supermarket

Language

Grok 3 Mini

By SpaceXAI (xAI), in the Grok family.

Released
17 Feb 2025
Status
Retired
Context
131.1K
Max output
8.2K
Input per 1M tokens
$0.30
Output per 1M tokens
$0.50
Open weights
No
License
proprietary
Parameters
—
Knowledge cutoff
Nov 2024
Reasoning
Yes
Modalities
text → text

Category scores

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

Category scores
CategoryScoreRankCoverage
Coding & software engineering49.3Not ranked1 of 5
Human preference44.8Not ranked1 of 5

Benchmark results

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

Scientific reasoning

Scientific reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GPQA DiamondAccuracy76.3%Independentlow10 Apr 2025Epoch AI
GPQA DiamondAccuracy75.5%Independenthigh26 May 2025Epoch AI

Mathematics

Mathematics results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
FrontierMath Tiers 1-3 (v1)Accuracy5.9%Independenthigh10 Apr 2025Epoch AI
FrontierMath Tiers 1-3 (v1)Accuracy2.8%Independentlow10 Apr 2025Epoch AI
MATH Level 5Accuracy90.9%Independentlow10 Apr 2025Epoch AI
MATH Level 5Accuracy88.1%Independenthigh10 Apr 2025Epoch AI
OTIS Mock AIME 2024-2025Accuracy77.8%Independenthigh10 Apr 2025Epoch AI
OTIS Mock AIME 2024-2025Accuracy62.2%Independentlow10 Apr 2025Epoch AI

Coding & software engineering

Coding & software engineering results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Aider PolyglotPercent correct49.3%Third partyhigh—https://aider.chat/docs/leaderboards/ via Epoch AI
Aider PolyglotPercent correct34.7%Third partylow—https://aider.chat/docs/leaderboards/ via Epoch AI
WeirdML (v2)Average accuracy42.6%Third partyhigh—WeirdML Leaderboard via Epoch AI
WeirdML (v2)Average accuracy42.6%Third partyhigh—WeirdML Leaderboard via Epoch AI

Long context

Long context results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Fiction.LiveBench% correct at 16K tokens (Epoch's column)66.7%Third partymedium—Fiction.live leaderboard via Epoch AI

Writing

Writing results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
LLM Creative Story-Writing Benchmark V1 (Lech Mazur)Mean rubric score (percent of the 10-point scale)73.5%Third partylow—lechmazur/writing Github repository via Epoch AI

Human preference

Human preference results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Text Arena (arena.ai)Arena score (Elo scale)1364Independenthigh25 Sep 2026Arena
Text Arena (arena.ai)Arena score (Elo scale)1358Independent—25 Sep 2026Arena
Text Arena (arena.ai)Votes20813Independent—25 Sep 2026Arena
Text Arena (arena.ai)Votes15505Independenthigh25 Sep 2026Arena

Other Grok versions

Sources