Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Vulnerability Detection on Average
Loading...
65.08
Precision
Qwen3-14B
51.0504
54.6927
58.335
61.9773
Feb 7, 2026
Precision
Recall
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Precision
Recall
F1 Score
Qwen3-14B
Source Type=Open-Sourc...
2026.02
65.08
54.79
58.39
Qwen2.5-Coder-7B-Inst
Source Type=Open-Sourc...
2026.02
64.2
10.72
17.1
Qwen3-8B
Source Type=Open-Sourc...
2026.02
61.87
55.65
57.71
Qwen2.5-Coder-14B-Inst
Source Type=Open-Sourc...
2026.02
60.68
43.21
46.46
SecCoderX RM 8B
Source Type=Open-Sourc...
2026.02
59.37
81.2
67.9
GPT-4.1
Source Type=Closed-Source
2026.02
59.2
75.94
66.34
R2Vul 7B
Source Type=Open-Sourc...
2026.02
56.58
82.36
66.68
Gemini-2.5-Flash
Source Type=Closed-Source
2026.02
51.59
88.36
65.09
Feedback
Search any
task
Search any
task