Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language Agent Task on WebShop (OOD)
Loading...
49.6
Score
Task-Perturbed NLL Optimization
45.024
46.212
47.4
48.588
Jun 25, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Task-Perturbed NLL Optimization
Backbone=Qwen3-8B
2026.06
49.6
Task Aug
Backbone=Qwen3-8B
2026.06
47.5
SFT
Backbone=Qwen3-8B
2026.06
47.1
COIN
Backbone=Qwen3-8B
2026.06
45.2
Feedback
Search any
task
Search any
task