Webshop
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
WebShop
100CDA
24
WebShop (test)
0.95CDA
24
WebShop
69.2Average Reward
24
WebShop (Seen)
86.2Average Reward
22
WebShop
68.36Average Task Performance
20
WebShop
92.6TSR
20
WebShop (seen)
42.5Success Rate
20
Webshop (test)
100Search
20
WebShop
89.8Score
19
WebShop (test)
85.5Score
18
WebShop OOD v1.0
42.1Access Success Rate
18
WebShop Agent
18Delay (s)
18
WebShop
34.8Average Reasoning Length (tokens)
18
WebShop Drift II
95Success Rate
18
WebShop Drift I
95Success Rate
18
WebShop Source
100Score
18
WebShop Drift II - Semantic Shift
95Success Rate
18
WebShop Drift I - Semantic Shift
95Success Rate
18
WebShop semantic shift Source
1Score
18
WebShop
70.4Average Reward
17
WebShop (WS) (test)
36.7Loop Ratio
17
WebShop (test)
63Token F1
16
WebShop (test)
34.6Success Rate
16
WebShop (WS)
79.05EM Accuracy
16
WebShop Clarification (test)
0.245Success Rate
15