Model

Palmyra X

Google

deepmind.google

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
BoolQ89.6scoreN/AIndependentmediumcrfm.stanford.edu

Math

Math
BenchmarkScoreMetricHarnessSourceConfidenceLink
GSM8K63.3exact_matchN/AIndependentmediumcrfm.stanford.edu

Reproduced by the community

Loading community runs…