Attack Success Rate Evaluation on HRL/LRL Safety Prompts English, Single Image v1
0ASRClaude 3.5 Sonnet
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude 3.5 Sonnet2025.04 | 0 | |
| GPT-4o Mini2025.04 | 0.03 | |
| Claude 3 Haiku2025.04 | 0.1 | |
| GPT-4o2025.04 | 0.13 | |
| Gemini 1.5 Pro2025.04 | 0.23 | |
| Gemini 1.5 Flash2025.04 | 0.72 |