Skip to content
Leaderboard / OpenAI

GPT-6.1 Sol

OpenAI Max CLOSED Proprietary
Verdict

GPT-6.1 Sol is a top-tier model: #9 of 406 by SIscope score. Strong at everything it's been tested on, especially math. On the pricey side: costs more than 77% of priced models.

SIscope score
93
#9 of 406
Human-vote rank
#62
of 419 · score 1446
Price per 1M tokens, blended
$4
$2 in · $10 out
Context window
1.1M
1,050,000 tokens

Shape

Each spoke is a category, 0 at the centre, 100 at the edge.

CodingAgentsReasoningMathChatInstructions

Category scores

Percentiles: 90 means better than about 90% of tested models.

Coding93
Agents & tools91
Reasoning & knowledge95
Math96
Chat quality85
Following instructions93

What goes into each category · Compare with DeepSeek V4.1 Flash

Human-vote score over time

Text arena, recent updates.

143514431450Oct 20: 1443.4 (rank #66)Oct 22: 1444.1 (rank #66)Oct 28: 1445.6 (rank #62)Oct 20Oct 28

Coding votes over time

WebDev arena, recent updates.

174517531760Oct 16: 1755.5 (rank #4)Oct 18: 1754.3 (rank #4)Oct 19: 1753.1 (rank #4)Oct 22: 1749 (rank #4)Oct 23: 1749.3 (rank #4)Oct 27: 1751.6 (rank #4)Oct 28: 1750.6 (rank #5)Oct 16Oct 28

Independent test runs

Run by Epoch AI on the same harness for every model. Bars show the share of questions answered correctly.

GPQA Diamond95%
PhD-level science multiple choice questions
Better than 99% of 333 tested models. Run Sep 29, 2026.
SimpleQA Verified74%
Short factual questions; rewards not making things up
Better than 98% of 100 tested models. Run Sep 29, 2026.
OTIS Mock AIME 2024-25100%
Competition maths problems in the style of AIME
Better than 96% of 313 tested models. Run Sep 29, 2026.
FrontierMath Tiers 1-394%
Very hard, unpublished research-style maths problems
Better than 99% of 122 tested models. Run Sep 29, 2026.

Human-vote arenas

People compare two anonymous answers and pick the better one. Scores work like chess ratings.

ArenaRankScoreRange (95%)VotesUpdated
Text arena
Everyday chat, blind human votes
#62 of 41914461439–14539,367Oct 28, 2026
WebDev arena
Building web apps, blind human votes
#5 of 15217511739–17624,092Oct 28, 2026
Vision arena
Questions about images, blind human votes
#29 of 16712881275–13012,330Oct 19, 2026
Agent arena
Real multi-step agent sessions
#6 of 5712.2%11.2–13.3%29,814Nov 2, 2026

Source: Arena (formerly LMArena) leaderboard dataset, CC BY 4.0. Fetched Nov 4, 2026.

Price

Input
$2
per 1M tokens
Output
$10
per 1M tokens
Blended
$4
3 in : 1 out, per 1M
Context window
1.1M
max tokens per request
Speed
Coming soon
our own tests

List price from the OpenRouter models API (openai/gpt-6.1-sol), Nov 4, 2026. Providers can charge differently.