According to 36 Krypton’s report on June 29, recently, the China Industrial Internet Research Institute conducted a systematic evaluation of the knowledge question-answering ability of large artificial intelligence models in the Chinese industrial field. The evaluation objects cover large models at home and abroad such as GPT4, GPT3.5, Wenxin Yiyan, and ChatGLM. The results showed that GPT4 performed best. The performance of the large head model in China is outstanding, which is comparable to GPT3.5 as a whole, and the performance of Baidu Wenxin Yiyan exceeds GPT3.5.
View Original
The content is for reference only, not a solicitation or offer. No investment, tax, or legal advice provided. See Disclaimer for more risks disclosure.
According to 36 Krypton’s report on June 29, recently, the China Industrial Internet Research Institute conducted a systematic evaluation of the knowledge question-answering ability of large artificial intelligence models in the Chinese industrial field. The evaluation objects cover large models at home and abroad such as GPT4, GPT3.5, Wenxin Yiyan, and ChatGLM. The results showed that GPT4 performed best. The performance of the large head model in China is outstanding, which is comparable to GPT3.5 as a whole, and the performance of Baidu Wenxin Yiyan exceeds GPT3.5.