ResearchDatasetsMMLU, ARC-c, ARC-e, CSQA, OBQA, PIQA, SIQA, WinograndeMMLU, ARC-c, ARC-e, CSQA, OBQA, PIQA, SIQA, WinograndeFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMultiple-choice Question AnsweringMMLU, ARC-c, ARC-e, CSQA, OBQA, PIQA, SIQA, Winogrande zero-shot30.81MMLU Accuracy (zero-shot)9
Multiple-choice Question AnsweringMMLU, ARC-c, ARC-e, CSQA, OBQA, PIQA, SIQA, Winogrande zero-shot30.81MMLU Accuracy (zero-shot)9