Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Error recognition on WebShop
Loading...
24
Tolerant Accuracy (±1 step)
CORRECT
15.68
17.84
20
22.16
Sep 28, 2025
Tolerant Accuracy (±1 step)
Improvement (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Tolerant Accuracy (±1 step)
Improvement (%)
CORRECT
Base Model=GPT-5-nano,...
2025.09
24
8
Baseline
Base Model=GPT-5-nano,...
2025.09
16
-
Feedback
Search any
task
Search any
task
