Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Sequential Decision Making on WebShop (post-training evaluation)
Loading...
14.8
Rollout Length
Starting policy
6.5008
8.6554
10.81
12.9646
Jun 30, 2026
Rollout Length
Updated 24d ago
Evaluation Results
Method
Method
Links
Rollout Length
Starting policy
Backbone=Qwen2.5-7B-In...
2026.06
14.8
GRPO
Backbone=Qwen2.5-7B-In...
2026.06
8
TRIAGE
Backbone=Qwen2.5-7B-In...
2026.06
6.82
Feedback
Search any
task
Search any
task