Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Secure Code Generation on Primary Dataset
Loading...
8
Total Vulnerabilities
gemini-2.5
6.48
16.74
27
37.26
May 22, 2026
Total Vulnerabilities
Updated 8d ago
Evaluation Results
Method
Method
Links
Total Vulnerabilities
gemini-2.5
Prompting Strategy=MA-CoT
2026.05
8
claude-4.5
Prompting Strategy=MA-CoT
2026.05
14
gpt-5
Prompting Strategy=MA-CoT
2026.05
17
gpt-5
Prompting Strategy=Van...
2026.05
22
gemini-2.5
Prompting Strategy=Van...
2026.05
24
gemini-2.5
Prompting Strategy=Cha...
2026.05
26
gpt-5
Prompting Strategy=Zer...
2026.05
28
gpt-5
Prompting Strategy=Cha...
2026.05
29
gemini-2.5
Prompting Strategy=Zer...
2026.05
29
claude-4.5
Prompting Strategy=Zer...
2026.05
43
claude-4.5
Prompting Strategy=Cha...
2026.05
43
claude-4.5
Prompting Strategy=Van...
2026.05
46
Feedback
Search any
task
Search any
task