MiMo V2.6 Flash RL — Benchmarks

Benchmark scores for MiMo V2.6 Flash RL aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.

No llmrun Composite Score for MiMo V2.6 Flash RL: the score is only published for a model measured on at least 4 of the boards in the score panel, spanning at least 2 benchmark categories and including a reasoning or coding board. Its individual scores below stand on their own — see how the llmrun Composite Score is built.

Coding

BenchmarkScoreOpen rankAll models
LMArena WebDev1636.8#2 / 50#16 / 135
SciCode51.3%#7 / 65#87 / 200

Instruction Following

BenchmarkScoreOpen rankAll models
LMArena Text1450.7#15 / 186#75 / 403

Math

BenchmarkScoreOpen rankAll models
ProofBench63.0%#4 / 26#18 / 79

Reasoning

BenchmarkScoreOpen rankAll models
CritPt12.0%#10 / 65#95 / 212

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