Model

Ring-2.6-1T

Ant Group

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
CritPt3.7accuracyN/AIndependentlowepoch.ai

Coding

Coding
BenchmarkScoreMetricHarnessSourceConfidenceLink
SciCode42.4scoreN/AIndependentmediumartificialanalysis.ai

Reproduced by the community

Loading community runs…