ResearchDatasetsEvaluation Suite (ARC, BoolQ, HellaSwag, PIQA)Evaluation Suite (ARC, BoolQ, HellaSwag, PIQA)FollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsZero-shot EvaluationEvaluation Suite (ARC, BoolQ, HellaSwag, PIQA) Zero-shot69.82Average Score5