ResearchDatasetsMMLU, AGIEvalMMLU, AGIEvalFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsGeneral Language UnderstandingMMLU, AGIEval0.559MMLU Score10Language UnderstandingMMLU, MMLU-Redux, MMLU-Pro, AGIEval—Primary metric0