ResearchDatasetsPIQA, HellaSwag, WinoGrande, ARC, SocialIQA, BoolQFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsCommonsense ReasoningPIQA, HellaSwag, WinoGrande, ARC, SocialIQA, BoolQ zero-shot74.15PIQA Accuracy12
Commonsense ReasoningPIQA, HellaSwag, WinoGrande, ARC, SocialIQA, BoolQ zero-shot74.15PIQA Accuracy12