ResearchTasksReasoning failure predictionReasoning failure predictionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedCodeLingua (L3)thought-tree-based classifier76Accuracy2Apr 21, 2026CodeLingua (L2)thought-tree-based classifier75Accuracy2Apr 21, 2026CodeLingua (L1)thought-tree-based classifier73Accuracy2Apr 21, 2026