ResearchDatasetsCommonsense and LanguageFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsCommonsense and Language ReasoningCommonsense and Language Aggregate: HellaSwag, Winogrande, BoolQ (test)70.6Accuracy6
Commonsense and Language ReasoningCommonsense and Language Aggregate: HellaSwag, Winogrande, BoolQ (test)70.6Accuracy6