The Model Index
Up to four models

o3-mini vs Grok-3 mini

On the index (GPT-4 = 100), o3-mini scores 131 and Grok-3 mini 131. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to o3-mini
Presets
o3-mini
131115–147
WeightsClosed
ReleasedJan 2025
Price in / out–
Context–
Core tests taken3 of 9
Grok-3 mini
131115–146
WeightsClosed
ReleasedApr 2025
Price in / out–
Context–
Core tests taken2 of 9

o3-mini and Grok-3 mini are too close to call (1 point apart, within the uncertainty), ahead on 2 of 2 shared core tests.

Test by testthird-party results

o3-miniGrok-3 mini
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)GPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProFiction.LiveBenchFiction.LiveBenchMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)MATH (level 5)MATH (level 5)MATH 500MATH 500MGSMMGSMFrontierMath (2025 set)FrontierMath (2025 set)CODINGAider PolyglotAider PolyglotLiveCodeBenchLiveCodeBenchWeirdMLWeirdMLPROFESSIONAL WORKCorpFin v2CorpFin v2LegalBenchLegalBenchTaxEval v2TaxEval v2NOVEL PROBLEMSARC-AGI-2ARC-AGI-2ARC-AGI-1ARC-AGI-1
Every result as a table
Testo3-miniGrok-3 mini
Reasoning & knowledge
GPQA Diamond (Epoch AI)77.0%76.3%
GPQA Diamond (Vals AI)75.5%79.3%
MMLU Pro78.7%81.4%
Fiction.LiveBench50.0%66.7%
Maths
AIME-style maths (OTIS mock)76.9%77.8%
MATH (level 5)96.5%90.9%
MATH 50091.8%94.2%
MGSM91.3%90.4%
FrontierMath (2025 set)12.4%5.9%
Coding
Aider Polyglot60.4%49.3%
LiveCodeBench71.5%76.2%
WeirdML43.8%42.6%
Professional work
CorpFin v245.3%61.1%
LegalBench71.5%83.1%
TaxEval v269.4%73.0%
Novel problems
ARC-AGI-23.0%0.4%
ARC-AGI-134.5%16.5%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG