DocOS - Easy: leaderboard
Metric: Task completion rate (%; share of tasks whose final application state meets the goal after the agent searches the official documentation in a live browser for up to 15 steps and then executes for up to 50 steps; the 265 Easy tasks). Source: arxiv.org. Saturation forecast: Around January 2028. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | uitars-1.5-7B | 30.86 |
| 2 | MAI-UI-8B | 20.99 |
| 3 | GUI-Owl-7B | 9.88 |
| 4 | Qwen 3 VL 8B | 7.41 |
Interactive version: theaggregate.ai/benchmark?slug=docos-easy · How It Works · Data refreshed daily, snapshot 2026-09-26.