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

Interactive Environment Task Completion on WebShop (Seen)

86.2Average Reward

EAGLET + GiGPO

55.10463.17771.2579.323Oct 7, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.10
86.2
2025.10
83.5
2025.10
82.5
2025.10
80.1
2025.10
76.6
2025.10
75.3
2025.10
74.7
2025.10
72.6
2025.10
72.5
2025.10
70.8
2025.10
70.2
2025.10
70.2
2025.10
68.4
2025.10
66.9
2025.10
66.7
2025.10
66.7
2025.10
65.5
2025.10
64.8
2025.10
63.3
2025.10
63.2
2025.10
58.6
2025.10
56.3