ResearchDatasetsStandard NLP Evaluation SuiteStandard NLP Evaluation SuiteFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsNatural Language UnderstandingStandard NLP Evaluation Suite (BoolQ, HellaSwag, WinoGrande, ARC, OBQA, RACE)0.605BoolQ Accuracy2
Natural Language UnderstandingStandard NLP Evaluation Suite (BoolQ, HellaSwag, WinoGrande, ARC, OBQA, RACE)0.605BoolQ Accuracy2