_size":414},"math":{"rating":870.9,"rank":402,"pct":0.7,"board_size":405},"creative_writing":{"rating":863.4,"rank":416,"pct":0.2,"board_size":417},"instruction_following":{"rating":813.6,"rank":418,"pct":0.2,"board_size":419},"hard_prompts":{"rating":803.6,"rank":418,"pct":0.2,"board_size":419},"multi_turn":{"rating":740.4,"rank":417,"pct":0,"board_size":417},"non_english":{"rating":835.5,"rank":416,"pct":0.7,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/dolly-2-0-12b"},{"slug":"llama-13b","name":"LLaMA 13B","source_name":"LLaMA 13B","base":"LLaMA 13B","variant":null,"org":"meta","open_weights":true,"model_license":"Non-commercial","siscope":{"score":0,"rank":406,"coverage":0.75,"categories":{"coding":0,"reasoning":0,"math":0,"chat":0,"instructions":0}},"arena":{"text":{"rank":419,"date":"2026-10-28","rating":833.5,"lo":817.9,"hi":849,"votes":2391,"pct":0,"board_size":419,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"text_categories":{"cats":{"coding":{"rating":682.6,"rank":414,"pct":0,"board_size":414},"math":{"rating":837.8,"rank":405,"pct":0,"board_size":405},"creative_writing":{"rating":793.7,"rank":417,"pct":0,"board_size":417},"instruction_following":{"rating":780.7,"rank":419,"pct":0,"board_size":419},"hard_prompts":{"rating":727.9,"rank":419,"pct":0,"board_size":419},"multi_turn":{"rating":753.1,"rank":416,"pct":0.2,"board_size":417},"non_english":{"rating":818.4,"rank":417,"pct":0.5,"board_size":419}},"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/llama-13b"},{"slug":"claude-opus-5-5-max","name":"Claude Opus 5.5 (Max)","source_name":"Claude Opus 5.5 (Max)","base":"Claude Opus 5.5","variant":"Max","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":96.6,"rank":3,"coverage":0.85,"categories":{"coding":100,"agents":100,"reasoning":91.5,"math":97.3}},"arena":{"webdev":{"rank":1,"date":"2026-10-28","rating":1809.8,"lo":1797,"hi":1822.7,"votes":3473,"pct":100,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":1,"date":"2026-11-02","score":0.2004,"lo":0.1792,"hi":0.2215,"sessions":13954,"cost_per_task_p50":6.819,"pct":100,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9059,"stderr":0.0194,"tested_as":"claude-opus-5-5_max","approx":false,"run_date":"2026-09-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F6gmbahPSxHf9xVhAYqpnhi.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":87,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.722,"stderr":0.0142,"tested_as":"claude-opus-5-5_max","approx":false,"run_date":"2026-09-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FCgLfiGcNwMPVzxr8GdNUAK.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":96,"tested_models":100},{"benchmark":"otis_mock_aime","score":1,"stderr":0,"tested_as":"claude-opus-5-5_max","approx":false,"run_date":"2026-09-22","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FLSfona7P3jCAnZFXJ2YA7F.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":96.2,"tested_models":313},{"benchmark":"frontiermath","score":0.9123,"stderr":0.0168,"tested_as":"claude-opus-5-5_max","approx":false,"run_date":"2026-09-22","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":98.3,"tested_models":122}],"price":{"openrouter_id":"anthropic/claude-opus-5.5","input_per_m":4,"output_per_m":20,"blended_per_m":8,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-opus-5-5-max"},{"slug":"muse-wonder-full-max","name":"Muse Wonder Full (Max)","source_name":"Muse Wonder Full (Max)","base":"Muse Wonder Full","variant":"Max","org":"meta","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.5,"categories":{"coding":96,"agents":85.7}},"arena":{"webdev":{"rank":7,"date":"2026-10-28","rating":1725.3,"lo":1711.5,"hi":1739.2,"votes":2248,"pct":96,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":9,"date":"2026-11-02","score":0.0963,"lo":0.0865,"hi":0.1062,"sessions":30712,"cost_per_task_p50":null,"pct":85.7,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/muse-wonder-full-max"},{"slug":"claude-sonnet-5-5-high","name":"Claude Sonnet 5.5 (High)","source_name":"Claude Sonnet 5.5 (High)","base":"Claude Sonnet 5.5","variant":"High","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":95.4}},"arena":{"webdev":{"rank":8,"date":"2026-10-28","rating":1710.6,"lo":1701.4,"hi":1719.8,"votes":6371,"pct":95.4,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"anthropic/claude-sonnet-5.5","input_per_m":2,"output_per_m":10,"blended_per_m":4,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-sonnet-5-5-high"},{"slug":"kimi-k3-1-pro-max","name":"Kimi K3.1 Pro (Max)","source_name":"Kimi K3.1 Pro (Max)","base":"Kimi K3.1 Pro","variant":"Max","org":"moonshot","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.5,"categories":{"coding":94.7,"agents":78.6}},"arena":{"webdev":{"rank":9,"date":"2026-10-28","rating":1694.6,"lo":1681.6,"hi":1707.5,"votes":2671,"pct":94.7,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":13,"date":"2026-11-02","score":0.047,"lo":0.0338,"hi":0.0602,"sessions":16814,"cost_per_task_p50":1.468,"pct":78.6,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"moonshotai/kimi-k3.1-pro","input_per_m":2,"output_per_m":10,"blended_per_m":4,"context_length":1048576,"modalities_in":["text","image","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/kimi-k3-1-pro-max"},{"slug":"qwen3-8-max-0902","name":"Qwen3.8-Max (0902)","source_name":"Qwen3.8-Max (0902)","base":"Qwen3.8-Max","variant":"0902","org":"alibaba","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":92.1}},"arena":{"webdev":{"rank":13,"date":"2026-10-28","rating":1675.9,"lo":1669.3,"hi":1682.6,"votes":17936,"pct":92.1,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"qwen/qwen3.8-max-0902","input_per_m":2,"output_per_m":6,"blended_per_m":3,"context_length":1000000,"modalities_in":["text","image","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/qwen3-8-max-0902"},{"slug":"gpt-6-1-terra-max","name":"GPT-6.1 Terra (Max)","source_name":"GPT-6.1 Terra (Max)","base":"GPT-6.1 Terra","variant":"Max","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":90.3,"rank":18,"coverage":0.85,"categories":{"coding":91.4,"agents":87.5,"reasoning":89.6,"math":96.9}},"arena":{"webdev":{"rank":14,"date":"2026-10-28","rating":1672.7,"lo":1657.3,"hi":1688,"votes":1821,"pct":91.4,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":8,"date":"2026-11-02","score":0.1019,"lo":0.0902,"hi":0.1135,"sessions":19912,"cost_per_task_p50":0.788,"pct":87.5,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9432,"stderr":0.0149,"tested_as":"gpt-6.1-terra_max","approx":false,"run_date":"2026-10-26","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F5Jm2Rvv9sNx7M8nodinFAp.