Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Average Reward on AlfWorld (Agent Task)

59Average Reward

Ceiling Model

44.23248.06651.955.734Jul 25, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
59
57.5
56
55.2
2025.07
53.7
2025.07
51.5
2025.07
44.8