ResearchDatasetsNLP SuiteNLP SuiteFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsNatural Language UnderstandingNLP Suite (BoolQ, RTE, HellaSwag, WinoG, ARC-E, ARC-C, OpenBookQA) zero-shot72.5Average Accuracy41
Natural Language UnderstandingNLP Suite (BoolQ, RTE, HellaSwag, WinoG, ARC-E, ARC-C, OpenBookQA) zero-shot72.5Average Accuracy41