ResearchTasksQuery CategorizationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedAI pseudo-reference dataset OpenAI-GPT-4o-MiniCoT BFS132.1F1 Score (Scaled)3Feb 27, 2026Human judgment dataCoT BFS89.8Micro F11Feb 27, 2026