Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Anomaly Detection on R2R Unseen (val)
Loading...
1.5
EDR
Act. Failure
-0.116
10.792
21.7
32.608
Mar 14, 2026
EDR
FER
Gap
Precision
Recall
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
EDR
FER
Gap
Precision
Recall
F1 Score
Act. Failure
Type=rule-based heuristic
2026.03
1.5
6.3
4.8
77.9
5.6
10.4
Stagnation
Type=rule-based heuristic
2026.03
29.6
5.9
23.7
95.6
38.7
55.1
Navigation Heads
K=3, Window size (W)=1...
2026.03
41.9
9.6
32.2
92.5
65.1
76.4
Feedback
Search any
task
Search any
task