Model

Pythia 6.9B

Vendor N/A

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
LAMBADA67.3accuracyN/AIndependentmediumarxiv.org
PIQA75.2accuracyN/AIndependentmediumarxiv.org
WinoGrande60.9accuracyN/AIndependentmediumarxiv.org
WSC36.5accuracyN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…