Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Segment-level mistake detection on CaptainCook4D 5-recipe average
Loading...
16.2
F1@.5
GTG2Vid
9.96
11.58
13.2
14.82
Jun 19, 2026
F1@.5
EDA
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1@.5
EDA
GTG2Vid
Evaluation Protocol=Fu...
2026.06
16.2
66.3
ZeProM (Q-L)
Evaluation Protocol=Ze...
2026.06
16
67.4
EgoPED
Evaluation Protocol=Fu...
2026.06
10.5
-
ZeProM (Q-M)
Evaluation Protocol=Ze...
2026.06
10.2
66.3
Feedback
Search any
task
Search any
task