ResearchTasksClosed-ended reasoningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedGPQA Diamond (test)Majority Voting (MV)65.9Accuracy63Feb 26, 2026Closed regime n = 300Transactional leadership87.9Exact Match Accuracy21Jun 18, 2026AIME24TF-TTCL0.133Accuracy7Apr 16, 2026