ResearchTasksExpert Question AnsweringFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedHLE All Non-EasyQA+9.3Recovery Rate3Apr 6, 2026HLE Med. + HardQA+13.1Recovery Rate3Apr 6, 2026GPQA MC All Non-EasyQA13.6Recovery Rate3Apr 6, 2026GPQA MC (Med. + Hard)Bit-Limited Chain-of-Thought (BL-CoT)40Recovery Rate3Apr 6, 2026HLEQwQ-32B11.2Accuracy2Jun 4, 2026