Model

Chinchilla

Vendor N/A

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
BoolQ83.7scoreN/AIndependentmediumarxiv.org
LAMBADA77.7accuracyN/AIndependentmediumarxiv.org
LAMBADA77.4scoreN/AIndependentmediumarxiv.org
MMLU67.5exact_matchN/AIndependentmediumarxiv.org
Natural Questions35.5exact_matchN/AIndependentmediumarxiv.org
PIQA81.8scoreN/AIndependentmediumarxiv.org
siqa51.3accuracyN/AIndependentmediumarxiv.org
Trivia QA64.6exact_matchN/AIndependentmediumarxiv.org
WinoGrande74.9accuracyN/AIndependentmediumarxiv.org

Reproduced by the community

Loading community runs…