Noometry

Model comparison

Grok 4 vs MiniMax-M2.1

Grok 4 is the stronger model overall, scoring 48.1 to 38.9 on the Noometry Index.

Last verified . 18 shared benchmarks.

Grok 4 xAI

48.1

Rank #56 Confirmed

MiniMax-M2.1 MiniMax

38.9

Rank #178 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Grok 4 scores higher in 9 categories and MiniMax-M2.1 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Grok 4 leads 36.7 to 16.6.
  • The biggest single-benchmark swing is Terminal-Bench: 27.2% for Grok 4 and 36.6% for MiniMax-M2.1.
  • MiniMax-M2.1 has downloadable open weights; the other is API-only.

Side by side

Grok 4MiniMax-M2.1
ProviderxAIMiniMax
Noometry Index48.138.9
Released2025-07-092025-12-23
WeightsProprietaryOpen
Context window—205K
Max output—131K
Input $ / M tokens—$0.30
Output $ / M tokens—$1.20
Results tracked4822

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

Category by category

Coding Grok 4 leads

Grok 4: 50.3 (#46), MiniMax-M2.1: 40.4 (#143)

BenchmarkGrok 4MiniMax-M2.1
LMArena Coding14081421
Aider Polyglot79.6%—
LMArena WebDev—1384
WeirdML45.7%—
ALE-Bench—623.83

Agentic & Tool Use Grok 4 leads

Grok 4: 32.3 (#68), MiniMax-M2.1: 27.9 (#98)

BenchmarkGrok 4MiniMax-M2.1
Terminal-Bench27.2%36.6%
Berkeley Function Calling Leaderboard63%—
GDPval21.1%—
Cybench43%—
DeepResearch Bench47.3%—
BALROG43.6%—
LMArena Search1142—
METR Time Horizons66.6%—

Reasoning Grok 4 leads

Grok 4: 36.7 (#65), MiniMax-M2.1: 16.6 (#302)

BenchmarkGrok 4MiniMax-M2.1
LMArena Hard Prompts14091411
ARC-AGI-216%—
SimpleBench60.5%—
Kagi LLM Benchmark73.6%—
NYT Connections (extended)—11.2%
ARC-AGI-166.7%—
Chess Puzzles28%—
Epoch Capabilities Index146.44—
ForecastBench60.9—

Math Grok 4 leads

Grok 4: 48.4 (#64), MiniMax-M2.1: 38.3 (#138)

BenchmarkGrok 4MiniMax-M2.1
LMArena Math14221397
OTIS Mock AIME 2024-202584%—
Omni-MATH60.3%—
FrontierMath (Feb 2025 set)19.7%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge Grok 4 leads

Grok 4: 53.8 (#55), MiniMax-M2.1: 38.3 (#147)

BenchmarkGrok 4MiniMax-M2.1
LMArena Expert14151431
GPQA Diamond87%—
MMLU-Pro85.1%—
Confabulations12.4%—
Vectara Hallucination Rate—11.8%
GPQA (HELM)72.7%—

Multimodal Not comparable

Grok 4: 33.7 (#94), MiniMax-M2.1: —

BenchmarkGrok 4MiniMax-M2.1
LMArena Vision1210—
GeoBench45%—

Multilingual Grok 4 leads

Grok 4: 51.8 (#103), MiniMax-M2.1: 50.0 (#128)

BenchmarkGrok 4MiniMax-M2.1
LMArena Non-English14031378
LMArena Chinese14271430
LMArena French14181404
LMArena German14291381
LMArena Japanese13941287
LMArena Korean13771298
LMArena Russian14101387
LMArena Spanish14201397

Instruction Following Grok 4 leads

Grok 4: 79.2 (#5), MiniMax-M2.1: 73.8 (#112)

BenchmarkGrok 4MiniMax-M2.1
LMArena Instruction Following13871400
IFEval94.9%—

Long Context Grok 4 leads

Grok 4: 63.1 (#4), MiniMax-M2.1: 43.2 (#101)

BenchmarkGrok 4MiniMax-M2.1
LMArena Longer Query14091416
Fiction.LiveBench94.4%—

Writing & Preference Too close to call

Grok 4: 58.5 (#116), MiniMax-M2.1: 58.3 (#120)

BenchmarkGrok 4MiniMax-M2.1
LMArena Text14111392
LMArena Creative Writing13971361
LMArena Multi-Turn14161396
Short-Story Creative Writing76.9%—
WildBench79.7%—

Frequently asked questions

Is Grok 4 better than MiniMax-M2.1?

Grok 4 is the stronger model overall, scoring 48.1 to 38.9 on the Noometry Index.

Is Grok 4 or MiniMax-M2.1 better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 40.4 in the Noometry coding category.

How many benchmarks do Grok 4 and MiniMax-M2.1 share?

18 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and MiniMax-M2.1 has 22.

Related comparisons

Go deeper