ResearchDatasetsCaptainCook4DFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsSegment-level mistake detectionCaptainCook4D (Average)72.3EDA5Segment-level mistake detectionCaptainCook4D 5-recipe average16.2F1@.54Error DetectionCaptainCook4D66.8Precision3