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":97.3,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.573,"stderr":0.0156,"tested_as":"gpt-6.1-terra_max","approx":false,"run_date":"2026-10-26","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FBixeio8A6SejZtUzFXFSXK.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":81.8,"tested_models":100},{"benchmark":"otis_mock_aime","score":1,"stderr":0,"tested_as":"gpt-6.1-terra_max","approx":false,"run_date":"2026-10-26","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FYnwukT2gyJHGKzPNPU9hry.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":96.2,"tested_models":313},{"benchmark":"frontiermath","score":0.9088,"stderr":0.0171,"tested_as":"gpt-6.1-terra_max","approx":false,"run_date":"2026-10-26","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":97.5,"tested_models":122}],"price":{"openrouter_id":"openai/gpt-6.1-terra","input_per_m":1,"output_per_m":5,"blended_per_m":2,"context_length":1050000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-6-1-terra-max"},{"slug":"deepseek-v4-1-flash-20261017-max","name":"DeepSeek V4.1 Flash (Max, 2026-10-17)","source_name":"DeepSeek-V4.1-Flash-20261017 (Max)","base":"DeepSeek V4.1 Flash","variant":"Max, 2026-10-17","org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":null,"rank":null,"coverage":0.5,"categories":{"coding":90.1,"agents":64.3}},"arena":{"webdev":{"rank":16,"date":"2026-10-28","rating":1665,"lo":1657,"hi":1673.1,"votes":7842,"pct":90.1,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":21,"date":"2026-11-02","score":0.0213,"lo":0.0155,"hi":0.0271,"sessions":65677,"cost_per_task_p50":0.177,"pct":64.3,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/deepseek-v4-1-flash-20261017-max"},{"slug":"hy4-preview","name":"Hy4 preview","source_name":"Hy4 preview","base":"Hy4 preview","variant":null,"org":"tencent","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":null,"rank":null,"coverage":0.5,"categories":{"coding":85.4,"agents":58.9}},"arena":{"webdev":{"rank":23,"date":"2026-10-28","rating":1631.1,"lo":1621.5,"hi":1640.8,"votes":4765,"pct":85.4,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":24,"date":"2026-11-02","score":0.0094,"lo":0.0024,"hi":0.0163,"sessions":100538,"cost_per_task_p50":0.444,"pct":58.9,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"tencent/hy4-preview","input_per_m":0.834,"output_per_m":2.501,"blended_per_m":1.2508,"context_length":1048576,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/hy4-preview"},{"slug":"qwen3-8-flash-next","name":"Qwen3.8 Flash Next","source_name":"Qwen3.8-Flash-Next","base":"Qwen3.8 Flash Next","variant":null,"org":"alibaba","open_weights":true,"model_license":"qwen-community-1.0","siscope":{"score":null,"rank":null,"coverage":0.5,"categories":{"coding":84.8,"agents":32.1}},"arena":{"webdev":{"rank":24,"date":"2026-10-28","rating":1628.3,"lo":1620.7,"hi":1635.9,"votes":9703,"pct":84.8,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":39,"date":"2026-11-02","score":-0.0433,"lo":-0.0506,"hi":-0.0361,"sessions":109490,"cost_per_task_p50":0.221,"pct":32.1,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen3-8-flash-next"},{"slug":"muse-spark-1-3-xhigh","name":"Muse Spark 1.3 (xHigh)","source_name":"Muse Spark 1.3 (xHigh)","base":"Muse Spark 1.3","variant":"xHigh","org":"meta","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.4,"categories":{"coding":82.1,"math":87.6}},"arena":{"webdev":{"rank":28,"date":"2026-10-28","rating":1620.1,"lo":1612.7,"hi":1627.5,"votes":10243,"pct":82.1,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"vision":{"rank":19,"date":"2026-10-19","rating":1301.8,"lo":1292.3,"hi":1311.3,"votes":4897,"pct":89.2,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"otis_mock_aime","score":0.9917,"stderr":0.0062,"tested_as":"muse-spark-1.3_xhigh","approx":false,"run_date":"2026-09-17","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FWmxkx5m3qaQuwzem6gzZmg.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":93.3,"tested_models":313},{"benchmark":"frontiermath","score":0.7439,"stderr":0.0259,"tested_as":"muse-spark-1.3_xhigh","approx":false,"run_date":"2026-09-16","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":81.8,"tested_models":122}],"price":{"openrouter_id":"meta/muse-spark-1.3","input_per_m":1.25,"output_per_m":4.25,"blended_per_m":2,"context_length":1048576,"modalities_in":["text","image","video","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/muse-spark-1-3-xhigh"},{"slug":"gpt-5-6-sol-xhigh-codex-harness","name":"GPT-5.6 Sol (xHigh, Codex Harness)","source_name":"GPT-5.6 Sol (xHigh, Codex Harness)","base":"GPT-5.6 Sol","variant":"xHigh, Codex Harness","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":80.1}},"arena":{"webdev":{"rank":31,"date":"2026-10-28","rating":1615.8,"lo":1610,"hi":1621.5,"votes":18884,"pct":80.1,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/gpt-5.6-sol","input_per_m":4,"output_per_m":20,"blended_per_m":8,"context_length":1050000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-6-sol-xhigh-codex-harness"},{"slug":"minimax-m3-1-flash","name":"MiniMax-M3.1 Flash","source_name":"MiniMax-M3.1-Flash","base":"MiniMax-M3.1 Flash","variant":null,"org":"minimax","open_weights":true,"model_license":"MiniMax Community License","siscope":{"score":null,"rank":null,"coverage":0.5,"categories":{"coding":75.5,"agents":35.7}},"arena":{"webdev":{"rank":38,"date":"2026-10-28","rating":1582.5,"lo":1570.9,"hi":1594,"votes":3062,"pct":75.5,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":37,"date":"2026-11-02","score":-0.0322,"lo":-0.0478,"hi":-0.0165,"sessions":12103,"cost_per_task_p50":0.242,"pct":35.7,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"minimax/minimax-m3.1-flash","input_per_m":0.075,"output_per_m":0.3,"blended_per_m":0.1312,"context_length":1048576,"modalities_in":["text","image","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/minimax-m3-1-flash"},{"slug":"deepseek-v4-flash-high","name":"DeepSeek