Noometry

Model comparison

Claude Opus 4 vs MiniMax-M2.7

Claude Opus 4 is the stronger model overall, scoring 43.1 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 57× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.

Last verified . 21 shared benchmarks.

Claude Opus 4 Anthropic

43.1

Rank #100 Confirmed

MiniMax-M2.7 MiniMax

37.7

Rank #196 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Claude Opus 4 scores higher in 7 categories and MiniMax-M2.7 in 2 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 4 leads 42.0 to 25.9.
  • The biggest single-benchmark swing is WeirdML: 43.7% for Claude Opus 4 and 37% for MiniMax-M2.7.
  • MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $15 / $75 for Claude Opus 4.
  • MiniMax-M2.7 accepts more context: 205K tokens versus 200K.
  • MiniMax-M2.7 has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4MiniMax-M2.7
ProviderAnthropicMiniMax
Noometry Index43.137.7
Released2025-05-222026-03-18
WeightsProprietaryOpen
Context window200K205K
Max output32K131K
Input $ / M tokens$15$0.30
Output $ / M tokens$75$1.20
Results tracked5630

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

Category by category

Coding Claude Opus 4 leads

Claude Opus 4: 47.2 (#62), MiniMax-M2.7: 41.8 (#120)

BenchmarkClaude Opus 4MiniMax-M2.7
WeirdML43.7%37%
LMArena Coding14421454
SWE-bench Verified70.7%—
SWE-bench Verified (bash only)67.6%—
Aider Polyglot72%—
LMArena WebDev—1398
SciCode—47%
GSO6.9%—
ALE-Bench—599.25
AlgoTune1.33—

Agentic & Tool Use Claude Opus 4 leads

Claude Opus 4: 34.8 (#42), MiniMax-M2.7: 25.1 (#111)

BenchmarkClaude Opus 4MiniMax-M2.7
Terminal-Bench—45.1%
Cybench38%—
DeepResearch Bench46.8%—
ExploitBench—13.3%
GBAEval—0%
LMArena Search1127—
METR Time Horizons63.9%—

Reasoning Claude Opus 4 leads

Claude Opus 4: 27.3 (#121), MiniMax-M2.7: 19.7 (#253)

BenchmarkClaude Opus 4MiniMax-M2.7
CritPt0.3%0.6%
LMArena Hard Prompts13991422
Epoch Capabilities Index142.67145.85
ARC-AGI-28.6%—
SimpleBench58.8%—
Kagi LLM Benchmark74.3%—
NYT Connections (extended)—24.7%
ARC-AGI-135.7%—
EnigmaEval5.6%—
Thematic Generalization—39.3%
DTBench81.6%—
LMCA37.4%—
ForecastBench61.1—

Math Claude Opus 4 leads

Claude Opus 4: 42.0 (#86), MiniMax-M2.7: 25.9 (#263)

BenchmarkClaude Opus 4MiniMax-M2.7
LMArena Math13901420
OTIS Mock AIME 2024-202564.4%—
ProofBench—3%
Omni-MATH61.6%—
MATH Level 585%—
FrontierMath (Feb 2025 set)4.5%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Opus 4 leads

Claude Opus 4: 44.0 (#88), MiniMax-M2.7: 37.7 (#152)

BenchmarkClaude Opus 4MiniMax-M2.7
Vectara Hallucination Rate12%12.9%
LMArena Expert13861444
GPQA Diamond76.3%—
Humanity's Last Exam10.7%—
MMLU-Pro87.5%—
Confabulations15.9%—
GPQA (HELM)70.8%—

Multimodal Not comparable

Claude Opus 4: 31.5 (#106), MiniMax-M2.7: —

BenchmarkClaude Opus 4MiniMax-M2.7
LMArena Vision1192—
GeoBench49%—
VPCT38%—

Multilingual MiniMax-M2.7 leads

Claude Opus 4: 48.8 (#138), MiniMax-M2.7: 50.3 (#123)

BenchmarkClaude Opus 4MiniMax-M2.7
LMArena Non-English13621382
LMArena Chinese13861441
LMArena French13721421
LMArena German13911398
LMArena Japanese13311262
LMArena Korean13211313
LMArena Russian13921383
LMArena Spanish13891403

Instruction Following Claude Opus 4 leads

Claude Opus 4: 77.1 (#28), MiniMax-M2.7: 74.1 (#103)

BenchmarkClaude Opus 4MiniMax-M2.7
LMArena Instruction Following14061405
IFEval91.8%—

Long Context MiniMax-M2.7 leads

Claude Opus 4: 39.6 (#172), MiniMax-M2.7: 43.3 (#99)

BenchmarkClaude Opus 4MiniMax-M2.7
LMArena Longer Query14221419
Fiction.LiveBench61.1%—

Writing & Preference Claude Opus 4 leads

Claude Opus 4: 61.2 (#89), MiniMax-M2.7: 58.9 (#112)

BenchmarkClaude Opus 4MiniMax-M2.7
LMArena Text13771405
LMArena Creative Writing13871354
LMArena Multi-Turn13961412
Short-Story Creative Writing83.6%—
EQ-Bench Creative Writing1580—
WildBench85.2%—

Frequently asked questions

Is Claude Opus 4 better than MiniMax-M2.7?

Claude Opus 4 is the stronger model overall, scoring 43.1 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 57× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4 or MiniMax-M2.7?

MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Claude Opus 4 lists at $15 and $75.

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

Claude Opus 4 scores higher on coding benchmarks: 47.2 versus 41.8 in the Noometry coding category.

Which has the bigger context window?

MiniMax-M2.7 does, with 205K tokens against 200K.

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

21 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and MiniMax-M2.7 has 30.

Related comparisons

Go deeper