ResearchDatasetsHellaSwag, WinoGrande, BoolQ, CommonsenseQA, OpenBookQA, PIQA, SIQAHellaSwag, WinoGrande, BoolQ, CommonsenseQA, OpenBookQA, PIQA, SIQAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsCommonsense ReasoningHellaSwag, WinoGrande, BoolQ, CommonsenseQA, OpenBookQA, PIQA, SIQA—Primary metric0
Commonsense ReasoningHellaSwag, WinoGrande, BoolQ, CommonsenseQA, OpenBookQA, PIQA, SIQA—Primary metric0