Noometry

Model comparison

Grok 4 vs MiniMax-M2.7

Grok 4 is the stronger model overall, scoring 48.1 to 37.7 on the Noometry Index.

Last verified . 20 shared benchmarks.

Grok 4 xAI

48.1

Rank #56 Confirmed

MiniMax-M2.7 MiniMax

37.7

Rank #196 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Grok 4 scores higher in 8 categories and MiniMax-M2.7 in 1 category; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Grok 4 leads 48.4 to 25.9.
  • The biggest single-benchmark swing is Terminal-Bench: 27.2% for Grok 4 and 45.1% for MiniMax-M2.7.
  • MiniMax-M2.7 has downloadable open weights; the other is API-only.

Side by side

Grok 4MiniMax-M2.7
ProviderxAIMiniMax
Noometry Index48.137.7
Released2025-07-092026-03-18
WeightsProprietaryOpen
Context window—205K
Max output—131K
Input $ / M tokens—$0.30
Output $ / M tokens—$1.20
Results tracked4830

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-M2.7: 41.8 (#120)

BenchmarkGrok 4MiniMax-M2.7
WeirdML45.7%37%
LMArena Coding14081454
Aider Polyglot79.6%—
LMArena WebDev—1398
SciCode—47%
ALE-Bench—599.25

Agentic & Tool Use Grok 4 leads

Grok 4: 32.3 (#68), MiniMax-M2.7: 25.1 (#111)

BenchmarkGrok 4MiniMax-M2.7
Terminal-Bench27.2%45.1%
Berkeley Function Calling Leaderboard63%—
GDPval21.1%—
Cybench43%—
DeepResearch Bench47.3%—
BALROG43.6%—
ExploitBench—13.3%
GBAEval—0%
LMArena Search1142—
METR Time Horizons66.6%—

Reasoning Grok 4 leads

Grok 4: 36.7 (#65), MiniMax-M2.7: 19.7 (#253)

BenchmarkGrok 4MiniMax-M2.7
LMArena Hard Prompts14091422
Epoch Capabilities Index146.44145.85
ARC-AGI-216%—
SimpleBench60.5%—
Kagi LLM Benchmark73.6%—
NYT Connections (extended)—24.7%
ARC-AGI-166.7%—
CritPt—0.6%
Chess Puzzles28%—
Thematic Generalization—39.3%
ForecastBench60.9—

Math Grok 4 leads

Grok 4: 48.4 (#64), MiniMax-M2.7: 25.9 (#263)

BenchmarkGrok 4MiniMax-M2.7
LMArena Math14221420
OTIS Mock AIME 2024-202584%—
ProofBench—3%
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-M2.7: 37.7 (#152)

BenchmarkGrok 4MiniMax-M2.7
LMArena Expert14151444
GPQA Diamond87%—
MMLU-Pro85.1%—
Confabulations12.4%—
Vectara Hallucination Rate—12.9%
GPQA (HELM)72.7%—

Multimodal Not comparable

Grok 4: 33.7 (#94), MiniMax-M2.7: —

BenchmarkGrok 4MiniMax-M2.7
LMArena Vision1210—
GeoBench45%—

Multilingual Grok 4 leads

Grok 4: 51.8 (#103), MiniMax-M2.7: 50.3 (#123)

BenchmarkGrok 4MiniMax-M2.7
LMArena Non-English14031382
LMArena Chinese14271441
LMArena French14181421
LMArena German14291398
LMArena Japanese13941262
LMArena Korean13771313
LMArena Russian14101383
LMArena Spanish14201403

Instruction Following Grok 4 leads

Grok 4: 79.2 (#5), MiniMax-M2.7: 74.1 (#103)

BenchmarkGrok 4MiniMax-M2.7
LMArena Instruction Following13871405
IFEval94.9%—

Long Context Grok 4 leads

Grok 4: 63.1 (#4), MiniMax-M2.7: 43.3 (#99)

BenchmarkGrok 4MiniMax-M2.7
LMArena Longer Query14091419
Fiction.LiveBench94.4%—

Writing & Preference Too close to call

Grok 4: 58.5 (#116), MiniMax-M2.7: 58.9 (#112)

BenchmarkGrok 4MiniMax-M2.7
LMArena Text14111405
LMArena Creative Writing13971354
LMArena Multi-Turn14161412
Short-Story Creative Writing76.9%—
WildBench79.7%—

Frequently asked questions

Is Grok 4 better than MiniMax-M2.7?

Grok 4 is the stronger model overall, scoring 48.1 to 37.7 on the Noometry Index.

Is Grok 4 or MiniMax-M2.7 better for coding?

Grok 4 scores higher on coding benchmarks: 50.3 versus 41.8 in the Noometry coding category.

How many benchmarks do Grok 4 and MiniMax-M2.7 share?

20 benchmarks have published results for both models. Grok 4 has 48 scored results on Noometry and MiniMax-M2.7 has 30.

Related comparisons

Go deeper