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

Agent Task on WebShop

99Success Rate

W2SG with MCTS

2.90427.85252.877.748Jul 25, 2025Sep 11, 2025Oct 29, 2025Dec 16, 2025Feb 2, 2026Mar 22, 2026May 10, 2026
Updated 22d ago

Evaluation Results

MethodLinks
99-56.9-
2025.07
97.5-52-
97-53.2-
96.5-58.3-
96-52.3-
2025.07
94-51-
2025.07
87-47.1-
2026.03
87---
2026.03
84---
2026.03
81---
2026.05
71.5--81.2
2026.05
69.3--81
2026.05
68.7--81.4
2026.03
67---
2026.05
65.6--77.8
2026.03
59---
2026.05
52--0.7392
51--0.7132
2026.05
47--0.73
2026.02
43.227.1--
2026.02
4124.8--
2026.02
38.424.1--
2026.03
37---
2026.05
36--0.7034
2026.05
35.9--42.5
2026.02
3521.6--
2026.05
35--0.5204
2026.05
34--0.5998
2026.05
32--0.501
2026.05
32--0.5355
2026.05
32--0.516
2026.05
29--0.4582
2026.02
26.817.6--
2026.02
26.211.1--
2026.02
25.417.2--
2026.05
23.7--31.8
2026.02
22.614.3--
2026.02
2114.6--
2026.05
21--0.5819
2026.02
20.813.7--
2026.02
20.813.1--
2026.05
19.5--46.2
2026.02
18.812.2--
2026.05
17--0.2973
2026.02
16.411.5--
2026.02
15.25.4--
2026.02
159.6--
2026.02
12.28.2--
2026.05
7.8--26.4
2026.02
6.64.4--