ResearchDatasetsEvaluation Suite (ARC, BoolQ, HellaSwag, PIQA)FollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsZero-shot EvaluationEvaluation Suite (ARC, BoolQ, HellaSwag, PIQA) Zero-shot69.82Average Score5