ResearchDatasetsMMLU, SuperGPQA, LPFQAMMLU, SuperGPQA, LPFQAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsWorld KnowledgeMMLU, MMLU-pro, SuperGPQA, LPFQA93.8Pass@1 Score20