Model

Cohere medium v20221108

Vendor N/A

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
BoolQ70.0scoreN/AIndependentmediumcrfm.stanford.edu
HellaSwag72.6overall_accuracyN/AIndependentmediumcrfm.stanford.edu

Math

Math
BenchmarkScoreMetricHarnessSourceConfidenceLink
GSM8K1.7exact_matchN/AIndependentmediumcrfm.stanford.edu

Reproduced by the community

Loading community runs…