Model

Muse Glimmer

Meta AI

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
CritPt2.6accuracyN/AIndependentlowepoch.ai

Coding

Coding
BenchmarkScoreMetricHarnessSourceConfidenceLink
SciCode44.9scoreN/AIndependentmediumartificialanalysis.ai

Reproduced by the community

Loading community runs…