ResearchDatasetsLAMBADA, ARC-C, HellaSwag, BoolQ, MMLU, GSM8KLAMBADA, ARC-C, HellaSwag, BoolQ, MMLU, GSM8KFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsGeneral Language UnderstandingLAMBADA, ARC-C, HellaSwag, BoolQ, MMLU, GSM8K Average74.35Accuracy56