Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

CaptainCook4D

Benchmarks

Task NameDataset NameSOTA ResultTrend
Segment-level mistake detectionCaptainCook4D (Average)
EDA72.3
5
Segment-level mistake detectionCaptainCook4D 5-recipe average
F1@.516.2
4
Error DetectionCaptainCook4D
Precision66.8
3
Showing 3 of 3 rows