Model

PaLM-cont 62B

Google

deepmind.google

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
BoolQ83.9scoreN/AIndependentmediumarxiv.org
PIQA81.4scoreN/AIndependentmediumarxiv.org
WinoGrande77.0accuracyN/AIndependentmediumarxiv.org
WinoGrande77.0accuracyN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…