Noometry

Model comparison

Grok-3 mini vs o4-mini

Grok-3 mini and o4-mini score almost the same on the Noometry Index (41.2 vs 41.6), so choose on price, context window or the category you care about most.

Last verified . 35 shared benchmarks.

Grok-3 mini xAI

41.2

Rank #141 Confirmed

o4-mini OpenAI

41.6

Rank #132 Confirmed

Summary

  • They share 35 benchmarks with published results for both. Grok-3 mini scores higher in 4 categories and o4-mini in 4 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where o4-mini leads 24.6 to 13.6.
  • The biggest single-benchmark swing is ARC-AGI-1: 16.5% for Grok-3 mini and 58.7% for o4-mini.

Side by side

Grok-3 minio4-mini
ProviderxAIOpenAI
Noometry Index41.241.6
Released2025-04-092025-04-16
WeightsProprietaryProprietary
Context window—200K
Max output—100K
Input $ / M tokens—$1.10
Output $ / M tokens—$4.40
Results tracked3560

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Too close to call

Grok-3 mini: 40.8 (#131), o4-mini: 40.9 (#127)

BenchmarkGrok-3 minio4-mini
Aider Polyglot49.3%72%
WeirdML42.6%52.6%
LMArena Coding13791368
SWE-bench Verified (bash only)—45%
GSO—3.6%
CadEval—62%
ALE-Bench—826.17
AlgoTune—1.72

Agentic & Tool Use Not comparable

Grok-3 mini: —, o4-mini: 32.6 (#61)

BenchmarkGrok-3 minio4-mini
Berkeley Function Calling Leaderboard—53.2%
GDPval—25.3%
METR Time Horizons—63.9%

Reasoning o4-mini leads

Grok-3 mini: 13.6 (#334), o4-mini: 24.6 (#162)

BenchmarkGrok-3 minio4-mini
ARC-AGI-20.4%6.1%
Kagi LLM Benchmark61.3%67.6%
ARC-AGI-116.5%58.7%
LMArena Hard Prompts13751351
Epoch Capabilities Index140.35145.64
SimpleBench—38.7%
CritPt—0.6%
Chess Puzzles—26%
EnigmaEval—9.2%
Mystery Game Puzzles—5%
DTBench—77.6%
LMCA—26.5%
ForecastBench—61.8

Math Grok-3 mini leads

Grok-3 mini: 42.1 (#85), o4-mini: 40.8 (#89)

BenchmarkGrok-3 minio4-mini
OTIS Mock AIME 2024-202577.8%81.7%
Omni-MATH31.8%72%
LMArena Math13861389
MATH Level 590.9%97.8%
FrontierMath (Feb 2025 set)5.9%24.8%
FrontierMath (Tiers 1-3)—36.1%
FrontierMath Tier 4—4.9%
FrontierMath Tier 4 (v1)—6.3%

Knowledge Grok-3 mini leads

Grok-3 mini: 46.4 (#81), o4-mini: 43.6 (#91)

BenchmarkGrok-3 minio4-mini
GPQA Diamond76.3%79.6%
MMLU-Pro79.9%82%
Confabulations10.8%15.8%
GPQA (HELM)67.5%73.5%
LMArena Expert13951343
Humanity's Last Exam—18.1%
SimpleQA Verified—19.6%
Vectara Hallucination Rate—18.6%

Multimodal Not comparable

Grok-3 mini: —, o4-mini: 40.2 (#49)

BenchmarkGrok-3 minio4-mini
LMArena Vision—1194
GeoBench—64%
VPCT—57.5%

Multilingual Grok-3 mini leads

Grok-3 mini: 48.1 (#145), o4-mini: 47.0 (#154)

BenchmarkGrok-3 minio4-mini
LMArena Non-English13521337
LMArena Chinese13871354
LMArena French13571364
LMArena German13491336
LMArena Japanese13421308
LMArena Korean13351312
LMArena Russian13531334
LMArena Spanish13811347

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.5 (#9), o4-mini: 75.2 (#68)

BenchmarkGrok-3 minio4-mini
IFEval95.1%92.8%
LMArena Instruction Following13571321

Long Context o4-mini leads

Grok-3 mini: 41.0 (#147), o4-mini: 45.5 (#33)

BenchmarkGrok-3 minio4-mini
Fiction.LiveBench66.7%77.8%
LMArena Longer Query13721315

Writing & Preference o4-mini leads

Grok-3 mini: 52.5 (#169), o4-mini: 54.0 (#152)

BenchmarkGrok-3 minio4-mini
LMArena Text13701353
LMArena Creative Writing13421294
Short-Story Creative Writing73.5%75%
WildBench65.1%85.4%
LMArena Multi-Turn13551350

Frequently asked questions

Is Grok-3 mini better than o4-mini?

Grok-3 mini and o4-mini score almost the same on the Noometry Index (41.2 vs 41.6), so choose on price, context window or the category you care about most.

Is Grok-3 mini or o4-mini better for coding?

They score almost the same on coding (40.8 vs 40.9); test both on your own repository before choosing.

How many benchmarks do Grok-3 mini and o4-mini share?

35 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and o4-mini has 60.

Related comparisons

Go deeper