Model

Gopher

Vendor N/A

Knowledge & Reasoning

Knowledge & Reasoning
BenchmarkScoreMetricHarnessSourceConfidenceLink
BoolQ79.4scoreN/AIndependentmediumarxiv.org
BoolQ79.3accuracyN/AIndependentmediumarxiv.org
HellaSwag79.2overall_accuracyN/AIndependentmediumarxiv.org
LAMBADA74.5scoreN/ASelf-reportedmediumarxiv.org
LAMBADA74.5scoreN/AIndependentmediumarxiv.org
MMLU60.0exact_matchN/ASelf-reportedmediumarxiv.org
MMLU60.0exact_matchN/AIndependentmediumarxiv.org
Natural Questions28.2exact_matchN/AIndependentmediumarxiv.org
PIQA81.8scoreN/ASelf-reportedmediumarxiv.org
PIQA81.8scoreN/AIndependentmediumarxiv.org
PubMed Cognitive Control Abstracts0.6bpbN/AIndependentmediumarxiv.org
siqa50.6accuracyN/AIndependentmediumarxiv.org
Trivia QA57.2exact_matchN/AIndependentmediumarxiv.org
Trivia QA57.1exact_matchN/ASelf-reportedmediumarxiv.org
Ubuntu IRC1.1bpbN/AIndependentmediumarxiv.org
WinoGrande70.2accuracyN/AIndependentmediumarxiv.org
WinoGrande70.1accuracyN/ASelf-reportedmediumarxiv.org

Reproduced by the community

Loading community runs…