WindowsWorld (Screenshot + Accessibility Tree) - Intermediate Checkpoints: leaderboard
GUI agents on WindowsWorld (2026), 181 persona-driven professional tasks across 17 Windows desktop applications, mostly multi-application workflows plus infeasible tasks to reject, with the model observing screenshots plus the accessibility tree and acting through PyAutoGUI. Share of human-verified intermediate checkpoints reached on the feasible tasks, in percent; higher is better.
Metric: Intermediate checkpoint score (%): share of each task's human-verified intermediate checkpoints reached, averaged over the 169 feasible Level 1 to 3 tasks of WindowsWorld (persona-driven Windows desktop tasks across 17 applications, executed with a unified PyAutoGUI action space and level-specific step budgets of 15, 25, 40 and 20), the model observing screenshots plus the accessibility tree, states judged by a human-validated Qwen3-VL-Plus judge; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 50.32 | #152 |
| 2 | Gemini 3 Pro (Preview) | 38.8 | #119 |
| 3 | Qwen 3 VL Plus | 19.37 | #512 |
| 4 | GPT-5.2 | 6.62 | #185 |
| 5 | Claude Sonnet 4.5 | 5.84 | #261 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=windowsworld-screenshot-plus-accessibility-tree-intermediate-checkpoints · How It Works · Data refreshed daily, snapshot 2026-11-21.