ResearchTasksLong-CoT Question GenerationLong-CoT Question GenerationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedCoDiQ-Bench 1.0 (test)Qwen3-4B4.2Dialogue Rounds19Feb 26, 2026