ResearchDatasetsMMLU, ARC-c, HellaSwag, BOOLQ, PIQA, WinoGrandeMMLU, ARC-c, HellaSwag, BOOLQ, PIQA, WinoGrandeFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsNatural Language Understanding and ReasoningMMLU, ARC-c, HellaSwag, BOOLQ, PIQA, WinoGrande zero-shot69.72Average Score (Zero-shot)20
Natural Language Understanding and ReasoningMMLU, ARC-c, HellaSwag, BOOLQ, PIQA, WinoGrande zero-shot69.72Average Score (Zero-shot)20