Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Security Evaluation on DiverseVul C/C++
Loading...
142
VULNS Count
Self-Play
36.96
64.23
91.5
118.77
Jun 2, 2026
VULNS Count
Updated 1mo ago
Evaluation Results
Method
Method
Links
VULNS Count
Self-Play
Base Model=Qwen2.5-Cod...
2026.06
142
SFT
Base Model=Qwen2.5-Cod...
2026.06
140
Self-Play
Base Model=Qwen2.5-Cod...
2026.06
130
Base LLM
Base Model=CodeLlama-7B
2026.06
115
SFT
Base Model=CodeLlama-7B
2026.06
110
SFT
Base Model=Qwen2.5-Cod...
2026.06
107
Base LLM
Base Model=Qwen2.5-Cod...
2026.06
106
Self-Play
Base Model=CodeLlama-7B
2026.06
103
TSP (OURS)
Base Model=CodeLlama-7B
2026.06
94
Base LLM
Base Model=Qwen2.5-Cod...
2026.06
93
TSP (OURS)
Base Model=Qwen2.5-Cod...
2026.06
57
TSP (OURS)
Base Model=Qwen2.5-Cod...
2026.06
41
Feedback
Search any
task
Search any
task