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

MobileWorld

Benchmarks

Task NameDataset NameSOTA ResultTrend
Mobile GUI NavigationMobileWorld GUI-Only 117 tasks (test)
Pass@1 Success Rate43.9
32
GUI Agent InteractionMobileWorld GUI-Only
SR55.6
14
Mobile GUI InteractionMobileWorld
GUI-ONLY Score55.6
14
Mobile GUI task executionMobileWorld
Success Rate12
11
Mobile agent navigationMobileWorld (unseen environments)
Success Rate (SR)23.3
8
Mobile GUI Agent NavigationMobileWorld
Success Rate (SR)58
4
Showing 6 of 6 rows