V4 Flash (High)","source_name":"DeepSeek-V4-Flash (High)","base":"DeepSeek V4 Flash","variant":"High","org":"deepseek","open_weights":true,"model_license":"MIT","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":74.2}},"arena":{"webdev":{"rank":40,"date":"2026-10-28","rating":1581.8,"lo":1572.5,"hi":1591.1,"votes":4927,"pct":74.2,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/deepseek-v4-flash-high"},{"slug":"step-5-preview-high","name":"Step 5 Preview (High)","source_name":"Step 5 Preview (High)","base":"Step 5 Preview","variant":"High","org":"stepfun","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":72.8}},"arena":{"webdev":{"rank":42,"date":"2026-10-28","rating":1571,"lo":1562.1,"hi":1580,"votes":5966,"pct":72.8,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"stepfun/step-5-preview","input_per_m":1,"output_per_m":2.7,"blended_per_m":1.425,"context_length":1048576,"modalities_in":["text","image","video"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/step-5-preview-high"},{"slug":"muse-spark-open-max","name":"Muse Spark Open (Max)","source_name":"Muse Spark Open (Max)","base":"Muse Spark Open","variant":"Max","org":"meta","open_weights":true,"model_license":"muse-model-license","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":64.2}},"arena":{"webdev":{"rank":55,"date":"2026-10-28","rating":1526.2,"lo":1510.9,"hi":1541.5,"votes":1721,"pct":64.2,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"meta/muse-spark-open","input_per_m":1.25,"output_per_m":4.25,"blended_per_m":2,"context_length":1048576,"modalities_in":["text","image","video","file","audio"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/muse-spark-open-max"},{"slug":"gpt-5-6-terra-xhigh-codex-harness","name":"GPT-5.6 Terra (xHigh, Codex Harness)","source_name":"GPT-5.6 Terra (xHigh, Codex Harness)","base":"GPT-5.6 Terra","variant":"xHigh, Codex Harness","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":62.9}},"arena":{"webdev":{"rank":57,"date":"2026-10-28","rating":1520.1,"lo":1514,"hi":1526.2,"votes":15388,"pct":62.9,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/gpt-5.6-terra","input_per_m":2,"output_per_m":12,"blended_per_m":4.5,"context_length":1050000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-6-terra-xhigh-codex-harness"},{"slug":"seed2-1-pro-preview","name":"Seed2.1 Pro Preview","source_name":"Seed2.1 Pro Preview","base":"Seed2.1 Pro Preview","variant":null,"org":"bytedance","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":62.3}},"arena":{"webdev":{"rank":58,"date":"2026-10-28","rating":1519.1,"lo":1513.3,"hi":1524.9,"votes":16294,"pct":62.3,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/seed2-1-pro-preview"},{"slug":"gpt-5-6-luna-xhigh-codex-harness","name":"GPT-5.6 Luna (xHigh, Codex Harness)","source_name":"GPT-5.6 Luna (xHigh, Codex Harness)","base":"GPT-5.6 Luna","variant":"xHigh, Codex Harness","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":61.6}},"arena":{"webdev":{"rank":59,"date":"2026-10-28","rating":1518.9,"lo":1512.5,"hi":1525.3,"votes":12522,"pct":61.6,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/gpt-5.6-luna","input_per_m":0.2,"output_per_m":1.2,"blended_per_m":0.45,"context_length":1050000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-6-luna-xhigh-codex-harness"},{"slug":"qwen3-7-max-20260517","name":"Qwen3.7-Max (2026-05-17)","source_name":"Qwen3.7-Max (20260517)","base":"Qwen3.7-Max","variant":"2026-05-17","org":"alibaba","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":60.9}},"arena":{"webdev":{"rank":60,"date":"2026-10-28","rating":1515.1,"lo":1507.8,"hi":1522.5,"votes":8855,"pct":60.9,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen3-7-max-20260517"},{"slug":"gpt-5-5-xhigh-codex-harness","name":"GPT-5.5 (xHigh, Codex Harness)","source_name":"GPT-5.5 (xHigh, Codex Harness)","base":"GPT-5.5","variant":"xHigh, Codex Harness","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"coding":60.3,"reasoning":86.9,"math":89.3}},"arena":{"webdev":{"rank":61,"date":"2026-10-28","rating":1512.1,"lo":1506.1,"hi":1518.1,"votes":15553,"pct":60.3,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"simpleqa_verified","score":0.63,"stderr":0.0153,"tested_as":"gpt-5.5_xhigh","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FTijCafTTJUFrJ6jPGvBbgq.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":86.9,"tested_models":100},{"benchmark":"frontiermath","score":0.8526,"stderr":0.021,"tested_as":"gpt-5.5_xhigh","approx":false,"run_date":"2026-06-11","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":89.3,"tested_models":122}],"price":{"openrouter_id":"openai/gpt-5.5","input_per_m":5,"output_per_m":30,"blended_per_m":11.25,"context_length":1050000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-5-xhigh-codex-harness"},{"slug":"gpt-5-5-high-codex-harness","name":"GPT-5.5 (High, Codex Harness)","source_name":"GPT-5.5 (High, Codex Harness)","base":"GPT-5.5","variant":"High, Codex Harness","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":55.6}},"arena":{"webdev":{"rank":68,"date":"2026-10-28","rating":1486.7,"lo":1480.8,"hi":1492.6,"votes":17853,"pct":55.6,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/gpt-5.5","input_per_m":5,"output_per_m":30,"blended_per_m":11.25,"context_length":1050000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-5-high-codex-harness"},{"slug":"spark-x2-6","name":"Spark-X2.6","source_name":"Spark-X2.6","base":"Spark-X2.6","variant":null,"org":"synlan","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.5,"categories":{"coding":54.3,"agents":12.5}},"arena":{"webdev":{"rank":70,"date":"2026-10-28","rating":1482,"lo":1463.1,"hi":1500.9,"votes":1210,"pct":54.3,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"},"agent":{"rank":50,"date":"2026-11-02","score":-0.1,"lo":-0.1149,"hi":-0.0851,"sessions":8166,"cost_per_task_p50":0.098,"pct":12.5,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/spark-x2-6"},{"slug":"kimi-k2-7-code","name":"Kimi K2.7 Code","source_name":"Kimi K2.7 Code","base":"Kimi K2.7 Code","variant":null,"org":"moonshot","open_weights":true,"model_license":"Modified MIT","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"coding":52.3,"reasoning":59.8,"math":69.4}},"arena":{"webdev":{"rank":73,"date":"2026-10-28","rating":1473.5,"lo":1464.1,"hi":1483,"votes":4950,"pct":52.3,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8788,"stderr":0.0233,"tested_as":"kimi-k2.7-code","approx":false,"run_date":"2026-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FXneEig6pACkAWeekvgCwNk.