FineState-Bench - Control Localization: leaderboard
FineState-Bench (2026) shows a GUI agent a screenshot and asks it to locate a control and then point where an action sets the control to an exact target state, such as a slider value or a selected option. Share of instances where the first point lands on the target control, averaged over the three platforms, in percent; higher is better.
Metric: Localization success rate (SR@Loc, %): the predicted control-location point falls inside the current visible extent of the target control, mean of the mobile, web and desktop rates, on FineState-Bench (2,209 instances); single-point protocol on static screenshots, no localization hints; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 8 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | UGround-V1-7B | 53 | |
| 2 | OS-Atlas-Base-7B | 42 | |
| 3 | Gemini 2.5 Flash | 36.4 | #466 |
| 4 | ShowUI-2B | 25.8 | |
| 5 | GPT-4o | 24.8 | #754 |
| 6 | CogAgent-9B-20241220 | 23.7 | |
| 7 | Claude 3.5 Sonnet | 23 | #755 |
| 8 | Jedi-7B-1080p | 12.7 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=finestate-bench-control-localization · How It Works · Data refreshed daily, snapshot 2026-11-22.