Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Red-teaming on Illegal Activity principle v1 (test)
Loading...
-2.73
Mean Score (Best Category)
RS
-2.9676
-1.3638
0.24
1.8438
Feb 12, 2026
Mean Score (Best Category)
Updated 4d ago
Evaluation Results
Method
Method
Links
Mean Score (Best Category)
RS
Target Model=Qwen3-30B...
2026.02
-2.73
RS
Target Model=Gemma3-12...
2026.02
-2.26
RS
Target Model=Llama-3.1...
2026.02
-2.25
RS
Target Model=GPT-4.1-Mini
2026.02
-1.63
QCI
Target Model=Gemma3-12...
2026.02
0.41
QCI
Target Model=Qwen3-30B...
2026.02
1.27
QCI
Target Model=Llama-3.1...
2026.02
1.58
CRL
Target Model=Qwen3-30B...
2026.02
1.86
QCI
Target Model=GPT-4.1-Mini
2026.02
2.13
CRL
Target Model=Gemma3-12...
2026.02
2.15
CRL
Target Model=GPT-4.1-Mini
2026.02
2.4
CRL
Target Model=Llama-3.1...
2026.02
3.21
Feedback
Search any
task
Search any
task
