List your company

Red-teaming on Illegal Activity principle v1 (test)

-2.73Mean Score (Best Category)RS
-2.9676-1.36380.241.8438Feb 12, 2026

Evaluation results

MethodLinks
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-IT2026.020.41
QCITarget Model=Qwen3-30B-A3B-Instruct-25072026.021.27
QCITarget Model=Llama-3.1-8B-Instruct2026.021.58
CRLTarget Model=Qwen3-30B-A3B-Instruct-25072026.021.86
QCITarget Model=GPT-4.1-Mini2026.022.13
CRLTarget Model=Gemma3-12B-IT2026.022.15
CRLTarget Model=GPT-4.1-Mini2026.022.4
CRLTarget Model=Llama-3.1-8B-Instruct2026.023.21