Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Attack Evaluation on HarmfulQA
Loading...
16
ASR
DeepSeek V3.1
14.7
23.475
32.25
41.025
Jan 8, 2026
ASR
Updated 4d ago
Evaluation Results
Method
Method
Links
ASR
DeepSeek V3.1
Model=DeepSeek V3.1
2026.01
16
Grok 3 Mini
Model=Grok 3 Mini
2026.01
17.5
Gemini 2.5 Flash
Model=Gemini 2.5 Flash
2026.01
18
Qwen2.5 7B
Model=Qwen2.5 7B
2026.01
21
GPT-4o-mini
Model=GPT-4o-mini
2026.01
22.5
Mixtral 8×7B
Model=Mixtral 8×7B
2026.01
48.5
Feedback
Search any
task
Search any
task