Model

Ada

OpenAI

openai.com

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
BoolQ58.1scoreN/AIndependentmediumcrfm.stanford.edu
HellaSwag43.5overall_accuracyN/AIndependentmediumcrfm.stanford.edu

Math

Math
BenchmarkScoreMetricHarnessSourceConfidenceLink
GSM8K0.6exact_matchN/AIndependentmediumcrfm.stanford.edu

Reproduced by the community

Loading community runs…