Binary Accuracy on SecGenEval-PS CodeAnalysis
100AccuracyQwen2.5-Coder-7B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2.5-Coder-7BEvaluation Mode=M12026.01 | 100 | |
| Qwen2.5-Coder-7BEvaluation Mode=M32026.01 | 100 | |
| Qwen2.5-7BEvaluation Mode=M12026.01 | 100 | |
| Qwen2.5-Coder-7BEvaluation Mode=M22026.01 | 98.5 | |
| GPT-4oEvaluation Mode=M22026.01 | 95.8 | |
| GPT-4oEvaluation Mode=M32026.01 | 95.1 | |
| o3-miniEvaluation Mode=M22026.01 | 94.4 | |
| o3-miniEvaluation Mode=M32026.01 | 89.1 | |
| GPT-4oEvaluation Mode=M12026.01 | 87.2 | |
| DeepSeek-R1-Distill-Qwen-7BEvaluation Mode=M12026.01 | 57.1 | |
| o3-miniEvaluation Mode=M12026.01 | 41 |