Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agreement with outcome human labels on CUAVerifierBench Browserbase OM2W (n=106)
Loading...
88
Accuracy
Universal Verifier (UV)
46.4
57.2
68
78.8
Apr 5, 2026
Accuracy
F1 Score
Cohen’s κ
FNR
FPR
Updated 9d ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
Cohen’s κ
FNR
FPR
Universal Verifier (UV)
Verifier=UV, Backbone=...
2026.04
88
65
0.58
31
8
Universal Verifier
Verifier=UV, Base Mode...
2026.04
88
65
0.58
31
8
WebVoy.
Verifier=WebVoy., Back...
2026.04
74
50
0.36
18
28
WebJudge
Verifier=WebJudge, Bac...
2026.04
74
46
0.31
29
26
WebJudge
Verifier=WebJudge, Bac...
2026.04
64
44
0.26
12
40
WebJudge
Verifier=WebJudge, Bas...
2026.04
64
44
0.26
12
40
WebVoy.
Verifier=WebVoy., Back...
2026.04
48
35
0.13
12
60
WebVoyager
Verifier=WebVoy., Base...
2026.04
48
35
0.13
12
60
Feedback
Search any
task
Search any
task