Kaixin Li et al.
ScreenSpot Pro
A GUI-grounding benchmark for 1,581 instructions in full-screen, high-resolution professional interfaces. It tests where a target is, not whether an agent can finish the surrounding workflow.
ModelsModels with a result.20
Top-3 spreadPoints from first to third.7.3 pts
YearYear of release.2025
Result and price
12 of 20 results
Results
20 results#ModelResultThe score from the source.
