ResearchDatasetsSuperGPQA, MMLU, BBEHSuperGPQA, MMLU, BBEHFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsGeneral-domain reasoningSuperGPQA, MMLU-Pro, BBEH40.75Overall Avg Score28