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":76.2,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.365,"stderr":0.0152,"tested_as":"kimi-k2.7-code","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F5AijYw5bFJtSuahnbzNo6Z.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":43.4,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9556,"stderr":0.0311,"tested_as":"kimi-k2.7-code","approx":false,"run_date":"2026-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FENc5ZM5TpBYNKkTWN4xyQM.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":81.7,"tested_models":313},{"benchmark":"frontiermath","score":0.5404,"stderr":0.0296,"tested_as":"kimi-k2.7-code","approx":false,"run_date":"2026-06-13","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FX3RxRkt2pBUXYJjAQHsUo6.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":57,"tested_models":122}],"price":{"openrouter_id":"moonshotai/kimi-k2.7-code","input_per_m":0.6,"output_per_m":3.5,"blended_per_m":1.325,"context_length":262144,"modalities_in":["text","image"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/kimi-k2-7-code"},{"slug":"gpt-5-4-high-codex-harness","name":"GPT-5.4 (High, Codex Harness)","source_name":"GPT-5.4 (High, Codex Harness)","base":"GPT-5.4","variant":"High, Codex Harness","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"coding":64.9,"reasoning":84.3,"math":87.5}},"arena":{"webdev":{"rank":76,"date":"2026-10-28","rating":1463.5,"lo":1444.6,"hi":1482.3,"votes":1345,"pct":50.3,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.899,"stderr":0.0215,"tested_as":"gpt-5.4-2026-03-05_high","approx":false,"run_date":"2026-07-15","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FFbhcT8NnJUntcyNGubJXY6.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":84.3,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.9778,"stderr":0.0222,"tested_as":"gpt-5.4-2026-03-05_high","approx":false,"run_date":"2026-07-15","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FDpPahiEawokzgidE3cNZbS.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":87.5,"tested_models":313},{"benchmark":"swe_bench_verified","score":0.7686,"stderr":0.0192,"tested_as":"gpt-5.4-2026-03-05_high","approx":false,"run_date":"2026-03-06","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Fi9HTMbAxcwsrTf2w2FuJ6N.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":79.4,"tested_models":35}],"price":{"openrouter_id":"openai/gpt-5.4","input_per_m":2.5,"output_per_m":15,"blended_per_m":5.625,"context_length":1050000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-4-high-codex-harness"},{"slug":"gpt-5-5-codex-harness","name":"GPT-5.5 (Codex Harness)","source_name":"GPT-5.5 (Codex Harness)","base":"GPT-5.5","variant":"Codex Harness","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":49}},"arena":{"webdev":{"rank":78,"date":"2026-10-28","rating":1456.1,"lo":1450.2,"hi":1462,"votes":15811,"pct":49,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/gpt-5.5","input_per_m":5,"output_per_m":30,"blended_per_m":11.25,"context_length":1050000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-5-codex-harness"},{"slug":"gpt-5-4-medium-codex-harness","name":"GPT-5.4 (Medium, Codex Harness)","source_name":"GPT-5.4 (Medium, Codex Harness)","base":"GPT-5.4","variant":"Medium, Codex Harness","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"coding":47,"reasoning":81.3,"math":81.7}},"arena":{"webdev":{"rank":81,"date":"2026-10-28","rating":1443.6,"lo":1425.3,"hi":1461.9,"votes":1374,"pct":47,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8889,"stderr":0.0224,"tested_as":"gpt-5.4-2026-03-05_medium","approx":false,"run_date":"2026-07-15","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FManJk43Kf9VuXowNqoDrov.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":81.3,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.9556,"stderr":0.0311,"tested_as":"gpt-5.4-2026-03-05_medium","approx":false,"run_date":"2026-07-15","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FeUJNMJSdLnJWNgRY8D2rYw.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":81.7,"tested_models":313}],"price":{"openrouter_id":"openai/gpt-5.4","input_per_m":2.5,"output_per_m":15,"blended_per_m":5.625,"context_length":1050000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-4-medium-codex-harness"},{"slug":"gpt-5-medium","name":"GPT-5 (Medium)","source_name":"GPT-5 (Medium)","base":"GPT-5","variant":"Medium","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"coding":36.1,"reasoning":69.6,"math":69.6}},"arena":{"webdev":{"rank":92,"date":"2026-10-28","rating":1417.3,"lo":1401.7,"hi":1432.9,"votes":3089,"pct":39.7,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8535,"stderr":0.0213,"tested_as":"gpt-5-2025-08-07_medium","approx":false,"run_date":"2025-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FYQCwJRoGbGAqNCQoaL6cjk.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":69.6,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.8722,"stderr":0.0388,"tested_as":"gpt-5-2025-08-07_medium","approx":false,"run_date":"2025-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FctsGxm6WkzCGEqiAbJR3kk.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":69.6,"tested_models":313},{"benchmark":"swe_bench_verified","score":0.7149,"stderr":0.0205,"tested_as":"gpt-5-2025-08-07_medium","approx":false,"run_date":"2026-02-05","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FFCCkMNVHcjLLUDeNFqTGRL.