ResearchDatasetsCommon Reasoning TasksFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsReasoning7 Common Reasoning Tasks (ARC-E, ARC-C, BoolQ, WinoGrande, HellaSwag, MMLU, PIQA)78.9ARC-E Accuracy32
Reasoning7 Common Reasoning Tasks (ARC-E, ARC-C, BoolQ, WinoGrande, HellaSwag, MMLU, PIQA)78.9ARC-E Accuracy32