Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Task-free exploration on WA Shopping
Loading...
43.1
Success Rate
AMZ + Target + WA
37.172
38.711
40.25
41.789
Oct 17, 2025
Success Rate
Skill Usage Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
Skill Usage Rate
AMZ + Target + WA
Training Setting=Self-...
2025.10
43.1
14.6
WA
Training Setting=Singl...
2025.10
42.3
14.9
WA → Target → AMZ
Training Setting=Seque...
2025.10
42.1
10.8
AMZ → WA
Training Setting=Seque...
2025.10
40.2
12.3
SkillWeaver*
Training Setting=Seque...
2025.10
39.8
8.6
Target → AMZ → WA
Training Setting=Seque...
2025.10
39.5
11.5
AMZ → Target → WA
Training Setting=Seque...
2025.10
38.2
11.9
AMZ
Training Setting=Singl...
2025.10
38.1
2.7
Target
Training Setting=Singl...
2025.10
38
2.1
Baseline
Iterations=–
2025.10
37.4
-
Feedback
Search any
task
Search any
task