Model

PaLM 8B

Google

deepmind.google

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
MMLU25.4exact_matchN/AIndependentmediumarxiv.org

Math

Math
BenchmarkScoreMetricHarnessSourceConfidenceLink
GSM8K4.1accuracyN/AIndependentmediumarxiv.org
GSM8K4.1exact_matchN/AIndependentmediumarxiv.org
MATH1.5accuracyN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…