notesum.ai
Published at November 25CS-Eval: A Comprehensive Large Language Model Benchmark for CyberSecurity
cs.CR
Released Date: November 25, 2024
Authors: Zhengmin Yu1, Jiutian Zeng2, Siyi Chen2, Wenhan Xu2, Dandan Xu2, Xiangyu Liu2, Zonghao Ying2, Nan Wang1, Yuan Zhang1, Min Yang1
Aff.: 1Fudan University; 2Alibaba Group

| Model | Creator | #Parameters | Access |
|---|---|---|---|
| GPT4o | OpenAI | unpublic | API |
| GPT4-8K | OpenAI | unpublic | API |
| GPT3.5-Turbo-16K | OpenAI | unpublic | API |
| DeepSeek-V2-0628 | DeepSeek | 236B | API |
| Qwen-14B-Chat | Alibaba Cloud | 14B | Weights |
| Qwen1.5-14B-Chat | Alibaba Cloud | 14B | Weights |
| Qwen1.5-MoE-A2.7B-Chat | Alibaba Cloud | 14.3B | Weights |
| Qwen2-7B-Instruct | Alibaba Cloud | 7B | Weights |
| Qwen2-72B-Instruct | Alibaba Cloud | 72B | Weights |
| Baichuan-13B-Chat | BaiChuan-Inc | 13B | Weights |
| Baichuan2-13B-Chat | BaiChuan-Inc | 13B | Weights |
| 360Zhizhao-7B-Chat-4K | 360 | 7B | Weights |
| Mistral-7B-Instruct-v0.2 | Mistral AI | 7.3B | Weights |
| Yi-6B-Chat | 01.AI | 6B | Weights |
| ChatGLM3-6B | Zhipu AI | 6B | Weights |
| ChatGLM4 | Zhipu AI | 9B | API |
| SecGPT-13B | Clouditera | 13B | Weights |
| Llama-2-13b-chat-hf | Meta | 13B | Weights |
| Llama-3.1-8B-Instruct | Meta | 8B | Weights |
| Llama-3.1-70B-Instruct | Meta | 70B | Weights |