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

Task Goal Completion on AppWorld Average 168 tasks (test normal)

44Accuracy

No compression

25.48830.29435.139.906Jun 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
4419.192.30
2026.06
41.121.869.10
2026.06
34.530.656.50
2026.06
26.233.551.25.45