Vulnerability Prediction on CWE-Prediction
70.4AccuracyFoundation-Sec-8B-Reasoning
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Foundation-Sec-8B-ReasoningNumber of trials=52026.01 | 70.4 | 0.004 | |
| GPT-5Number of trials=52026.01 | 70.1 | 0.002 | |
| GPT-4.1Number of trials=52026.01 | 68.2 | 0.004 | |
| GPT-5-MiniNumber of trials=52026.01 | 66.6 | 0.001 | |
| GPT-OSS-120BNumber of trials=52026.01 | 66.1 | 0.002 | |
| O3-MiniNumber of trials=52026.01 | 63.2 | 0.001 | |
| Foundation-Sec-8B-InstructNumber of trials=52026.01 | 61.6 | 0.003 | |
| Llama-Primus-Nemotron-70B-InstructNumber of trials=52026.01 | 61.3 | 0.003 | |
| GPT-5-NanoNumber of trials=52026.01 | 61.2 | 0.003 | |
| Llama-3.3-70B-InstructNumber of trials=52026.01 | 60.7 | 0.003 | |
| Phi-4Number of trials=52026.01 | 55.4 | 0.004 | |
| Llama-Primus-MergedNumber of trials=52026.01 | 55 | 0.002 | |
| Qwen-3-14BNumber of trials=52026.01 | 53.4 | 0.005 | |
| GPT-OSS-20BNumber of trials=52026.01 | 51.9 | 0.006 | |
| Llama-3.1-8B-InstructNumber of trials=52026.01 | 47.3 | 0.003 | |
| Qwen-3-8BNumber of trials=52026.01 | 46.4 | 0.002 | |
| DeepHat-V1-7BNumber of trials=52026.01 | 36 | 0.003 |