Attack Success Rate Evaluation on HRL/LRL Safety Prompts English Multi-Image v1
2ASRGPT-4o Mini
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o Mini2025.04 | 2 | |
| Claude 3.5 Sonnet2025.04 | 25 | |
| Gemini 1.5 Pro2025.04 | 26 | |
| Claude 3 Haiku2025.04 | 27 | |
| Gemini 1.5 Flash2025.04 | 30 | |
| GPT-4o2025.04 | 37 |