E-commerce Risk Management Multi-step Trajectory Evaluation on RISK-Bench Multi-step
82.8Multi-step Success RateRISK-R1-7B
Evaluation Results
| Method | Links | |
|---|---|---|
| RISK-R1-7BModel Category=Ours, Base Model=Qwen2.5-VL-7B-Instruct, Training Type=RFT2025.09 | 82.8 | |
| RISK-SFT-7BModel Category=Ours, Base Model=Qwen2.5-VL-7B-Instruct, Training Type=SFT2025.09 | 75.3 | |
| GPT-4oModel Category=Commercial Models2025.09 | 74 | |
| Qwen2.5-VL-72BModel Category=General Open-source Models2025.09 | 67.8 | |
| Qwen-VL-MaxModel Category=Commercial Models2025.09 | 50 | |
| Qwen2.5-VL-7BModel Category=General Open-source Models2025.09 | 0.6 | |
| InternVL3-8BModel Category=General Open-source Models2025.09 | 0 | |
| UI-TARS-2BModel Category=GUI-specific Models (SFT)2025.09 | 0 | |
| UI-TARS-7BModel Category=GUI-specific Models (SFT)2025.09 | 0 | |
| UI-TARS-72BModel Category=GUI-specific Models (SFT)2025.09 | 0 | |
| OS-Atlas-7BModel Category=GUI-specific Models (SFT)2025.09 | 0 | |
| ShowUI-2BModel Category=GUI-specific Models (SFT)2025.09 | 0 | |
| Aguvis-7BModel Category=GUI-specific Models (SFT)2025.09 | 0 | |
| GUI-R1-3BModel Category=GUI-specific Models (RL)2025.09 | 0 | |
| GUI-R1-7BModel Category=GUI-specific Models (RL)2025.09 | 0 | |
| InfiGUI-R1-3BModel Category=GUI-specific Models (RL)2025.09 | 0 | |
| GUI-G1-3BModel Category=GUI-specific Models (RL)2025.09 | 0 | |
| UI-TARS-1.5-7BModel Category=GUI-specific Models (RL)2025.09 | 0 | |
| UI-Venus-Navi-7BModel Category=GUI-specific Models (RL)2025.09 | 0 |