Noometry

Model comparison

Grok 3 vs o4-mini

o4-mini is the stronger model overall, scoring 41.6 to 39.9 on the Noometry Index.

Last verified . 38 shared benchmarks.

Grok 3 xAI

39.9

Rank #157 Confirmed

o4-mini OpenAI

41.6

Rank #132 Confirmed

Summary

  • They share 38 benchmarks with published results for both. Grok 3 scores higher in 4 categories and o4-mini in 5 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where o4-mini leads 24.6 to 13.7.
  • The biggest single-benchmark swing is ARC-AGI-1: 5.5% for Grok 3 and 58.7% for o4-mini.

Side by side

Grok 3o4-mini
ProviderxAIOpenAI
Noometry Index39.941.6
Released2025-04-092025-04-16
WeightsProprietaryProprietary
Context window—200K
Max output—100K
Input $ / M tokens—$1.10
Output $ / M tokens—$4.40
Results tracked4060

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

Category by category

Coding Too close to call

Grok 3: 41.9 (#115), o4-mini: 40.9 (#127)

BenchmarkGrok 3o4-mini
Aider Polyglot53.3%72%
WeirdML37.2%52.6%
LMArena Coding14321368
SWE-bench Verified (bash only)—45%
GSO—3.6%
CadEval—62%
ALE-Bench—826.17
AlgoTune—1.72

Agentic & Tool Use o4-mini leads

Grok 3: 30.5 (#76), o4-mini: 32.6 (#61)

BenchmarkGrok 3o4-mini
Berkeley Function Calling Leaderboard—53.2%
GDPval—25.3%
BALROG29.5%—
METR Time Horizons—63.9%

Reasoning o4-mini leads

Grok 3: 13.7 (#333), o4-mini: 24.6 (#162)

BenchmarkGrok 3o4-mini
ARC-AGI-20%6.1%
SimpleBench36.1%38.7%
Kagi LLM Benchmark61.3%67.6%
ARC-AGI-15.5%58.7%
LMArena Hard Prompts14341351
Epoch Capabilities Index138.33145.64
CritPt—0.6%
Chess Puzzles—26%
EnigmaEval—9.2%
Mystery Game Puzzles—5%
DTBench—77.6%
LMCA—26.5%
ForecastBench—61.8

Math o4-mini leads

Grok 3: 38.0 (#145), o4-mini: 40.8 (#89)

BenchmarkGrok 3o4-mini
OTIS Mock AIME 2024-202555.6%81.7%
Omni-MATH46.4%72%
LMArena Math13911389
MATH Level 588.7%97.8%
FrontierMath (Feb 2025 set)3.8%24.8%
FrontierMath Tier 4 (v1)0%6.3%
FrontierMath (Tiers 1-3)—36.1%
FrontierMath Tier 4—4.9%

Knowledge Grok 3 leads

Grok 3: 46.2 (#82), o4-mini: 43.6 (#91)

BenchmarkGrok 3o4-mini
GPQA Diamond75.8%79.6%
MMLU-Pro78.8%82%
Confabulations14.2%15.8%
Vectara Hallucination Rate5.8%18.6%
GPQA (HELM)65%73.5%
LMArena Expert14211343
Humanity's Last Exam—18.1%
SimpleQA Verified—19.6%

Multimodal Not comparable

Grok 3: —, o4-mini: 40.2 (#49)

BenchmarkGrok 3o4-mini
LMArena Vision—1194
GeoBench—64%
VPCT—57.5%

Multilingual Grok 3 leads

Grok 3: 52.3 (#87), o4-mini: 47.0 (#154)

BenchmarkGrok 3o4-mini
LMArena Non-English14101337
LMArena Chinese14481354
LMArena French14601364
LMArena German14311336
LMArena Japanese13871308
LMArena Korean13731312
LMArena Russian14161334
LMArena Spanish14171347

Instruction Following Too close to call

Grok 3: 75.0 (#73), o4-mini: 75.2 (#68)

BenchmarkGrok 3o4-mini
IFEval88.4%92.8%
LMArena Instruction Following14091321

Long Context o4-mini leads

Grok 3: 38.7 (#192), o4-mini: 45.5 (#33)

BenchmarkGrok 3o4-mini
Fiction.LiveBench58.3%77.8%
LMArena Longer Query14391315

Writing & Preference Grok 3 leads

Grok 3: 55.8 (#141), o4-mini: 54.0 (#152)

BenchmarkGrok 3o4-mini
LMArena Text14261353
LMArena Creative Writing14141294
Short-Story Creative Writing76.4%75%
WildBench84.9%85.4%
LMArena Multi-Turn14251350
EQ-Bench Creative Writing1186—

Frequently asked questions

Is Grok 3 better than o4-mini?

o4-mini is the stronger model overall, scoring 41.6 to 39.9 on the Noometry Index.

Is Grok 3 or o4-mini better for coding?

They score almost the same on coding (41.9 vs 40.9); test both on your own repository before choosing.

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

38 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and o4-mini has 60.

Related comparisons

Go deeper