Noometry

Model comparison

Claude 3 Opus vs MiniMax-M2.1

MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 29.5 on the Noometry Index.

Last verified . 17 shared benchmarks.

Claude 3 Opus Anthropic

29.5

Rank #310 Confirmed

MiniMax-M2.1 MiniMax

38.9

Rank #178 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and MiniMax-M2.1 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where MiniMax-M2.1 leads 38.3 to 14.8.
  • MiniMax-M2.1 has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusMiniMax-M2.1
ProviderAnthropicMiniMax
Noometry Index29.538.9
Released2024-02-292025-12-23
WeightsProprietaryOpen
Context window—205K
Max output—131K
Input $ / M tokens—$0.30
Output $ / M tokens—$1.20
Results tracked4622

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

Category by category

Coding MiniMax-M2.1 leads

Claude 3 Opus: 32.9 (#267), MiniMax-M2.1: 40.4 (#143)

BenchmarkClaude 3 OpusMiniMax-M2.1
LMArena Coding12641421
LMArena WebDev—1384
WeirdML19.2%—
BigCodeBench Instruct45.5%—
LiveBench Coding38.6%—
BigCodeBench Complete57.4%—
ALE-Bench—623.83
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use MiniMax-M2.1 leads

Claude 3 Opus: 24.6 (#116), MiniMax-M2.1: 27.9 (#98)

BenchmarkClaude 3 OpusMiniMax-M2.1
Terminal-Bench—36.6%
Cybench10%—
METR Time Horizons29.5%—

Reasoning MiniMax-M2.1 leads

Claude 3 Opus: 14.6 (#324), MiniMax-M2.1: 16.6 (#302)

BenchmarkClaude 3 OpusMiniMax-M2.1
LMArena Hard Prompts12451411
SimpleBench23.5%—
NYT Connections (extended)—11.2%
Chess Puzzles5%—
EnigmaEval0.8%—
LiveBench Reasoning40.6%—
DTBench61.6%—
LiveBench Data Analysis57.9%—
LMCA17%—
Epoch Capabilities Index126.91—
ForecastBench58.4—
LiveBench49.2%—
WinoGrande88.5%—

Math MiniMax-M2.1 leads

Claude 3 Opus: 14.8 (#299), MiniMax-M2.1: 38.3 (#138)

BenchmarkClaude 3 OpusMiniMax-M2.1
LMArena Math12731397
OTIS Mock AIME 2024-20254.7%—
LiveBench Math43.6%—
MATH Level 537.5%—

Knowledge MiniMax-M2.1 leads

Claude 3 Opus: 24.5 (#267), MiniMax-M2.1: 38.3 (#147)

BenchmarkClaude 3 OpusMiniMax-M2.1
LMArena Expert12231431
GPQA Diamond47.2%—
SimpleQA Verified12.6%—
Confabulations22.7%—
Vectara Hallucination Rate—11.8%
MMLU84.6%—

Multimodal Not comparable

Claude 3 Opus: 27.1 (#116), MiniMax-M2.1: —

BenchmarkClaude 3 OpusMiniMax-M2.1
LMArena Vision1023—

Multilingual MiniMax-M2.1 leads

Claude 3 Opus: 41.4 (#207), MiniMax-M2.1: 50.0 (#128)

BenchmarkClaude 3 OpusMiniMax-M2.1
LMArena Non-English12581378
LMArena Chinese12481430
LMArena French12751404
LMArena German12581381
LMArena Japanese12041287
LMArena Korean11871298
LMArena Russian12801387
LMArena Spanish12461397

Instruction Following MiniMax-M2.1 leads

Claude 3 Opus: 64.1 (#228), MiniMax-M2.1: 73.8 (#112)

BenchmarkClaude 3 OpusMiniMax-M2.1
LMArena Instruction Following12481400
LiveBench Instruction Following63.9%—

Long Context MiniMax-M2.1 leads

Claude 3 Opus: 38.2 (#202), MiniMax-M2.1: 43.2 (#101)

BenchmarkClaude 3 OpusMiniMax-M2.1
LMArena Longer Query12591416

Writing & Preference MiniMax-M2.1 leads

Claude 3 Opus: 47.2 (#213), MiniMax-M2.1: 58.3 (#120)

BenchmarkClaude 3 OpusMiniMax-M2.1
LMArena Text12621392
LMArena Creative Writing12351361
LMArena Multi-Turn12751396
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than MiniMax-M2.1?

MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 29.5 on the Noometry Index.

Is Claude 3 Opus or MiniMax-M2.1 better for coding?

MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3 Opus and MiniMax-M2.1 share?

17 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and MiniMax-M2.1 has 22.

Related comparisons

Go deeper