ResearchDatasetsARC-Easy, ARC-Challenge, OpenBookQA, WinoGrande, PIQA, HellaSwag, MathQA, RTE, BoolQARC-Easy, ARC-Challenge, OpenBookQA, WinoGrande, PIQA, HellaSwag, MathQA, RTE, BoolQFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsZero-shot evaluationARC-Easy, ARC-Challenge, OpenBookQA, WinoGrande, PIQA, HellaSwag, MathQA, RTE, BoolQ zero-shot71.08Mean Accuracy59
Zero-shot evaluationARC-Easy, ARC-Challenge, OpenBookQA, WinoGrande, PIQA, HellaSwag, MathQA, RTE, BoolQ zero-shot71.08Mean Accuracy59