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

Agent Task Completion on AppWorld (Official)

60.1Accuracy

Metis

51.46853.70955.9558.191Jun 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
60.197.411.257.9
2026.06
54.8100.312.39.4
2026.06
53.6422.413.66.9
2026.06
51.8112.614.550