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":32.4,"tested_models":35}],"price":{"openrouter_id":"openai/gpt-5","input_per_m":1.25,"output_per_m":10,"blended_per_m":3.4375,"context_length":400000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-medium"},{"slug":"gpt-5-3-codex-codex-harness","name":"GPT-5.3-Codex (Codex Harness)","source_name":"GPT-5.3-Codex (Codex Harness)","base":"GPT-5.3-Codex","variant":"Codex Harness","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":26.5}},"arena":{"webdev":{"rank":112,"date":"2026-10-28","rating":1370.9,"lo":1359.6,"hi":1382.3,"votes":3648,"pct":26.5,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/gpt-5.3-codex","input_per_m":1.75,"output_per_m":14,"blended_per_m":4.8125,"context_length":400000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-3-codex-codex-harness"},{"slug":"gpt-5-1-medium","name":"GPT-5.1 (Medium)","source_name":"GPT-5.1 (Medium)","base":"GPT-5.1","variant":"Medium","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"coding":31.8,"reasoning":69,"math":66}},"arena":{"webdev":{"rank":104,"date":"2026-10-28","rating":1395.6,"lo":1384.1,"hi":1407.2,"votes":4891,"pct":31.8,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8504,"stderr":0.0213,"tested_as":"gpt-5.1-2025-11-13_medium","approx":false,"run_date":"2025-11-17","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FV3YQtSEnQ3TPZEPPgkCKQM.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":69,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.8556,"stderr":0.0439,"tested_as":"gpt-5.1-2025-11-13_medium","approx":false,"run_date":"2025-11-17","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2Fk7inKYrGDT2LFcCiQhGfTP.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":66,"tested_models":313}],"price":{"openrouter_id":"openai/gpt-5.1","input_per_m":1.25,"output_per_m":10,"blended_per_m":3.4375,"context_length":400000,"modalities_in":["image","text","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-1-medium"},{"slug":"laguna-m-1","name":"Laguna M.1","source_name":"Laguna M.1","base":"Laguna M.1","variant":null,"org":"poolside","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":19.9}},"arena":{"webdev":{"rank":122,"date":"2026-10-28","rating":1349.2,"lo":1339.9,"hi":1358.5,"votes":5359,"pct":19.9,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/laguna-m-1"},{"slug":"gpt-5-2-codex","name":"GPT-5.2-Codex","source_name":"GPT-5.2-Codex","base":"GPT-5.2-Codex","variant":null,"org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":17.9}},"arena":{"webdev":{"rank":125,"date":"2026-10-28","rating":1338.7,"lo":1329.7,"hi":1347.6,"votes":6705,"pct":17.9,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/gpt-5.2-codex","input_per_m":1.75,"output_per_m":14,"blended_per_m":4.8125,"context_length":400000,"modalities_in":["text","image"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-2-codex"},{"slug":"gpt-5-1-codex","name":"GPT-5.1-Codex","source_name":"GPT-5.1-Codex","base":"GPT-5.1-Codex","variant":null,"org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":17.2}},"arena":{"webdev":{"rank":126,"date":"2026-10-28","rating":1337.1,"lo":1325.5,"hi":1348.7,"votes":4981,"pct":17.2,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/gpt-5.1-codex","input_per_m":1.25,"output_per_m":10,"blended_per_m":3.4375,"context_length":400000,"modalities_in":["text","image"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-1-codex"},{"slug":"laguna-xs-2","name":"Laguna XS.2","source_name":"Laguna XS.2","base":"Laguna XS.2","variant":null,"org":"poolside","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":13.9}},"arena":{"webdev":{"rank":131,"date":"2026-10-28","rating":1302.4,"lo":1291.7,"hi":1313.2,"votes":4204,"pct":13.9,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/laguna-xs-2"},{"slug":"kat-coder-pro-v1","name":"KAT-Coder-Pro V1","source_name":"KAT-Coder-Pro V1","base":"KAT-Coder-Pro V1","variant":null,"org":"other","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":9.3}},"arena":{"webdev":{"rank":138,"date":"2026-10-28","rating":1255.8,"lo":1236.3,"hi":1275.3,"votes":1503,"pct":9.3,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/kat-coder-pro-v1"},{"slug":"gpt-5-1-codex-mini","name":"GPT-5.1-Codex-Mini","source_name":"GPT-5.1-Codex-Mini","base":"GPT-5.1-Codex-Mini","variant":null,"org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":7.3}},"arena":{"webdev":{"rank":141,"date":"2026-10-28","rating":1243.5,"lo":1221.5,"hi":1265.6,"votes":1154,"pct":7.3,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/gpt-5.1-codex-mini","input_per_m":0.25,"output_per_m":2,"blended_per_m":0.6875,"context_length":400000,"modalities_in":["image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-5-1-codex-mini"},{"slug":"devstral-2","name":"Devstral 2","source_name":"Devstral 2","base":"Devstral 2","variant":null,"org":"mistral","open_weights":true,"model_license":"Modified MIT","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":3.3}},"arena":{"webdev":{"rank":147,"date":"2026-10-28","rating":1197.1,"lo":1176.4,"hi":1217.9,"votes":1182,"pct":3.3,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/devstral-2"},{"slug":"grok-code-fast-1","name":"Grok Code Fast 1","source_name":"Grok Code Fast 1","base":"Grok Code Fast 1","variant":null,"org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":1.3}},"arena":{"webdev":{"rank":150,"date":"2026-10-28","rating":1166.3,"lo":1138.1,"hi":1194.6,"votes":789,"pct":1.3,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/grok-code-fast-1"},{"slug":"devstral-medium-2507","name":"Devstral Medium (2507)","source_name":"Devstral Medium (2507)","base":"Devstral Medium","variant":"2507","org":"mistral","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"coding":0}},"arena":{"webdev":{"rank":152,"date":"2026-10-28","rating":1071.4,"lo":1040.8,"hi":1102,"votes":842,"pct":0,"board_size":152,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/devstral-medium-2507"},{"slug":"ernie-5-0-preview-1220","name":"ERNIE-5.0-Preview (1220)","source_name":"ERNIE-5.0-Preview (1220)","base":"ERNIE-5.0-Preview","variant":"1220","org":"baidu","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":65,"date":"2026-10-19","rating":1248.5,"lo":1237.3,"hi":1259.6,"votes":3349,"pct":61.4,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/ernie-5-0-preview-1220"},{"slug":"qwen-vl-max-2025-08-13","name":"Qwen-VL-Max (2025-08-13)","source_name":"Qwen-VL-Max (2025-08-13)","base":"Qwen-VL-Max","variant":"2025-08-13","org":"alibaba","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":87,"date":"2026-10-19","rating":1212.6,"lo":1200.6,"hi":1224.6,"votes":3170,"pct":48.2,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen-vl-max-2025-08-13"},{"slug":"qwen2-5-vl-32b-instruct","name":"Qwen2.5 VL 32B Instruct","source_name":"Qwen2.5-VL-32B-Instruct","base":"Qwen2.5 VL 32B