ResearchTasksAnswerability PredictionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedCODE n=30 (matched pairs)Refusal (Keyword Classifier)85AUC9May 6, 2026FACT n=10 (matched pairs)Refusal (Keyword Classifier)0.75AUC9May 6, 2026MATH n=50 (matched pairs)Geometry (own_dist)84.1AUC9May 6, 2026