MiMo V2.5 — Benchmarks

Benchmark scores for MiMo V2.5 aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

Overall rank: #113 of 123 open modelscomposite 20.9/100 across 3 benchmarks in 3 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
SciCode43.1%#21 / 50#94 / 155

Math

BenchmarkScoreOpen rankAll models
ProofBench16.0%#13 / 21#44 / 64

Reasoning

BenchmarkScoreOpen rankAll models
CritPt3.7%#18 / 50#88 / 167

Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.

MiMo V2.5 Benchmarks — Scores & Rankings | llmrun