ResearchDatasetsMC, GEN, AGIEval, BBH, MMLUMC, GEN, AGIEval, BBH, MMLUFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMultiple Choice Question AnsweringMC9, GEN5, AGIEval, BBH, MMLU, MMLU-Pro (test)69.36MC9 Accuracy12