ResearchTasksFailure prediction stoppingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedALFWorldEndtoEndRL94.6Max Accuracy6Jun 5, 2026AppWorldα-STOP78.8Max Accuracy6Jun 5, 2026P4Gα-STOP77.5Max Accuracy6Jun 5, 2026BETOLDα-STOP80.8Max Accuracy6Jun 5, 2026PCSα-STOP87.4Max Accuracy6Jun 5, 2026