FineState-Bench - Desktop: leaderboard
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 810 desktop instances of FineState-Bench; single-point protocol on static screenshots, no localization hints; higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet | 3.4 |
| 2 | GPT-4o | 2.2 |
| 3 | Gemini 2.5 Flash | 0.7 |
Interactive version: theaggregate.ai/benchmark?slug=finestate-bench-desktop · How It Works · Data refreshed daily, snapshot 2026-10-07.