Instruct","variant":null,"org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":119,"date":"2026-10-19","rating":1152.2,"lo":1136.8,"hi":1167.5,"votes":1490,"pct":28.9,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen2-5-vl-32b-instruct"},{"slug":"step-1o-vision-32k-high-res","name":"Step-1o Vision 32K (High Res)","source_name":"Step-1o Vision 32K (High Res)","base":"Step-1o Vision 32K","variant":"High Res","org":"stepfun","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":127,"date":"2026-10-19","rating":1121.8,"lo":1109.2,"hi":1134.5,"votes":2833,"pct":24.1,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/step-1o-vision-32k-high-res"},{"slug":"qwen2-5-vl-72b-instruct","name":"Qwen2.5 VL 72B Instruct","source_name":"Qwen2.5-VL-72B-Instruct","base":"Qwen2.5 VL 72B Instruct","variant":null,"org":"alibaba","open_weights":true,"model_license":"Qwen","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":130,"date":"2026-10-19","rating":1107.4,"lo":1096.5,"hi":1118.3,"votes":3768,"pct":22.3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"qwen/qwen2.5-vl-72b-instruct","input_per_m":0.8,"output_per_m":1,"blended_per_m":0.85,"context_length":128000,"modalities_in":["text","image"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/qwen2-5-vl-72b-instruct"},{"slug":"pixtral-large-2411","name":"Pixtral Large (2411)","source_name":"Pixtral Large (2411)","base":"Pixtral Large","variant":"2411","org":"mistral","open_weights":true,"model_license":"MRL","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":134,"date":"2026-10-19","rating":1089.4,"lo":1080.1,"hi":1098.7,"votes":5423,"pct":19.9,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/pixtral-large-2411"},{"slug":"qwen-vl-max-1119","name":"Qwen-VL-Max (1119)","source_name":"Qwen-VL-Max (1119)","base":"Qwen-VL-Max","variant":"1119","org":"alibaba","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":140,"date":"2026-10-19","rating":1057.6,"lo":1041.4,"hi":1073.8,"votes":1422,"pct":16.3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen-vl-max-1119"},{"slug":"qwen2-vl-72b","name":"Qwen2 VL 72B","source_name":"Qwen2-VL-72B","base":"Qwen2 VL 72B","variant":null,"org":"alibaba","open_weights":true,"model_license":"Qwen","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":141,"date":"2026-10-19","rating":1047,"lo":1036.7,"hi":1057.2,"votes":5937,"pct":15.7,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen2-vl-72b"},{"slug":"step-1v-32k","name":"Step-1V 32K","source_name":"Step-1V 32K","base":"Step-1V 32K","variant":null,"org":"stepfun","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":142,"date":"2026-10-19","rating":1046,"lo":1029.3,"hi":1062.7,"votes":1534,"pct":15.1,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/step-1v-32k"},{"slug":"molmo-72b-0924","name":"Molmo 72B (0924)","source_name":"Molmo 72B (0924)","base":"Molmo 72B","variant":"0924","org":"allenai","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":145,"date":"2026-10-19","rating":1012.3,"lo":999.2,"hi":1025.4,"votes":3048,"pct":13.3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/molmo-72b-0924"},{"slug":"pixtral-12b-2409","name":"Pixtral 12B (2409)","source_name":"Pixtral 12B (2409)","base":"Pixtral 12B","variant":"2409","org":"mistral","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":146,"date":"2026-10-19","rating":1008.6,"lo":999,"hi":1018.1,"votes":7511,"pct":12.7,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/pixtral-12b-2409"},{"slug":"internvl2-26b","name":"InternVL2 26B","source_name":"InternVL2 26B","base":"InternVL2 26B","variant":null,"org":"other","open_weights":true,"model_license":"MIT","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":148,"date":"2026-10-19","rating":1004.6,"lo":991.8,"hi":1017.4,"votes":5148,"pct":11.4,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/internvl2-26b"},{"slug":"llama-3-2-90b-vision-instruct","name":"Llama 3.2 90B Vision Instruct","source_name":"Llama 3.2 90B Vision Instruct","base":"Llama 3.2 90B Vision Instruct","variant":null,"org":"meta","open_weights":true,"model_license":"Llama 3.2","siscope":{"score":null,"rank":null,"coverage":0.35,"categories":{"reasoning":15.1,"math":7.1}},"arena":{"vision":{"rank":149,"date":"2026-10-19","rating":999.7,"lo":990.4,"hi":1008.9,"votes":8682,"pct":10.8,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.4104,"stderr":0.0229,"tested_as":"Llama-3.2-90B-Vision-Instruct","approx":false,"run_date":"2025-01-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F9SSHEP95FYVZvHDdoHSRy3.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":15.1,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.0264,"stderr":0.0094,"tested_as":"Llama-3.2-90B-Vision-Instruct","approx":false,"run_date":"2025-02-25","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FLHRL6nQJZXGJmYppR7kbGw.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":7.1,"tested_models":313}],"price":null,"url":"https://siscope.app/models/llama-3-2-90b-vision-instruct"},{"slug":"hunyuan-standard-vision-2024-12-31","name":"Hunyuan Standard Vision (2024-12-31)","source_name":"Hunyuan Standard Vision (2024-12-31)","base":"Hunyuan Standard Vision","variant":"2024-12-31","org":"tencent","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":150,"date":"2026-10-19","rating":999.1,"lo":977.7,"hi":1020.5,"votes":809,"pct":10.2,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/hunyuan-standard-vision-2024-12-31"},{"slug":"aya-vision-32b","name":"Aya Vision 32B","source_name":"Aya Vision 32B","base":"Aya Vision 32B","variant":null,"org":"cohere","open_weights":true,"model_license":"CC-BY-NC-4.0","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":151,"date":"2026-10-19","rating":995.6,"lo":973.6,"hi":1017.6,"votes":847,"pct":9.6,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/aya-vision-32b"},{"slug":"qwen2-vl-7b-instruct","name":"Qwen2 VL 7B Instruct","source_name":"Qwen2-VL-7B-Instruct","base":"Qwen2 VL 7B Instruct","variant":null,"org":"alibaba","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":153,"date":"2026-10-19","rating":989.9,"lo":979.4,"hi":1000.5,"votes":5766,"pct":8.4,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/qwen2-vl-7b-instruct"},{"slug":"yi-vision","name":"Yi Vision","source_name":"Yi Vision","base":"Yi