ResearchDatasetsARC, BoolQ, HellaSwag, OpenBookQA, PIQA, SIQA, WinoGrandeFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsCommon-sense ReasoningARC-e, ARC-c, BoolQ, HellaSwag, OpenBookQA, PIQA, SIQA, WinoGrande73.410-shot Accuracy92
Common-sense ReasoningARC-e, ARC-c, BoolQ, HellaSwag, OpenBookQA, PIQA, SIQA, WinoGrande73.410-shot Accuracy92