GUI-RobustEval - Error Depth 0: 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 0: the verified-correct prefix; up to 50 steps including the prefix; mean of 3 runs). Source: arxiv.org. Saturation forecast: Around 2032. 11 models tracked.

Top models

#ModelScore
1Qwen 3 VL 8B Instruct48.1
2uitars-1.5-7B39.6
3GUI-Owl-7B28.7
4GPT-5.123.4
5Qwen 2.5 VL 7B Instruct5.1

Interactive version: theaggregate.ai/benchmark?slug=gui-robusteval-error-depth-0 · How It Works · Data refreshed daily, snapshot 2026-09-26.