Vision","variant":null,"org":"other","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":156,"date":"2026-10-19","rating":977.7,"lo":959.6,"hi":995.9,"votes":1219,"pct":6.6,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/yi-vision"},{"slug":"llama-3-2-11b-vision-instruct","name":"Llama 3.2 11B Vision Instruct","source_name":"Llama 3.2 11B Vision Instruct","base":"Llama 3.2 11B Vision Instruct","variant":null,"org":"meta","open_weights":true,"model_license":"Llama 3.2","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":157,"date":"2026-10-19","rating":966.4,"lo":955.1,"hi":977.7,"votes":4817,"pct":6,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/llama-3-2-11b-vision-instruct"},{"slug":"molmo-7b-d-0924","name":"Molmo 7B-D (0924)","source_name":"Molmo 7B-D (0924)","base":"Molmo 7B-D","variant":"0924","org":"allenai","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":158,"date":"2026-10-19","rating":958.7,"lo":944.9,"hi":972.5,"votes":2815,"pct":5.4,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/molmo-7b-d-0924"},{"slug":"internvl2-4b","name":"InternVL2 4B","source_name":"InternVL2 4B","base":"InternVL2 4B","variant":null,"org":"other","open_weights":true,"model_license":"MIT","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":160,"date":"2026-10-19","rating":941.3,"lo":928.8,"hi":953.9,"votes":3703,"pct":4.2,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/internvl2-4b"},{"slug":"nvila-internal-15b-v1","name":"NVILA Internal 15B v1","source_name":"nvila-internal-15b-v1","base":"NVILA Internal 15B v1","variant":null,"org":"nvidia","open_weights":false,"model_license":"-","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":161,"date":"2026-10-19","rating":940.2,"lo":920.3,"hi":960.1,"votes":1077,"pct":3.6,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/nvila-internal-15b-v1"},{"slug":"llava-1-6-34b","name":"LLaVA 1.6 34B","source_name":"LLaVA 1.6 34B","base":"LLaVA 1.6 34B","variant":null,"org":"other","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":162,"date":"2026-10-19","rating":936.5,"lo":924.2,"hi":948.7,"votes":4531,"pct":3,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/llava-1-6-34b"},{"slug":"cogvlm2-llama3-chat-19b","name":"CogVLM2 Llama3 Chat 19B","source_name":"CogVLM2 Llama3 Chat 19B","base":"CogVLM2 Llama3 Chat 19B","variant":null,"org":"zai","open_weights":true,"model_license":"CogVLM2","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":163,"date":"2026-10-19","rating":927.6,"lo":912.3,"hi":942.8,"votes":1991,"pct":2.4,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/cogvlm2-llama3-chat-19b"},{"slug":"llava-onevision-qwen2-72b-ov","name":"LLaVA-OneVision Qwen2 72B OV","source_name":"LLaVA-OneVision Qwen2 72B OV","base":"LLaVA-OneVision Qwen2 72B OV","variant":null,"org":"other","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":164,"date":"2026-10-19","rating":922.8,"lo":904.8,"hi":940.8,"votes":1321,"pct":1.8,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/llava-onevision-qwen2-72b-ov"},{"slug":"minicpm-v-2-6","name":"MiniCPM-V 2.6","source_name":"MiniCPM-V 2.6","base":"MiniCPM-V 2.6","variant":null,"org":"other","open_weights":true,"model_license":"Apache 2.0","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":165,"date":"2026-10-19","rating":911.6,"lo":895.7,"hi":927.6,"votes":1987,"pct":1.2,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/minicpm-v-2-6"},{"slug":"phi-3-5-vision-instruct","name":"Phi-3.5 Vision Instruct","source_name":"Phi-3.5 Vision Instruct","base":"Phi-3.5 Vision Instruct","variant":null,"org":"microsoft","open_weights":true,"model_license":"MIT","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":166,"date":"2026-10-19","rating":851.5,"lo":835.7,"hi":867.3,"votes":2592,"pct":0.6,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/phi-3-5-vision-instruct"},{"slug":"phi-3-vision-128k-instruct","name":"Phi-3 Vision 128K Instruct","source_name":"Phi-3 Vision 128K Instruct","base":"Phi-3 Vision 128K Instruct","variant":null,"org":"microsoft","open_weights":true,"model_license":"MIT","siscope":{"score":null,"rank":null,"coverage":0,"categories":{}},"arena":{"vision":{"rank":167,"date":"2026-10-19","rating":811.7,"lo":793,"hi":830.5,"votes":1401,"pct":0,"board_size":167,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":null,"url":"https://siscope.app/models/phi-3-vision-128k-instruct"},{"slug":"claude-sonnet-5-5-max","name":"Claude Sonnet 5.5 (Max)","source_name":"Claude Sonnet 5.5 (Max)","base":"Claude Sonnet 5.5","variant":"Max","org":"anthropic","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"agents":96.4,"reasoning":81,"math":95.2}},"arena":{"agent":{"rank":3,"date":"2026-11-02","score":0.1462,"lo":0.1183,"hi":0.174,"sessions":8436,"cost_per_task_p50":3.941,"pct":96.4,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9558,"stderr":0.0137,"tested_as":"claude-sonnet-5-5_max","approx":false,"run_date":"2026-09-29","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FQPk8jbJvo4986sbWtdte6J.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":99.4,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.465,"stderr":0.0158,"tested_as":"claude-sonnet-5-5_max","approx":false,"run_date":"2026-09-29","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FGtJ5yd3ZPQ7HVcm6Q9ssQz.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":62.6,"tested_models":100},{"benchmark":"otis_mock_aime","score":1,"stderr":0,"tested_as":"claude-sonnet-5-5_max","approx":false,"run_date":"2026-09-29","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FbSEaZLPehiNVDQL7HP9EJS.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":96.2,"tested_models":313},{"benchmark":"frontiermath","score":0.8877,"stderr":0.0187,"tested_as":"claude-sonnet-5-5_max","approx":false,"run_date":"2026-09-29","log_url":null,"source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":94.2,"tested_models":122}],"price":{"openrouter_id":"anthropic/claude-sonnet-5.5","input_per_m":2,"output_per_m":10,"blended_per_m":4,"context_length":1000000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/claude-sonnet-5-5-max"},{"slug":"grok-4-6-xhigh","name":"Grok 4.6 (xHigh)","source_name":"Grok 4.6 (xHigh)","base":"Grok 4.6","variant":"xHigh","org":"xai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"agents":48.2,"reasoning":81.7,"math":82.2}},"arena":{"agent":{"rank":30,"date":"2026-11-02","score":0.0032,"lo":-0.0082,"hi":0.0147,"sessions":30344,"cost_per_task_p50":1.688,"pct":48.2,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9318,"stderr":0.0152,"tested_as":"grok-4.6_xhigh","approx":false,"run_date":"2026-08-14","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F9YJf2nviwjM6WVhw8qeJta.