ResearchDatasetsLAMBADA, ARC-C, HellaSwag, BoolQ, MMLU, GSM8KFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsGeneral Language UnderstandingLAMBADA, ARC-C, HellaSwag, BoolQ, MMLU, GSM8K Average74.35Accuracy56