Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Web Navigation on WebShop (val)
Loading...
85.3
Success Rate
TSR (Beam Search)
-0.292
21.929
44.15
66.371
Feb 12, 2026
Success Rate
Avg Response Length
Avg Interaction Turns
Updated 4d ago
Evaluation Results
Method
Method
Links
Success Rate
Avg Response Length
Avg Interaction Turns
TSR (Beam Search)
Model=Qwen2.5-3B
2026.02
85.3
453
5.8
TSR (Lookahead)
Model=Qwen2.5-3B
2026.02
82.3
475
6.1
TSR (Best-of-N)
Model=Qwen2.5-3B
2026.02
77.3
504
6.5
Instance Filtering
Model=Qwen2.5-3B
2026.02
70.3
519
6.8
Base Model
Model=Qwen2.5-3B
2026.02
3
747
7.7
Feedback
Search any
task
Search any
task