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":93.7,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.489,"stderr":0.0158,"tested_as":"grok-4.6_xhigh","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FdKCWFaoGCWJTnD5CPWQGru.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":69.7,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9917,"stderr":0.0047,"tested_as":"grok-4.6_xhigh","approx":false,"run_date":"2026-08-14","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F7crLvnfQc987dC6mr3iGbf.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":93.3,"tested_models":313},{"benchmark":"frontiermath","score":0.6596,"stderr":0.0281,"tested_as":"grok-4.6_xhigh","approx":false,"run_date":"2026-08-14","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FZb2AKwa942D7dBTTcebAba.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":71.1,"tested_models":122}],"price":{"openrouter_id":"x-ai/grok-4.6","input_per_m":2,"output_per_m":6,"blended_per_m":3,"context_length":500000,"modalities_in":["text","image","file"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/grok-4-6-xhigh"},{"slug":"gpt-6-luna-medium","name":"GPT-6 Luna (Medium)","source_name":"GPT-6 Luna (Medium)","base":"GPT-6 Luna","variant":"Medium","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"agents":41.1}},"arena":{"agent":{"rank":34,"date":"2026-11-02","score":-0.0193,"lo":-0.0249,"hi":-0.0137,"sessions":60580,"cost_per_task_p50":0.027,"pct":41.1,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/gpt-6-luna","input_per_m":0.1,"output_per_m":0.5,"blended_per_m":0.2,"context_length":1050000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-6-luna-medium"},{"slug":"gpt-6-luna-low","name":"GPT-6 Luna (Low)","source_name":"GPT-6 Luna (Low)","base":"GPT-6 Luna","variant":"Low","org":"openai","open_weights":false,"model_license":"Proprietary","siscope":{"score":null,"rank":null,"coverage":0.25,"categories":{"agents":26.8}},"arena":{"agent":{"rank":42,"date":"2026-11-02","score":-0.0587,"lo":-0.066,"hi":-0.0514,"sessions":39811,"cost_per_task_p50":0.01,"pct":26.8,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[],"price":{"openrouter_id":"openai/gpt-6-luna","input_per_m":0.1,"output_per_m":0.5,"blended_per_m":0.2,"context_length":1050000,"modalities_in":["file","image","text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/gpt-6-luna-low"},{"slug":"qwen3-7-max","name":"Qwen3.7-Max","source_name":"Qwen3.7-Max","base":"Qwen3.7-Max","variant":null,"org":"alibaba","open_weights":false,"model_license":"Proprietary","siscope":{"score":57.8,"rank":147,"coverage":0.85,"categories":{"coding":82.4,"agents":23.2,"reasoning":83.4,"math":74.8}},"arena":{"agent":{"rank":44,"date":"2026-11-02","score":-0.0667,"lo":-0.0787,"hi":-0.0547,"sessions":43216,"cost_per_task_p50":0.353,"pct":23.2,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.9091,"stderr":0.0205,"tested_as":"qwen3.7-max","approx":false,"run_date":"2026-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FW6mTanyjvXhasFBzHukv4S.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":88,"tested_models":333},{"benchmark":"simpleqa_verified","score":0.5577,"stderr":0.0157,"tested_as":"qwen3.7-max","approx":false,"run_date":"2026-08-27","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FDMjUrG6eZEqwcQ4SqUoViu.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":78.8,"tested_models":100},{"benchmark":"otis_mock_aime","score":0.9556,"stderr":0.0311,"tested_as":"qwen3.7-max","approx":false,"run_date":"2026-08-07","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FD3YDUZSfEUDsS4frLbEKDu.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":81.7,"tested_models":313},{"benchmark":"frontiermath","score":0.6456,"stderr":0.0284,"tested_as":"qwen3.7-max","approx":false,"run_date":"2026-06-13","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FRG2biwnmGybSVTVxxMdRWa.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":67.8,"tested_models":122},{"benchmark":"swe_bench_verified","score":0.7727,"stderr":0.0191,"tested_as":"qwen3.7-max","approx":false,"run_date":"2026-06-18","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2F83hhDhcT9UUrZ2NiUbWSUU.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":82.4,"tested_models":35}],"price":{"openrouter_id":"qwen/qwen3.7-max","input_per_m":1.475,"output_per_m":4.425,"blended_per_m":2.2125,"context_length":1000000,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/qwen3-7-max"},{"slug":"nemotron-3-ultra","name":"Nemotron 3 Ultra","source_name":"Nemotron 3 Ultra","base":"Nemotron 3 Ultra","variant":null,"org":"nvidia","open_weights":true,"model_license":"OpenMDW-1.1","siscope":{"score":null,"rank":null,"coverage":0.6,"categories":{"agents":7.1,"reasoning":69.6,"math":67.3}},"arena":{"agent":{"rank":53,"date":"2026-11-02","score":-0.156,"lo":-0.1882,"hi":-0.1239,"sessions":13650,"cost_per_task_p50":0.15,"pct":7.1,"board_size":57,"source":"arena","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:39:46Z"}},"epoch":[{"benchmark":"gpqa_diamond","score":0.8535,"stderr":0.0252,"tested_as":"nemotron-3-ultra","approx":false,"run_date":"2026-08-10","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FbpZy8tAbh7UV6A6U7XZtBg.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":69.6,"tested_models":333},{"benchmark":"otis_mock_aime","score":0.8667,"stderr":0.0512,"tested_as":"nemotron-3-ultra","approx":false,"run_date":"2026-08-10","log_url":"https://logs.epoch.ai/inspect-viewer/36231d6d/viewer.html?log_file=https%3A%2F%2Flogs.epoch.ai%2Finspect_ai_logs%2FWYTWr3Xk4qxymhMsm7vRQ2.eval","source":"epoch","license":"CC-BY-4.0","fetched_at":"2026-11-04T00:26:01Z","pct":67.3,"tested_models":313}],"price":{"openrouter_id":"nvidia/nemotron-3-ultra-550b-a55b","input_per_m":0.6,"output_per_m":2.4,"blended_per_m":1.05,"context_length":262144,"modalities_in":["text"],"as_of":"2026-11-04T00:26:02Z","source":"openrouter","license":"OpenRouter API terms; cite source","fetched_at":"2026-11-04T00:26:02Z"},"url":"https://siscope.app/models/nemotron-3-ultra"}]}