ResearchTasksSegment-level mistake detectionSegment-level mistake detectionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedEgoPERZeProM (Q-L)85.2Quesadilla EDA6Jun 23, 2026CaptainCook4D (Average)AMNAR72.3EDA5Jun 23, 2026CaptainCook4D 5-recipe averageGTG2Vid16.2F1@.54Jun 23, 2026