ResearchTasksAbstention ClassificationAbstention ClassificationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedHotPotQA (test)Ternary1Abs(0)9Apr 14, 2026NaturalQA (test)OTC100Accuracy (Abs=0)9Apr 14, 2026