Noometry

Model comparison

Claude 3 Opus vs MiMo-V2.5

MiMo-V2.5 is the stronger model overall, scoring 43.0 to 29.3 on the Noometry Index.

Last verified . 18 shared benchmarks.

Claude 3 Opus Anthropic

29.3

Rank #300 Confirmed

MiMo-V2.5 Xiaomi

43.0

Rank #89 Confirmed

Summary

  • They share 18 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and MiMo-V2.5 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where MiMo-V2.5 leads 35.4 to 13.9.
  • MiMo-V2.5 has downloadable open weights; the other is API-only.

Side by side

Claude 3 OpusMiMo-V2.5
ProviderAnthropicXiaomi
Noometry Index29.343.0
Released2024-02-292026-04-22
WeightsProprietaryOpen
Context window—1.05M
Max output—131K
Input $ / M tokens—$0.14
Output $ / M tokens—$0.28
Results tracked4623

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

Category by category

Coding MiMo-V2.5 leads

Claude 3 Opus: 32.4 (#261), MiMo-V2.5: 43.6 (#75)

BenchmarkClaude 3 OpusMiMo-V2.5
LMArena Coding12641469
LMArena WebDev—1438
SciCode—43.1%
WeirdML19.2%—
BigCodeBench Instruct45.5%—
LiveBench Coding38.6%—
BigCodeBench Complete57.4%—
ALE-Bench—513.95
HumanEval+77.4%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

Claude 3 Opus: 24.3 (#110), MiMo-V2.5: —

BenchmarkClaude 3 OpusMiMo-V2.5
Cybench10%—
METR Time Horizons29.5%—

Reasoning MiMo-V2.5 leads

Claude 3 Opus: 14.2 (#318), MiMo-V2.5: 27.8 (#98)

BenchmarkClaude 3 OpusMiMo-V2.5
LMArena Hard Prompts12461450
SimpleBench23.5%—
CritPt—3.7%
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 MiMo-V2.5 leads

Claude 3 Opus: 13.9 (#293), MiMo-V2.5: 35.4 (#145)

BenchmarkClaude 3 OpusMiMo-V2.5
LMArena Math12731436
OTIS Mock AIME 2024-20254.7%—
ProofBench—16%
LiveBench Math43.6%—
MATH Level 537.5%—

Knowledge MiMo-V2.5 leads

Claude 3 Opus: 24.5 (#262), MiMo-V2.5: 40.2 (#109)

BenchmarkClaude 3 OpusMiMo-V2.5
LMArena Expert12231459
GPQA Diamond47.2%—
SimpleQA Verified12.6%—
Confabulations22.7%—
MMLU84.6%—

Multimodal MiMo-V2.5 leads

Claude 3 Opus: 26.6 (#112), MiMo-V2.5: 39.0 (#53)

BenchmarkClaude 3 OpusMiMo-V2.5
LMArena Vision10231245

Multilingual MiMo-V2.5 leads

Claude 3 Opus: 41.6 (#202), MiMo-V2.5: 52.0 (#96)

BenchmarkClaude 3 OpusMiMo-V2.5
LMArena Non-English12581404
LMArena Chinese12481467
LMArena French12741447
LMArena German12581421
LMArena Japanese12041304
LMArena Korean11871363
LMArena Russian12801395
LMArena Spanish12461412

Instruction Following MiMo-V2.5 leads

Claude 3 Opus: 64.3 (#223), MiMo-V2.5: 75.7 (#55)

BenchmarkClaude 3 OpusMiMo-V2.5
LMArena Instruction Following12481433
LiveBench Instruction Following63.9%—

Long Context MiMo-V2.5 leads

Claude 3 Opus: 38.2 (#197), MiMo-V2.5: 44.1 (#69)

BenchmarkClaude 3 OpusMiMo-V2.5
LMArena Longer Query12591444

Writing & Preference MiMo-V2.5 leads

Claude 3 Opus: 47.4 (#208), MiMo-V2.5: 61.8 (#82)

BenchmarkClaude 3 OpusMiMo-V2.5
LMArena Text12621427
LMArena Creative Writing12351392
LMArena Multi-Turn12751445
LiveBench Language50.4%—

Frequently asked questions

Is Claude 3 Opus better than MiMo-V2.5?

MiMo-V2.5 is the stronger model overall, scoring 43.0 to 29.3 on the Noometry Index.

Is Claude 3 Opus or MiMo-V2.5 better for coding?

MiMo-V2.5 scores higher on coding benchmarks: 43.6 versus 32.4 in the Noometry coding category.

How many benchmarks do Claude 3 Opus and MiMo-V2.5 share?

18 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and MiMo-V2.5 has 23.

Related comparisons

Go deeper