GUI Localization on GUIZoom-Bench easy-mislead
47.6Localization AccuracyQwen3-VL-8B
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen3-VL-8BZoom Depth=d32025.12 | 47.6 | |
| Qwen3-VL-32BZoom Depth=d42025.12 | 47.6 | |
| Qwen3-VL-32BZoom Depth=d32025.12 | 45.2 | |
| Qwen3-VL-8BZoom Depth=d42025.12 | 42.9 | |
| UI-Venus-7BZoom Depth=d42025.12 | 42.9 | |
| UI-Venus-7BZoom Depth=d32025.12 | 40.5 | |
| Qwen3-VL-8BZoom Depth=d22025.12 | 38.1 | |
| UI-Venus-7BZoom Depth=d22025.12 | 38.1 | |
| Qwen3-VL-32BZoom Depth=d22025.12 | 35.7 | |
| UI-Venus-7BZoom Depth=d12025.12 | 31 | |
| UI-TARS-1.5-7BZoom Depth=d32025.12 | 28.6 | |
| UI-TARS-1.5-7BZoom Depth=d42025.12 | 28.6 | |
| Qwen3-VL-8BZoom Depth=d12025.12 | 26.2 | |
| UI-TARS-1.5-7BZoom Depth=d22025.12 | 26.2 | |
| Qwen3-VL-32BZoom Depth=d12025.12 | 23.8 | |
| UI-TARS-7BZoom Depth=d32025.12 | 21.4 | |
| UI-TARS-7BZoom Depth=d22025.12 | 19 | |
| UI-TARS-7BZoom Depth=d42025.12 | 19 | |
| UI-TARS-1.5-7BZoom Depth=d12025.12 | 19 | |
| UI-TARS-7BZoom Depth=d12025.12 | 16.7 | |
| Qwen2.5-VL-7BZoom Depth=d22025.12 | 9.5 | |
| Qwen2.5-VL-7BZoom Depth=d42025.12 | 9.5 | |
| Qwen2.5-VL-7BZoom Depth=d12025.12 | 7.1 | |
| Qwen2.5-VL-7BZoom Depth=d32025.12 | 7.1 | |
| Claude-4.5-SonnetZoom Depth=d12025.12 | 5.9 | |
| GPT-5Zoom Depth=d12025.12 | 3.1 | |
| GPT-5Zoom Depth=d22025.12 | 2.4 | |
| GPT-5Zoom Depth=d32025.12 | 2.4 | |
| GPT-5Zoom Depth=d42025.12 | 2.4 |