Web Navigation on Mind2Web Service
36.27Success RateMem-W-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| Mem-W-8BBackbone=UI-Venus-1.5-8B2026.05 | 36.27 | |
| GUI-Owl-1.5-8BModel Class=Open-source Native Models2026.05 | 30.39 | |
| Qwen3-VL-32BModel Class=Open-source Native Models2026.05 | 27.45 | |
| GLM-4.1V-9B-ThinkingModel Class=Open-source Native Models2026.05 | 26.47 | |
| Qwen3-VL-8BModel Class=Open-source Native Models2026.05 | 26.47 | |
| Mem-W-4BBackbone=Qwen3-VL-4B2026.05 | 26.47 | |
| Qwen3-VL-2BModel Class=Open-source Native Models2026.05 | 23.52 | |
| Mem-W-7BBackbone=UI-TARS-1.5-7B2026.05 | 22.55 | |
| MAI-UI-2BModel Class=Open-source Native Models2026.05 | 21.57 | |
| Step-GUI-4BModel Class=Open-source Native Models2026.05 | 21.56 | |
| Qwen2.5-VL-7BModel Class=Open-source Native Models2026.05 | 17.65 | |
| UI-Venus-1.5-8BModel Class=Mem-W Models2026.05 | 15.69 | |
| Qwen3-VL-4BModel Class=Mem-W Models2026.05 | 14.71 | |
| UI-Venus-1.5-30B-A3BModel Class=Open-source Native Models2026.05 | 8.82 | |
| UI-TARS-1.5-7BModel Class=Mem-W Models2026.05 | 6.86 |