FineState-Bench - Mobile: 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. Exact-state success rate on mobile screens, in percent; higher is better.
Metric: Exact-state success rate at interact (ES-SR@Int, %): the predicted operation point falls inside the state-changing region of the target control and the resulting state equals the instructed exact goal state (a slider value, toggle, selected option), on the 698 mobile instances of FineState-Bench; single-point protocol on static screenshots, no localization hints; higher is better. Source: arxiv.org. Saturation forecast: Around October 2027. 8 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | UGround-V1-7B | 19.6 | |
| 2 | Gemini 2.5 Flash | 17.6 | #466 |
| 3 | OS-Atlas-Base-7B | 12.8 | |
| 4 | Claude 3.5 Sonnet | 11.5 | #755 |
| 5 | GPT-4o | 6.2 | #754 |
| 6 | ShowUI-2B | 5.2 | |
| 7 | CogAgent-9B-20241220 | 1.8 | |
| 8 | Jedi-7B-1080p | 1.5 |
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-mobile · How It Works · Data refreshed daily, snapshot 2026-11-22.