ResearchTasksTask Progression Failure DetectionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedCover Object (Combined)GPT-4o Image QA100TPR16Mar 13, 2026Cover Object Policy Success Rate: 3% (Out-of-Distribution)GPT-4o Image QA100TPR16Mar 13, 2026Cover Object Policy Success Rate: 98% (In-Distribution)Temporal Non-Distr. Min.100TPR16Mar 13, 2026Close Box CombinedGPT-4o Image QA100TPR12Mar 13, 2026Close Box Out-of-DistributionGPT-4o Image QA100TPR12Mar 13, 2026Close Box In-DistributionTemporal Non-Distr. Min.100TPR12Mar 13, 2026