ResearchDatasetsARC-C, ARC-E, BoolQ, HellaSwag, PIQA, RTE, WinoGrandeFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsZero-shot EvaluationARC-C, ARC-E, BoolQ, HellaSwag, PIQA, RTE, WinoGrande Zero-shot72.9Accuracy57