MiMo V2.5 Pro — Benchmarks

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

Overall rank: #107 of 123 open modelscomposite 25.4/100 across 3 benchmarks in 3 categories · methodology

Coding

BenchmarkScoreOpen rankAll models
SciCode50.2%#5 / 50#56 / 155

Math

BenchmarkScoreOpen rankAll models
ProofBench22.0%#7 / 21#33 / 64

Reasoning

BenchmarkScoreOpen rankAll models
CritPt4.0%#15 / 50#85 / 167

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

MiMo V2.5 Pro Benchmarks — Scores & Rankings | llmrun