Released
12 Aug 2026
Status
Legacy
Context
500K
Max output
—
Input per 1M tokens
$2.00
Output per 1M tokens
$6.00
Open weights
No
License
proprietary
Parameters
—
Knowledge cutoff
—
Reasoning
Yes
Modalities
text, image → text

Category scores

Out of 100, from independent and third-party results only, by method category-2026-09-29.1.

Category scores
CategoryScoreRankCoverage
Knowledge & reasoning48.9194 of 4
Coding & software engineering57.7Not ranked2 of 5
Factuality & hallucination49.3241 of 1
Human preference64.813 of 5

Benchmark results

Every result we hold for this model, with who ran it and where it was published.

Knowledge & reasoning

Knowledge & reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Chess PuzzlesPuzzles solved40.0%Independenthigh12 Aug 2026Epoch AI
Chess PuzzlesPuzzles solved31.0%Independentxhigh14 Aug 2026Epoch AI
DTBench (Decision Theory Benchmark)Accuracy (capability questions)97.3%Third partyxhigh—https://conceptualreasoning.ai/dtbench via Epoch AI
Earthborne Rangers (EBR-bench)Objectives reached30.5%Independentxhigh18 Aug 2026Epoch AI
LMCA (Language Model Conceptual Argumentation)Correlation with expert ratings (Pearson r)0.4845Third partyxhigh—https://conceptualreasoning.ai/lmca via Epoch AI
Mystery Game PuzzlesPuzzles solved34.0%Independentxhigh14 Aug 2026Epoch AI
SimpleBenchScore (AVG@5)75.9%Third partyunknown—https://lmcouncil.ai/benchmarks via Epoch AI

Scientific reasoning

Scientific reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GPQA DiamondAccuracy94.0%Independenthigh12 Aug 2026Epoch AI
GPQA DiamondAccuracy93.2%Independentxhigh14 Aug 2026Epoch AI

Mathematics

Mathematics results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
FrontierMath Tier 4Accuracy31.7%Independentxhigh14 Aug 2026Epoch AI
FrontierMath Tiers 1-3Accuracy66.0%Independentxhigh14 Aug 2026Epoch AI
OTIS Mock AIME 2024-2025Accuracy99.2%Independentxhigh14 Aug 2026Epoch AI
OTIS Mock AIME 2024-2025Accuracy97.8%Independenthigh12 Aug 2026Epoch AI

Coding & software engineering

Coding & software engineering results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
DeepSWEPass@167.5%Third partymedium—https://deepswe.datacurve.ai/ via Epoch AI
DeepSWEPass@166.7%Third partyxhigh—https://deepswe.datacurve.ai/ via Epoch AI
DeepSWEPass@165.2%Third partyhigh—https://deepswe.datacurve.ai/ via Epoch AI
DeepSWEPass@141.6%Third partylow—https://deepswe.datacurve.ai/ via Epoch AI
FrontierCodeMain score (Mean@5)48.0%Third partyunknown—https://cognition.com/frontiercode via Epoch AI
WeirdML (v2)Average accuracy67.3%Third partyhigh—https://htihle.github.io/weirdml.html via Epoch AI

Professional knowledge work

Professional knowledge work results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
APEX-AgentsPass@1 (all rubric criteria met)65.3%Source not statedunknown—Epoch AI via Epoch AI

Vision & multimodal understanding

Vision & multimodal understanding results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Furniture AssemblyScore40.0%Independentxhigh24 Sep 2026Epoch AI

Factuality & hallucination

Factuality & hallucination results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
SimpleQA VerifiedAccuracy (% correct)49.3%Independenthigh27 Aug 2026Epoch AI
SimpleQA VerifiedAccuracy (% correct)48.9%Independentxhigh27 Aug 2026Epoch AI

Human preference

Human preference results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Code Arena: WebDev (arena.ai)Arena score (Elo scale)1621Independenthigh25 Sep 2026Arena
Code Arena: WebDev (arena.ai)Votes7040Independenthigh25 Sep 2026Arena
Document Arena (arena.ai)Arena score (Elo scale)1461Independenthigh13 Sep 2026Arena
Document Arena (arena.ai)Votes2258Independenthigh13 Sep 2026Arena
Text Arena (arena.ai)Arena score (Elo scale)1453Independenthigh25 Sep 2026Arena
Text Arena (arena.ai)Votes21380Independenthigh25 Sep 2026Arena
Vision Arena (arena.ai)Arena score (Elo scale)1263Independenthigh28 Sep 2026Arena
Vision Arena (arena.ai)Votes5374Independenthigh28 Sep 2026Arena

Other Grok versions

Sources