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

Web-based Agent Interaction on WebShop (val)

84.4Success Rate

D2Skill(O3)

-3.37619.41242.264.988Mar 30, 2026Apr 1, 2026Apr 3, 2026Apr 6, 2026Apr 8, 2026Apr 10, 2026Apr 13, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2026.03
84.490.1
2026.03
81.389.2
2026.03
80.591.1
2026.03
79.988.2
2026.03
72.785.2
2026.03
72.686
2026.03
71.984.1
2026.03
67.277.4
2026.03
53.165.6
2026.03
46.967.8
2026.03
37.558.1
2026.04
36.88-
2026.04
33.68-
2026.04
31.79-
2026.04
31.34-
2026.04
30.94-
2026.04
30.8-
2026.04
30.69-
2026.04
30.48-
2026.04
30.43-
2026.04
30.26-
2026.04
29.31-
2026.04
28.9-
2026.04
28.13-
2026.03
16.514.1
2026.03
4.75.8
2026.03
3.916.6
2026.04
0-
2026.04
0-
2026.04
0-
2026.04
0-