ResearchDatasetsARC, BoolQ, HellaSwag, OpenBookQA, PIQA, RTEARC, BoolQ, HellaSwag, OpenBookQA, PIQA, RTEFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsZero-shot EvaluationARC-C, BoolQ, HellaSwag, OpenBookQA, PIQA, RTE55.6ARC-C Accuracy6