ResearchDatasetsHellaSwag, ARC, PIQA, LambadaHellaSwag, ARC, PIQA, LambadaFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsZero-shot Commonsense Reasoning and KnowledgeHellaSwag, ARC (Easy and Challenge), PIQA, Lambada (test)55.4HellaSwag Accuracy7
Zero-shot Commonsense Reasoning and KnowledgeHellaSwag, ARC (Easy and Challenge), PIQA, Lambada (test)55.4HellaSwag Accuracy7