Model

Muse Wonder 1.0

Meta AI

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
CritPt28.3accuracyN/AIndependentlowepoch.ai

Coding

Coding
BenchmarkScoreMetricHarnessSourceConfidenceLink
SciCode60.3scoreN/AIndependentmediumartificialanalysis.ai

Multimodal

Multimodal
BenchmarkScoreMetricHarnessSourceConfidenceLink
GDP.pdf30.8gdp.pdf_scoreN/AIndependentmediumsurgehq.ai

Reproduced by the community

Loading community runs…