Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Adversarial Code Compliance on C++
Loading...
100
Decoupling Probability
DeepSeek-v3.2
30.632
48.641
66.65
84.659
Jan 29, 2026
Decoupling Probability
Severity Index
Updated 4d ago
Evaluation Results
Method
Method
Links
Decoupling Probability
Severity Index
DeepSeek-v3.2
Model Category=Open So...
2026.01
100
61.1
Gemma-3-27b
Model Category=Open So...
2026.01
97.8
47.1
Llama-3.1-8B
Model Category=Open So...
2026.01
97.8
43.7
Gemini-2.5-Flash
Model Category=Proprie...
2026.01
96.7
58.1
Qwen3-235B
Model Category=Open So...
2026.01
94.6
38.6
GPT-5
Model Category=Proprie...
2026.01
91
50.1
Llama-3.2-3B
Model Category=Open So...
2026.01
80.7
26.7
GPT-OSS-120B
Model Category=Open So...
2026.01
33.3
2.2
GPT-5-Mini
Model Category=Proprie...
2026.01
33.3
0.6
Feedback
Search any
task
Search any
task