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

Agent Task on AppWorld Normal (test)

76.2TGC

ReAct + ACE

-1.810418.442338.69558.9477Oct 6, 2025Nov 7, 2025Dec 9, 2025Jan 10, 2026Feb 11, 2026Mar 15, 2026Apr 17, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.10
76.264.3
2025.10
7564.3
2026.04
73.8155.36
2025.10
69.653.6
2025.10
65.558.9
2025.10
64.944.6
2025.10
64.346.4
2025.10
63.742.9
2026.04
54.7633.93
2026.04
53.5732.14
2026.04
47.0230.36
2026.04
35.7114.28
2026.04
31.5512.5
2026.04
31.548.92
2026.04
30.421.4
2026.04
27.9812.5
2026.04
23.817.14
2026.04
17.863.57
2026.04
16.675.36
2026.04
1.190