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

Agent Task on AppWorld Average

59.5Average Score

ReAct + ACE

41.71646.33350.9555.567Oct 6, 2025
Updated 19d ago

Evaluation Results

MethodLinks
2025.10
59.5
2025.10
59.4
2025.10
57.2
2025.10
51.9
2025.10
46.4
2025.10
46
2025.10
42.4