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

Agent task completion on AppWorld

83.7TGC Success Rate (N)

PREPING

69.03672.84376.6580.457May 11, 2026
Updated 19d ago

Evaluation Results

MethodLinks
2026.05
83.770.272.254.770.2
2026.05
82.769.16950.367.8
2026.05
80.465.578.360.971.3
2026.05
74.65656.63555.6
2026.05
73.652.455.936.954.7
2026.05
72.855.45634.554.7
2026.05
69.649.456.736.753.1