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

Agent Task Execution on AppWorld online mode

57.7Accuracy

SkillComposer-4B

55.155.77556.4557.125Jun 4, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
57.788.3
2026.06
57.186
2026.06
55.288.1