ResearchDatasetsPIQA, WinoGrande, HellaSwag, BoolQ, SocialIQA, OpenBookQAFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsCommonsense ReasoningPIQA, WinoGrande, HellaSwag, BoolQ, SocialIQA, OpenBookQA90.2PIQA Accuracy7