Noometry

Model comparison

Grok-3 mini vs o3-mini

Grok-3 mini is the stronger model overall, scoring 41.2 to 36.7 on the Noometry Index.

Last verified . 29 shared benchmarks.

Grok-3 mini xAI

41.2

Rank #141 Confirmed

o3-mini OpenAI

36.7

Rank #212 Confirmed

Summary

  • They share 29 benchmarks with published results for both. Grok-3 mini scores higher in 6 categories and o3-mini in 2 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok-3 mini leads 42.1 to 28.1.
  • The biggest single-benchmark swing is ARC-AGI-1: 16.5% for Grok-3 mini and 34.5% for o3-mini.

Side by side

Grok-3 minio3-mini
ProviderxAIOpenAI
Noometry Index41.236.7
Released2025-04-092024-12-20
WeightsProprietaryProprietary
Context window—200K
Max output—100K
Input $ / M tokens—$1.10
Output $ / M tokens—$4.40
Results tracked3551

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), o3-mini: 40.8 (#132)

BenchmarkGrok-3 minio3-mini
Aider Polyglot49.3%60.4%
WeirdML42.6%43.7%
LMArena Coding13791378
SciCode—39.8%
GSO—1.3%
LiveBench Coding—82.7%
CadEval—54%

Agentic & Tool Use Not comparable

Grok-3 mini: —, o3-mini: 29.6 (#84)

BenchmarkGrok-3 minio3-mini
Cybench—22.5%

Reasoning o3-mini leads

Grok-3 mini: 13.6 (#334), o3-mini: 16.3 (#305)

BenchmarkGrok-3 minio3-mini
ARC-AGI-20.4%3%
ARC-AGI-116.5%34.5%
LMArena Hard Prompts13751366
Epoch Capabilities Index140.35140.34
SimpleBench—22.8%
Kagi LLM Benchmark61.3%—
CritPt—0.3%
Chess Puzzles—17%
LiveBench Reasoning—89.6%
Mystery Game Puzzles—7%
DTBench—68.8%
LiveBench Data Analysis—70.6%
LMCA—19%
ForecastBench—59.6
LiveBench—75.9%

Math Grok-3 mini leads

Grok-3 mini: 42.1 (#85), o3-mini: 28.1 (#244)

BenchmarkGrok-3 minio3-mini
OTIS Mock AIME 2024-202577.8%76.9%
LMArena Math13861396
MATH Level 590.9%96.5%
FrontierMath (Feb 2025 set)5.9%12.4%
FrontierMath (Tiers 1-3)—18.6%
FrontierMath Tier 4—0%
Omni-MATH31.8%—
LiveBench Math—77.3%
FrontierMath Tier 4 (v1)—4.2%

Knowledge Grok-3 mini leads

Grok-3 mini: 46.4 (#81), o3-mini: 38.3 (#146)

BenchmarkGrok-3 minio3-mini
GPQA Diamond76.3%77%
Confabulations10.8%17.9%
LMArena Expert13951364
SimpleQA Verified—15.3%
MMLU-Pro79.9%—
GPQA (HELM)67.5%—

Multilingual Grok-3 mini leads

Grok-3 mini: 48.1 (#145), o3-mini: 45.7 (#164)

BenchmarkGrok-3 minio3-mini
LMArena Non-English13521319
LMArena Chinese13871379
LMArena French13571334
LMArena German13491303
LMArena Japanese13421286
LMArena Korean13351314
LMArena Russian13531304
LMArena Spanish13811321

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.5 (#9), o3-mini: 75.1 (#72)

BenchmarkGrok-3 minio3-mini
LMArena Instruction Following13571337
LiveBench Instruction Following—84.4%
IFEval95.1%—

Long Context Grok-3 mini leads

Grok-3 mini: 41.0 (#147), o3-mini: 33.8 (#256)

BenchmarkGrok-3 minio3-mini
Fiction.LiveBench66.7%50%
LMArena Longer Query13721343

Writing & Preference Grok-3 mini leads

Grok-3 mini: 52.5 (#169), o3-mini: 50.3 (#182)

BenchmarkGrok-3 minio3-mini
LMArena Text13701337
LMArena Creative Writing13421286
Short-Story Creative Writing73.5%61.7%
LMArena Multi-Turn13551320
WildBench65.1%—
LiveBench Language—50.7%

Frequently asked questions

Is Grok-3 mini better than o3-mini?

Grok-3 mini is the stronger model overall, scoring 41.2 to 36.7 on the Noometry Index.

Is Grok-3 mini or o3-mini better for coding?

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

How many benchmarks do Grok-3 mini and o3-mini share?

29 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and o3-mini has 51.

Related comparisons

Go deeper