ResearchDatasetsOBQA, ARC, Riddle, PQA, and MMLUFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsReasoning and Multitask Language UnderstandingOBQA, ARC, Riddle, PQA, and MMLU77OBQA Accuracy4