Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Jailbreak Robustness on Jailbreak Cipher, CodeChameleon (test)
Loading...
95.75
Cipher Success Rate
DASE
27.37
45.1225
62.875
80.6275
Jan 29, 2026
Cipher Success Rate
CodeChameleon Success Rate
Average Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
Cipher Success Rate
CodeChameleon Success Rate
Average Success Rate
DASE
Base Model=Kimi-K2-Ins...
2026.01
95.75
60.9
78.33
Gemma-2 + SaRFT
Size=9B
2026.01
87.5
3.1
45.3
Kimi-K2-Instruct
Size=1T
2026.01
85.5
39.5
62.5
gpt-oss-120b
Size=120B
2026.01
71
82.4
76.7
Qwen3-235B-A22B-Instruct-2507
Size=235B
2026.01
70.75
80.1
75.42
DASE
Base Model=GPT-5.2, Si...
2026.01
68
100
84
LLaMA-3 + SaRFT
Size=8B
2026.01
64
55.1
59.55
GPT-5.2
Size=Undisclosed
2026.01
63.5
95.6
79.55
Qwen3-32B
Size=32B
2026.01
61.75
55.8
58.77
Qwen2.5 + SaRFT
Size=7B
2026.01
30
14.2
22.1
Feedback
Search any
task
Search any
task