Model

Trinity Large Thinking

Arcee AI

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
CritPt0.9accuracyN/AIndependentlowepoch.ai

Coding

Coding
BenchmarkScoreMetricHarnessSourceConfidenceLink
SciCode36.1scoreN/AIndependentmediumartificialanalysis.ai

Reproduced by the community

Loading community runs…