GUI-RobustEval - Error Depth 1: 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 1: one step past the root-cause error; up to 50 steps including the prefix; mean of 3 runs). Source: arxiv.org. Saturation forecast: Around 2034. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 VL 8B Instruct | 38.7 |
| 2 | uitars-1.5-7B | 34.2 |
| 3 | GPT-5.1 | 16.5 |
| 4 | GUI-Owl-7B | 15.6 |
| 5 | Qwen 2.5 VL 7B Instruct | 3 |
Interactive version: theaggregate.ai/benchmark?slug=gui-robusteval-error-depth-1 · How It Works · Data refreshed daily, snapshot 2026-09-26.