Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Error Recognition on ALFWorld
Loading...
35
Tolerant Accuracy (±1 step)
CORRECT
21.48
24.99
28.5
32.01
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
35
13
Baseline
Base Model=GPT-5-nano,...
2025.09
22
-
Feedback
Search any
task
Search any
task
