GUI Visual Question Answering on GUI 885-sample
100Eligibility RateGO-opt.
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| GO-opt.Victim=GUI-Owl-7B [54], Pass@k=pass@32026.04 | 100 | 24.18 | 35.59 | 44.29 | 48.36 | 50.96 | |
| UT-opt.Victim=UI-TARS-1.5-7B [39], Pass@k=pass@32026.04 | 100 | 12.99 | 20.79 | 26.67 | 29.72 | 32.99 | |
| GO-opt.Victim=UI-TARS-1.5-7B [39], Pass@k=pass@32026.04 | 99.97 | 14.04 | 21.86 | 27.97 | 31.71 | 34.43 | |
| Rand. Inject.Victim=UI-TARS-1.5-7B [39], Pass@k=pass@32026.04 | 99.89 | 2.38 | 3.73 | 4.75 | 6.22 | 7.58 | |
| Rand. Inject.Victim=GUI-Owl-7B [54], Pass@k=pass@32026.04 | 98.19 | 8.52 | 13.58 | 17.03 | 20.02 | 23.36 | |
| UT-opt.Victim=Qwen3-VL-8B-Instruct [5], Pass@k=pass@32026.04 | 96.61 | 13.33 | 20.35 | 26.08 | 29.12 | 31.7 | |
| GO-opt.Victim=Qwen3-VL-8B-Instruct [5], Pass@k=pass@32026.04 | 96.61 | 11.7 | 20.7 | 25.38 | 29.82 | 32.87 | |
| Rand. Inject.Victim=Qwen3-VL-8B-Instruct [5], Pass@k=pass@32026.04 | 96.5 | 2.34 | 3.98 | 6.21 | 7.14 | 8.43 | |
| UT-opt.Victim=GUI-Owl-7B [54], Pass@k=pass@32026.04 | 95.59 | 23.88 | 34.87 | 42.67 | 47.64 | 51.65 | |
| Rand. Inject.Victim=OpenCUA-7B [45], Pass@k=pass@32026.04 | 89.94 | 8.79 | 13.94 | 17.09 | 20.23 | 23.37 | |
| UT-opt.Victim=OpenCUA-7B [45], Pass@k=pass@32026.04 | 89.6 | 23.33 | 33.67 | 41.99 | 47.54 | 51.58 | |
| GO-opt.Victim=OpenCUA-7B [45], Pass@k=pass@32026.04 | 89.6 | 23.08 | 34.8 | 40.86 | 48.05 | 51.83 | |
| Rand. Inject.Victim=Qwen2.5-VL-7B-Instruct [40], Pass@k=pass@32026.04 | 11.3 | 50 | 66 | 73 | 79 | 82 | |
| UT-opt.Victim=Qwen2.5-VL-7B-Instruct [40], Pass@k=pass@32026.04 | 11.19 | 58.59 | 77.78 | 84.85 | 86.87 | 86.87 | |
| GO-opt.Victim=Qwen2.5-VL-7B-Instruct [40], Pass@k=pass@32026.04 | 11.19 | 68.69 | 82.83 | 85.86 | 87.88 | 88.89 |