Noometry

Model comparison

Claude 3 Opus vs MiniMax-M2.7

MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 29.5 on the Noometry Index.

Last verified . 19 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

MiniMax-M2.7 MiniMax

37.7

Rank #196 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and MiniMax-M2.7 in 9 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where MiniMax-M2.7 leads 37.7 to 24.5.
  • The biggest single-benchmark swing is WeirdML: 19.2% for Claude 3 Opus and 37% for MiniMax-M2.7.
  • MiniMax-M2.7 has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusMiniMax-M2.7
ProviderAnthropicMiniMax
Noometry Index29.537.7
Released2024-02-292026-03-18
WeightsProprietaryOpen
Context window—205K
Max output—131K
Input $ / M tokens—$0.30
Output $ / M tokens—$1.20
Results tracked4630

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

Category by category

Coding MiniMax-M2.7 leads

Claude 3 Opus: 32.9 (#267), MiniMax-M2.7: 41.8 (#120)

BenchmarkClaude 3 OpusMiniMax-M2.7
WeirdML19.2%37%
LMArena Coding12641454
LMArena WebDev—1398
SciCode—47%
BigCodeBench Instruct45.5%—
LiveBench Coding38.6%—
BigCodeBench Complete57.4%—
ALE-Bench—599.25
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use Too close to call

Claude 3 Opus: 24.6 (#116), MiniMax-M2.7: 25.1 (#111)

BenchmarkClaude 3 OpusMiniMax-M2.7
Terminal-Bench—45.1%
Cybench10%—
ExploitBench—13.3%
GBAEval—0%
METR Time Horizons29.5%—

Reasoning MiniMax-M2.7 leads

Claude 3 Opus: 14.6 (#324), MiniMax-M2.7: 19.7 (#253)

BenchmarkClaude 3 OpusMiniMax-M2.7
LMArena Hard Prompts12451422
Epoch Capabilities Index126.91145.85
SimpleBench23.5%—
NYT Connections (extended)—24.7%
CritPt—0.6%
Chess Puzzles5%—
EnigmaEval0.8%—
Thematic Generalization—39.3%
LiveBench Reasoning40.6%—
DTBench61.6%—
LiveBench Data Analysis57.9%—
LMCA17%—
ForecastBench58.4—
LiveBench49.2%—
WinoGrande88.5%—

Math MiniMax-M2.7 leads

Claude 3 Opus: 14.8 (#299), MiniMax-M2.7: 25.9 (#263)

BenchmarkClaude 3 OpusMiniMax-M2.7
LMArena Math12731420
OTIS Mock AIME 2024-20254.7%—
ProofBench—3%
LiveBench Math43.6%—
MATH Level 537.5%—

Knowledge MiniMax-M2.7 leads

Claude 3 Opus: 24.5 (#267), MiniMax-M2.7: 37.7 (#152)

BenchmarkClaude 3 OpusMiniMax-M2.7
LMArena Expert12231444
GPQA Diamond47.2%—
SimpleQA Verified12.6%—
Confabulations22.7%—
Vectara Hallucination Rate—12.9%
MMLU84.6%—

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), MiniMax-M2.7: —

BenchmarkClaude 3 OpusMiniMax-M2.7
LMArena Vision1023—

Multilingual MiniMax-M2.7 leads

Claude 3 Opus: 41.4 (#207), MiniMax-M2.7: 50.3 (#123)

BenchmarkClaude 3 OpusMiniMax-M2.7
LMArena Non-English12581382
LMArena Chinese12481441
LMArena French12751421
LMArena German12581398
LMArena Japanese12041262
LMArena Korean11871313
LMArena Russian12801383
LMArena Spanish12461403

Instruction Following MiniMax-M2.7 leads

Claude 3 Opus: 64.1 (#228), MiniMax-M2.7: 74.1 (#103)

BenchmarkClaude 3 OpusMiniMax-M2.7
LMArena Instruction Following12481405
LiveBench Instruction Following63.9%—

Long Context MiniMax-M2.7 leads

Claude 3 Opus: 38.2 (#202), MiniMax-M2.7: 43.3 (#99)

BenchmarkClaude 3 OpusMiniMax-M2.7
LMArena Longer Query12591419

Writing & Preference MiniMax-M2.7 leads

Claude 3 Opus: 47.2 (#213), MiniMax-M2.7: 58.9 (#112)

BenchmarkClaude 3 OpusMiniMax-M2.7
LMArena Text12621405
LMArena Creative Writing12351354
LMArena Multi-Turn12751412
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than MiniMax-M2.7?

MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 29.5 on the Noometry Index.

Is Claude 3 Opus or MiniMax-M2.7 better for coding?

MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3 Opus and MiniMax-M2.7 share?

19 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and MiniMax-M2.7 has 30.

Related comparisons

Go deeper