Model

Solar Pro 3

Upstage

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
CritPt0.0accuracyN/AIndependentlowepoch.ai

Coding

Coding
BenchmarkScoreMetricHarnessSourceConfidenceLink
SciCode24.7scoreN/AIndependentmediumartificialanalysis.ai

Reproduced by the community

Loading community runs…