ResearchTasksDebatingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedInspireDebateo1-mini84.4EA10Feb 26, 2026Human Evaluation DebateGPT-4o-mini86.6EA10Feb 26, 2026