Noometry

Model comparison

Grok-3 mini vs o3

o3 is the stronger model overall, scoring 47.5 to 41.2 on the Noometry Index.

Last verified . 35 shared benchmarks.

Grok-3 mini xAI

41.2

Rank #141 Confirmed

o3 OpenAI

47.5

Rank #61 Confirmed

Summary

  • They share 35 benchmarks with published results for both. Grok-3 mini scores higher in 1 category and o3 in 7 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where o3 leads 32.0 to 13.6.
  • The biggest single-benchmark swing is ARC-AGI-1: 16.5% for Grok-3 mini and 60.8% for o3.

Side by side

Grok-3 minio3
ProviderxAIOpenAI
Noometry Index41.247.5
Released2025-04-092025-04-16
WeightsProprietaryProprietary
Context window—200K
Max output—100K
Input $ / M tokens—$2
Output $ / M tokens—$8
Results tracked3563

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

Category by category

Coding o3 leads

Grok-3 mini: 40.8 (#131), o3: 46.8 (#64)

BenchmarkGrok-3 minio3
Aider Polyglot49.3%81.3%
WeirdML42.6%52.4%
LMArena Coding13791408
SWE-bench Verified—62.3%
SWE-bench Verified (bash only)—58.4%
GSO—8.8%
CadEval—74%
ALE-Bench—933.55

Agentic & Tool Use Not comparable

Grok-3 mini: —, o3: 34.5 (#44)

BenchmarkGrok-3 minio3
Berkeley Function Calling Leaderboard—63%
GDPval—30.8%
DeepResearch Bench—45.2%
OSWorld—23%
LMArena Search—1144
METR Time Horizons—65.4%

Reasoning o3 leads

Grok-3 mini: 13.6 (#334), o3: 32.0 (#78)

BenchmarkGrok-3 minio3
ARC-AGI-20.4%6.5%
Kagi LLM Benchmark61.3%67.6%
ARC-AGI-116.5%60.8%
LMArena Hard Prompts13751402
Epoch Capabilities Index140.35146.86
SimpleBench—53.1%
CritPt—1.4%
Chess Puzzles—38%
EnigmaEval—13.1%
Mystery Game Puzzles—29%
DTBench—84.8%
LMCA—39.7%
ForecastBench—62.5

Math o3 leads

Grok-3 mini: 42.1 (#85), o3: 50.2 (#58)

BenchmarkGrok-3 minio3
OTIS Mock AIME 2024-202577.8%84.4%
Omni-MATH31.8%71.4%
LMArena Math13861426
MATH Level 590.9%97.8%
FrontierMath (Feb 2025 set)5.9%18.7%
FrontierMath (Tiers 1-3)—33.3%
FrontierMath Tier 4 (v1)—2.1%

Knowledge o3 leads

Grok-3 mini: 46.4 (#81), o3: 54.6 (#52)

BenchmarkGrok-3 minio3
GPQA Diamond76.3%81.8%
MMLU-Pro79.9%85.9%
Confabulations10.8%14.4%
GPQA (HELM)67.5%75.3%
LMArena Expert13951402
Humanity's Last Exam—20.3%
SimpleQA Verified—49.4%

Multimodal Not comparable

Grok-3 mini: —, o3: 41.4 (#36)

BenchmarkGrok-3 minio3
LMArena Vision—1214
GeoBench—74%
VPCT—52%

Multilingual o3 leads

Grok-3 mini: 48.1 (#145), o3: 51.7 (#105)

BenchmarkGrok-3 minio3
LMArena Non-English13521401
LMArena Chinese13871437
LMArena French13571430
LMArena German13491420
LMArena Japanese13421403
LMArena Korean13351370
LMArena Russian13531406
LMArena Spanish13811395

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.5 (#9), o3: 72.8 (#127)

BenchmarkGrok-3 minio3
IFEval95.1%86.9%
LMArena Instruction Following13571368

Long Context o3 leads

Grok-3 mini: 41.0 (#147), o3: 53.3 (#6)

BenchmarkGrok-3 minio3
Fiction.LiveBench66.7%88.9%
LMArena Longer Query13721372
CL-bench—17.8%

Writing & Preference o3 leads

Grok-3 mini: 52.5 (#169), o3: 63.5 (#64)

BenchmarkGrok-3 minio3
LMArena Text13701410
LMArena Creative Writing13421359
Short-Story Creative Writing73.5%83.9%
WildBench65.1%86.1%
LMArena Multi-Turn13551405
EQ-Bench Creative Writing—1676

Frequently asked questions

Is Grok-3 mini better than o3?

o3 is the stronger model overall, scoring 47.5 to 41.2 on the Noometry Index.

Is Grok-3 mini or o3 better for coding?

o3 scores higher on coding benchmarks: 46.8 versus 40.8 in the Noometry coding category.

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

35 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and o3 has 63.

Related comparisons

Go deeper