Model

Cohere medium v20220720

Vendor N/A

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
BoolQ65.9scoreN/AIndependentmediumcrfm.stanford.edu
HellaSwag70.6overall_accuracyN/AIndependentmediumcrfm.stanford.edu

Math

Math
BenchmarkScoreMetricHarnessSourceConfidenceLink
GSM8K1.5exact_matchN/AIndependentmediumcrfm.stanford.edu

Reproduced by the community

Loading community runs…