ResearchTasksKnowledge & QAKnowledge & QAFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMMLU-ProCoT2-Meta88.4Accuracy (Knowledge & QA)9Jun 11, 2026TruthfulQACoT2-Meta92.8Accuracy5Mar 31, 2026