Noometry

Model comparison

Grok 4 vs MiniMax-M3

Grok 4 is the stronger model overall, scoring 47.8 to 43.5 on the Noometry Index.

Last verified . 24 shared benchmarks.

Grok 4 xAI

47.8

Rank #49 Confirmed

MiniMax-M3 MiniMax

43.5

Rank #81 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Grok 4 scores higher in 6 categories and MiniMax-M3 in 4 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in long context, where Grok 4 leads 63.1 to 44.2.
  • The biggest single-benchmark swing is SimpleBench: 60.5% for Grok 4 and 45.8% for MiniMax-M3.
  • MiniMax-M3 has downloadable open weights; the other is API-only.

Side by side

Grok 4MiniMax-M3
ProviderxAIMiniMax
Noometry Index47.843.5
Released2025-07-092026-06-01
WeightsProprietaryOpen
Context window—1M
Max output—512K
Input $ / M tokens—$0.30
Output $ / M tokens—$1.20
Results tracked4841

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

Category by category

Coding Grok 4 leads

Grok 4: 49.9 (#44), MiniMax-M3: 41.5 (#111)

BenchmarkGrok 4MiniMax-M3
LMArena Coding14081470
FrontierCode—14.7%
Aider Polyglot79.6%—
LMArena WebDev—1482
SciCode—47.1%
WeirdML45.7%—
ALE-Bench—640.02

Agentic & Tool Use Grok 4 leads

Grok 4: 32.1 (#62), MiniMax-M3: 22.5 (#121)

BenchmarkGrok 4MiniMax-M3
Terminal-Bench27.2%—
APEX-Agents—37.7%
Berkeley Function Calling Leaderboard63%—
OSWorld 2.0—4.6%
GDPval21.1%—
Cybench43%—
DeepResearch Bench47.3%—
BALROG43.6%—
GBAEval—0.9%
LMArena Search1142—
METR Time Horizons66.6%—
Vending-Bench 2—2,158

Reasoning Grok 4 leads

Grok 4: 36.9 (#59), MiniMax-M3: 29.3 (#83)

BenchmarkGrok 4MiniMax-M3
SimpleBench60.5%45.8%
Chess Puzzles28%14%
LMArena Hard Prompts14091447
Epoch Capabilities Index146.46147
ForecastBench60.961.4
ARC-AGI-216%—
Kagi LLM Benchmark73.6%—
NYT Connections (extended)—65.1%
ARC-AGI-166.7%—
CritPt—3.7%
Mystery Game Puzzles—8%
DTBench—78.9%
LMCA—33.7%
Surface Evolver Bench—55%

Math Grok 4 leads

Grok 4: 46.5 (#58), MiniMax-M3: 39.1 (#83)

BenchmarkGrok 4MiniMax-M3
OTIS Mock AIME 2024-202584%71.1%
LMArena Math14221432
ProofBench—18%
Omni-MATH60.3%—
FrontierMath (Feb 2025 set)19.7%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge MiniMax-M3 leads

Grok 4: 53.7 (#50), MiniMax-M3: 58.4 (#32)

BenchmarkGrok 4MiniMax-M3
GPQA Diamond87%90.9%
LMArena Expert14171462
MMLU-Pro85.1%—
Confabulations12.4%—
GPQA (HELM)72.7%—

Multimodal MiniMax-M3 leads

Grok 4: 33.1 (#89), MiniMax-M3: 39.5 (#45)

BenchmarkGrok 4MiniMax-M3
LMArena Vision12111254
GeoBench45%—
LMArena Document—1435

Multilingual MiniMax-M3 leads

Grok 4: 52.0 (#98), MiniMax-M3: 53.2 (#70)

BenchmarkGrok 4MiniMax-M3
LMArena Non-English14031420
LMArena Chinese14281465
LMArena French14181445
LMArena German14291424
LMArena Japanese13961381
LMArena Korean13761372
LMArena Russian14091430
LMArena Spanish14191431

Instruction Following Grok 4 leads

Grok 4: 79.4 (#4), MiniMax-M3: 75.7 (#56)

BenchmarkGrok 4MiniMax-M3
LMArena Instruction Following13871433
IFEval94.9%—

Long Context Grok 4 leads

Grok 4: 63.1 (#4), MiniMax-M3: 44.2 (#68)

BenchmarkGrok 4MiniMax-M3
LMArena Longer Query14091445
Fiction.LiveBench94.4%—

Writing & Preference MiniMax-M3 leads

Grok 4: 58.7 (#111), MiniMax-M3: 62.3 (#79)

BenchmarkGrok 4MiniMax-M3
LMArena Text14121433
LMArena Creative Writing13971405
LMArena Multi-Turn14161441
Short-Story Creative Writing76.9%—
WildBench79.7%—
EQ-Bench 4—1150

Frequently asked questions

Is Grok 4 better than MiniMax-M3?

Grok 4 is the stronger model overall, scoring 47.8 to 43.5 on the Noometry Index.

Is Grok 4 or MiniMax-M3 better for coding?

Grok 4 scores higher on coding benchmarks: 49.9 versus 41.5 in the Noometry coding category.

How many benchmarks do Grok 4 and MiniMax-M3 share?

24 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and MiniMax-M3 has 41.

Related comparisons

Go deeper