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

DeepShop

Benchmarks

Task NameDataset NameSOTA ResultTrend
Visual Web Agent NavigationDeepShop
Success Rate68.7
21
GUI agent successDeepShop (test)
Success Rate64
17
Browser-useDeepShop
Success Rate0.62
13
Web NavigationDeepShop (live)
Accuracy65.8
11
Showing 4 of 4 rows