Skip to content
Leaderboard / xAI

Grok 4.7

xAI xHigh CLOSED Proprietary
Verdict

Grok 4.7 is a solid mid-pack model: #67 of 406 by SIscope score. Strongest at reasoning & knowledge, weaker at chat quality. Mid-range on price.

SIscope score
74
#67 of 406
Human-vote rank
#158
of 419 · score 1398
Price per 1M tokens, blended
$3
$2 in · $6 out
Context window
500K
500,000 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.

Coding76
Agents & tools73
Reasoning & knowledge79
Math71
Chat quality62
Following instructions73

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

Human-vote score over time

Text arena, recent updates.

139013981405Oct 20: 1399 (rank #156)Oct 22: 1398 (rank #158)Oct 28: 1398.1 (rank #158)Oct 20Oct 28

Coding votes over time

WebDev arena, recent updates.

163016381645Oct 16: 1638.7 (rank #16)Oct 18: 1638.2 (rank #17)Oct 19: 1637 (rank #18)Oct 22: 1636.6 (rank #18)Oct 23: 1637.9 (rank #19)Oct 27: 1637.2 (rank #21)Oct 28: 1637.5 (rank #21)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 Diamond93%
PhD-level science multiple choice questions
Better than 92% of 333 tested models. Run Sep 22, 2026.
SimpleQA Verified56%
Short factual questions; rewards not making things up
Better than 80% of 100 tested models. Run Sep 22, 2026.
OTIS Mock AIME 2024-2598%
Competition maths problems in the style of AIME
Better than 90% of 313 tested models. Run Sep 22, 2026.
FrontierMath Tiers 1-353%
Very hard, unpublished research-style maths problems
Better than 56% of 122 tested models. Run Sep 22, 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
#158 of 41913981392–140416,442Oct 28, 2026
WebDev arena
Building web apps, blind human votes
#21 of 15216381629–16466,572Oct 28, 2026
Vision arena
Questions about images, blind human votes
#79 of 16712311220–12423,736Oct 19, 2026
Agent arena
Real multi-step agent sessions
#16 of 572.6%1.2–4.1%18,788Nov 2, 2026

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

Price

Input
$2
per 1M tokens
Output
$6
per 1M tokens
Blended
$3
3 in : 1 out, per 1M
Context window
500K
max tokens per request
Speed
Coming soon
our own tests

List price from the OpenRouter models API (x-ai/grok-4.7), Nov 4, 2026. Providers can charge differently.