Vulnerability Severity Prediction on CTIBench-VSP
0.045Average CVSSDeepHat-V1-7B
Evaluation results
| Method | Links | |
|---|---|---|
| DeepHat-V1-7BModel Group=smaller specialized models, Number of Parameters=7B, Trials=52026.01 | 0.045 | |
| Llama-Primus-Nemotron-70B-InstructModel Group=Llama-family and cybersecurity-specialized, Number of Parameters=70B, Trials=52026.01 | 0.239 | |
| Phi-4Model Group=smaller specialized models, Trials=52026.01 | 0.647 | |
| Llama-Primus-MergedModel Group=Llama-family and cybersecurity-specialized, Trials=52026.01 | 0.788 | |
| Llama-3.1-8B-InstructModel Group=Llama-family and cybersecurity-specialized, Number of Parameters=8B, Trials=52026.01 | 0.811 | |
| GPT-5-NanoModel Group=frontier OpenAI API models, Trials=52026.01 | 0.822 | |
| Foundation-Sec-8B-InstructModel Group=Llama-family and cybersecurity-specialized, Number of Parameters=8B, Trials=52026.01 | 0.84 | |
| Llama-3.3-70B-InstructModel Group=Llama-family and cybersecurity-specialized, Number of Parameters=70B, Trials=52026.01 | 0.841 | |
| o3-MiniModel Group=frontier OpenAI API models, Trials=52026.01 | 0.843 | |
| GPT-4.1Model Group=frontier OpenAI API models, Trials=52026.01 | 0.848 | |
| Foundation-Sec-8B-ReasoningModel Group=our reasoning model, Number of Parameters=8B, Trials=52026.01 | 0.856 | |
| Qwen-3-8BModel Group=smaller specialized models, Number of Parameters=8B, Trials=52026.01 | 0.863 | |
| GPT-OSS-20BModel Group=GPT-OSS models, Number of Parameters=20B, Trials=52026.01 | 0.864 | |
| Qwen-3-14BModel Group=smaller specialized models, Number of Parameters=14B, Trials=52026.01 | 0.869 | |
| GPT-OSS-120BModel Group=GPT-OSS models, Number of Parameters=120B, Trials=52026.01 | 0.883 | |
| GPT-5-MiniModel Group=frontier OpenAI API models, Trials=52026.01 | 0.892 | |
| GPT-5Model Group=frontier OpenAI API models, Trials=52026.01 | 0.903 |