ResearchDatasetsOBQA, ARC, Riddle, PQA, and MMLUOBQA, ARC, Riddle, PQA, and MMLUFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsReasoning and Multitask Language UnderstandingOBQA, ARC, Riddle, PQA, and MMLU77OBQA Accuracy4