Table 1 Large language models participating in the test.
From: Arch-Eval benchmark for assessing chinese architectural domain knowledge in large language models
Creator | LLM | Parameter | Deployment Methods |
|---|---|---|---|
OpenAI | GPT-3.5-turbo | 175B | Online |
OpenAI | GPT-4-turbo | undisclosed | Online |
Baichuan | Baichuan-13B-Chat | 13B | Local |
Baichuan | Baichuan2-13B-Chat | 13B | Local |
Baichuan | Baichuan2-7B-Chat | 7B | Local |
Tsinghua & Zhipu AI | Chatglm2-6B | 6B | Local |
Tsinghua & Zhipu AI | Chatglm3-6B | 6B | Local |
Tsinghua & Zhipu AI | Chatglm3-6B-32k | 6B | Local |
Shanghai AI Laboratory | Internlm-Chat-7B | 7B | Local |
Meta | Llama2-Chinese-13B | 13B | Local |
Alibaba Cloud | Qwen1.5-14B-Chat | 14B | Local |
Alibaba Cloud | Qwen1.5-7B-Chat | 7B | Local |
Alibaba Cloud | Qwen-14B-Chat | 14B | Local |
Alibaba Cloud | Qwen-7B-Chat | 7B | Local |
