ResearchDatasetsARC-e, BoolQ, HellaSwag, LAMBADA, PIQA, RACE, SocialIQA, SciQ, SWAGARC-e, BoolQ, HellaSwag, LAMBADA, PIQA, RACE, SocialIQA, SciQ, SWAGFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsZero-shot Downstream Task EvaluationARC-e, BoolQ, HellaSwag, LAMBADA, PIQA, RACE, SocialIQA, SciQ, SWAG77.9ARC-e Accuracy12
Zero-shot Downstream Task EvaluationARC-e, BoolQ, HellaSwag, LAMBADA, PIQA, RACE, SocialIQA, SciQ, SWAG77.9ARC-e Accuracy12