ResearchDatasetsEvaluation Suite (ARC-e, ARC-c, PIQA, HellaS., WinoG., BoolQ)FollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsZero-shot ClassificationEvaluation Suite (ARC-e, ARC-c, PIQA, HellaS., WinoG., BoolQ) Zero-shot (test)92.59ARC-e Accuracy30
Zero-shot ClassificationEvaluation Suite (ARC-e, ARC-c, PIQA, HellaS., WinoG., BoolQ) Zero-shot (test)92.59ARC-e Accuracy30