Red-teaming on Illegal Activity principle v1 (test)
-2.73Mean Score (Best Category)RS
Evaluation Results
| Method | Links | |
|---|---|---|
| RSTarget Model=Qwen3-30B-A3B-Instruct-25072026.02 | -2.73 | |
| RSTarget Model=Gemma3-12B-IT2026.02 | -2.26 | |
| RSTarget Model=Llama-3.1-8B-Instruct2026.02 | -2.25 | |
| RSTarget Model=GPT-4.1-Mini2026.02 | -1.63 | |
| QCITarget Model=Gemma3-12B-IT2026.02 | 0.41 | |
| QCITarget Model=Qwen3-30B-A3B-Instruct-25072026.02 | 1.27 | |
| QCITarget Model=Llama-3.1-8B-Instruct2026.02 | 1.58 | |
| CRLTarget Model=Qwen3-30B-A3B-Instruct-25072026.02 | 1.86 | |
| QCITarget Model=GPT-4.1-Mini2026.02 | 2.13 | |
| CRLTarget Model=Gemma3-12B-IT2026.02 | 2.15 | |
| CRLTarget Model=GPT-4.1-Mini2026.02 | 2.4 | |
| CRLTarget Model=Llama-3.1-8B-Instruct2026.02 | 3.21 |