Noometry

Model comparison

Grok-3 mini vs MiniMax-M3

MiniMax-M3 is the stronger model overall, scoring 43.8 to 41.2 on the Noometry Index.

Last verified . 20 shared benchmarks.

Grok-3 mini xAI

41.2

Rank #141 Confirmed

MiniMax-M3 MiniMax

43.8

Rank #85 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Grok-3 mini scores higher in 2 categories and MiniMax-M3 in 6 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where MiniMax-M3 leads 30.1 to 13.6.
  • The biggest single-benchmark swing is GPQA Diamond: 76.3% for Grok-3 mini and 90.9% for MiniMax-M3.
  • MiniMax-M3 has downloadable open weights; the other is API-only.

Side by side

Grok-3 miniMiniMax-M3
ProviderxAIMiniMax
Noometry Index41.243.8
Released2025-04-092026-06-01
WeightsProprietaryOpen
Context window—1M
Max output—512K
Input $ / M tokens—$0.30
Output $ / M tokens—$1.20
Results tracked3541

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), MiniMax-M3: 41.8 (#118)

BenchmarkGrok-3 miniMiniMax-M3
LMArena Coding13791469
FrontierCode—14.7%
Aider Polyglot49.3%—
LMArena WebDev—1482
SciCode—47.1%
WeirdML42.6%—
ALE-Bench—640.02

Agentic & Tool Use Not comparable

Grok-3 mini: —, MiniMax-M3: 22.6 (#130)

BenchmarkGrok-3 miniMiniMax-M3
APEX-Agents—37.7%
OSWorld 2.0—4.6%
GBAEval—0.9%
Vending-Bench 2—2,158

Reasoning MiniMax-M3 leads

Grok-3 mini: 13.6 (#334), MiniMax-M3: 30.1 (#87)

BenchmarkGrok-3 miniMiniMax-M3
LMArena Hard Prompts13751447
Epoch Capabilities Index140.35146.95
ARC-AGI-20.4%—
SimpleBench—45.8%
Kagi LLM Benchmark61.3%—
NYT Connections (extended)—65.1%
ARC-AGI-116.5%—
CritPt—3.7%
Chess Puzzles—14%
Mystery Game Puzzles—8%
DTBench—78.9%
LMCA—33.7%
Surface Evolver Bench—55%
ForecastBench—61.4

Math Grok-3 mini leads

Grok-3 mini: 42.1 (#85), MiniMax-M3: 40.0 (#95)

BenchmarkGrok-3 miniMiniMax-M3
OTIS Mock AIME 2024-202577.8%71.1%
LMArena Math13861429
ProofBench—18%
Omni-MATH31.8%—
MATH Level 590.9%—
FrontierMath (Feb 2025 set)5.9%—

Knowledge MiniMax-M3 leads

Grok-3 mini: 46.4 (#81), MiniMax-M3: 58.4 (#35)

BenchmarkGrok-3 miniMiniMax-M3
GPQA Diamond76.3%90.9%
LMArena Expert13951461
MMLU-Pro79.9%—
Confabulations10.8%—
GPQA (HELM)67.5%—

Multimodal Not comparable

Grok-3 mini: —, MiniMax-M3: 40.2 (#51)

BenchmarkGrok-3 miniMiniMax-M3
LMArena Vision—1253
LMArena Document—1435

Multilingual MiniMax-M3 leads

Grok-3 mini: 48.1 (#145), MiniMax-M3: 53.0 (#75)

BenchmarkGrok-3 miniMiniMax-M3
LMArena Non-English13521420
LMArena Chinese13871463
LMArena French13571447
LMArena German13491426
LMArena Japanese13421381
LMArena Korean13351372
LMArena Russian13531428
LMArena Spanish13811432

Instruction Following Grok-3 mini leads

Grok-3 mini: 78.5 (#9), MiniMax-M3: 75.5 (#62)

BenchmarkGrok-3 miniMiniMax-M3
LMArena Instruction Following13571433
IFEval95.1%—

Long Context MiniMax-M3 leads

Grok-3 mini: 41.0 (#147), MiniMax-M3: 44.2 (#72)

BenchmarkGrok-3 miniMiniMax-M3
LMArena Longer Query13721445
Fiction.LiveBench66.7%—

Writing & Preference MiniMax-M3 leads

Grok-3 mini: 52.5 (#169), MiniMax-M3: 62.1 (#83)

BenchmarkGrok-3 miniMiniMax-M3
LMArena Text13701433
LMArena Creative Writing13421404
LMArena Multi-Turn13551442
Short-Story Creative Writing73.5%—
WildBench65.1%—
EQ-Bench 4—1150

Frequently asked questions

Is Grok-3 mini better than MiniMax-M3?

MiniMax-M3 is the stronger model overall, scoring 43.8 to 41.2 on the Noometry Index.

Is Grok-3 mini or MiniMax-M3 better for coding?

They score almost the same on coding (40.8 vs 41.8); test both on your own repository before choosing.

How many benchmarks do Grok-3 mini and MiniMax-M3 share?

20 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and MiniMax-M3 has 41.

Related comparisons

Go deeper