GUI Grounding on UI-Vision Functional
34.5Top-1 AccuracyOurs (Qwen3-VL-8B)
Evaluation Results
| Method | Links | |
|---|---|---|
| Ours (Qwen3-VL-8B)Model Category=Ours2026.04 | 34.5 | |
| Qwen3-VL-8BModel Category=General Open-source Models2026.04 | 30.6 | |
| GUI-SpotlightModel Category=GUI-specific Models2026.04 | 30.2 | |
| Qwen3-VL-4BModel Category=General Open-source Models2026.04 | 26.5 | |
| UI-TARS-1.5-7BModel Category=GUI-specific Models2026.04 | 25.1 | |
| Ours (UI-Tars1.5)Model Category=Ours2026.04 | 22.9 | |
| Aguvis-7BModel Category=GUI-specific Models2026.04 | 18.3 | |
| UGround-V1-7BModel Category=GUI-specific Models2026.04 | 17.1 | |
| OS-Atlas-Base-7BModel Category=GUI-specific Models2026.04 | 11.2 | |
| Qwen3-VL-2BModel Category=General Open-source Models2026.04 | 9.3 | |
| Claude-3.7 SonnetModel Category=Closed-Source Models2026.04 | 7.7 | |
| GPT-4oModel Category=Closed-Source Models2026.04 | 1.5 | |
| Qwen2.5-VL-7BModel Category=General Open-source Models2026.04 | 0.8 | |
| Qwen2.5-VL-3BModel Category=General Open-source Models2026.04 | 0.2 |