Model

MiMo-V2-Flash

Xiaomi · open weights

github.com

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
CritPt0.0accuracyN/AIndependentlowepoch.ai
GPQA Diamond83.7accuracyN/ASelf-reportedlowartificialanalysis.ai
LMArena1393.0eloN/ASelf-reportedlowlmarena.ai
MMLU-Pro84.9accuracyN/ASelf-reportedlowartificialanalysis.ai

Math

Math
BenchmarkScoreMetricHarnessSourceConfidenceLink
MATH-50094.1accuracyN/ASelf-reportedlowkaggle.com

Coding

Coding
BenchmarkScoreMetricHarnessSourceConfidenceLink
LiveCodeBench80.6pass@1N/ASelf-reportedlowlivecodebench.github.io
SciCode25.9scoreN/AIndependentmediumartificialanalysis.ai
SWE-bench Verified73.4resolved_rateN/ASelf-reportedlowswebench.com
Terminal-Bench 2.038.5accuracyN/ASelf-reportedlowtbench.ai

Reproduced by the community

Loading community runs…