ResearchDatasetsIn-Domain TasksFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsShot-Language Understanding12 In-Domain (ID) Tasks79Composition Rule Score8Common-sense ReasoningIn-Domain Tasks ARC-e, ARC-c, BoolQ, HellaSwag, PIQA74.7ARC-e Accuracy5