GUI Navigation and Interaction on DynamicGUIBench
36.8Success Rate (Chrome)DynamicUI (w/ Qwen3-vl-8B)
Evaluation results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DynamicUI (w/ Qwen3-vl-8B)Step=502026.04 | 36.8 | 30 | 14.3 | 14.3 | 7.1 | 9.1 | 28.6 | 44.4 | 40 | 8.3 | 22.1 | |
| DynamicUI (w/ Qwen3-vl-8B)Step=152026.04 | 29 | 10 | 14.3 | 0 | 7.1 | 12.2 | 14.3 | 11.1 | 0 | 16.7 | 15.5 | |
| Qwen3-vl-8BStep=502026.04 | 26.3 | 22 | 14.3 | 0 | 7.1 | 7.5 | 14.3 | 0 | 60 | 8.3 | 15.1 | |
| Qwen3-vl-8BStep=152026.04 | 21.1 | 20 | 14.3 | 0 | 14.3 | 9.1 | 14.3 | 0 | 40 | 16.7 | 14.8 | |
| Qwen3-vl-4BStep=152026.04 | 18.4 | 10 | 7.1 | 0 | 7.1 | 9.1 | 14.3 | 0 | 40 | 0 | 10.7 | |
| EvoCUA-8BStep=502026.04 | 18.4 | 33 | 0 | 0 | 7.1 | 4.5 | 28.6 | 0 | 20 | 16.7 | 11.7 | |
| UITARS-1.5-7BStep=502026.04 | 13.2 | 10 | 7.1 | 0 | 7.1 | 9.1 | 0 | 0 | 20 | 0 | 8.1 | |
| Qwen3-vl-4BStep=502026.04 | 13.2 | 10 | 7.1 | 0 | 7.1 | 9.1 | 28.6 | 0 | 60 | 0 | 10.7 | |
| o3Step=502026.04 | 10.5 | 0 | 14.3 | 0 | 7.1 | 6.1 | 42.9 | 0 | 20 | 0 | 8.7 | |
| Seed1.8-VLStep=502026.04 | 10.5 | 10 | 0 | 14.3 | 7.1 | 3 | 0 | 0 | 0 | 16.7 | 6.7 | |
| o3Step=152026.04 | 7.9 | 10 | 7.1 | 0 | 7.1 | 6.1 | 0 | 0 | 20 | 8.3 | 6.7 | |
| doubao-1-5-0717Step=502026.04 | 5.3 | 0 | 7.1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 2.8 |