GUI-RobustEval - Error Depth 3: leaderboard
Metric: Post-error success rate (%; the agent takes over a desktop task from an erroneous prefix replayed from another agent's failed OSWorld trajectory, error depth 3: three steps past the root-cause error; up to 50 steps including the prefix; mean of 3 runs). Source: arxiv.org. Saturation forecast: Around 2035. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 VL 8B Instruct | 30 |
| 2 | uitars-1.5-7B | 27.8 |
| 3 | GPT-5.1 | 13.1 |
| 4 | GUI-Owl-7B | 8.1 |
| 5 | Qwen 2.5 VL 7B Instruct | 2.9 |
Interactive version: theaggregate.ai/benchmark?slug=gui-robusteval-error-depth-3 · How It Works · Data refreshed daily, snapshot 2026-09-26.