Model

PALM

Google

deepmind.google

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
CNN/Daily Mail44.3rouge-1N/AIndependentmediumarxiv.org
CNN/Daily Mail41.4rouge-lN/AIndependentmediumarxiv.org
PubMedQA57.8accuracyN/AIndependentmediumarxiv.org
PubMedQA55.0accuracyN/AIndependentmediumarxiv.org
PubMedQA34.0accuracyN/AIndependentmediumarxiv.org

Math

Math
BenchmarkScoreMetricHarnessSourceConfidenceLink
SVAMP62.1execution_accuracyN/AIndependentmediumarxiv.org
SVAMP58.8execution_accuracyN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…