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

WoB

Benchmarks

Task NameDataset NameSOTA ResultTrend
GUI AutomationMiniWob++
Success Rate77.2
25
Web AutomationMiniWoB++ 56 tasks (test)
Success Rate99.2
15
Web-based interactionMiniWoB
Success Rate74.7
14
password navigationMiniWoB (test)
Success Rate10,000
10
GUI Agent AutomationMiniWoB++ (Online)
Success Rate59.7
6
Web-based task completionMiniWoB++ 53 tasks (All)
Success Rate94
5
payment navigationgMiniWoB (test)
Success Rate9,300
4
Showing 7 of 7 rows