The Chinese search engine has been publicly testing the Ernie Bot in China since it was revealed in March. The chatbot is based on Baidu’s foundational AI model called Ernie. A foundational model is AI that’s trained on vast amounts of data. The latest iteration of Baidu’s model is called Ernie 3.5.

According to the China Science Daily journal, Baidu said Ernie 3.5 surpassed ChatGPT in several benchmark tests. ChatGPT is based on OpenAI’s GPT 3.5 model.

Ernie 3.5 also beat GPT 4, OpenAI’s latest and more advanced model, in Chinese language tests, according to the science journal.

The focus on Baidu’s advancements underscores the intense competition in generative AI with technology giants in the U.S. and China rapidly advancing developments.

One test cited by the Chinese science journal was based on standard admission and qualification exams such as those required to get into college or qualify as a lawyer. Ernie 3.5 surpassed ChatGPT and GPT 4 in Chinese.

However, it was behind GPT 4 in English even though it was ahead of ChatGPT. Microsoft released this test

Another test focused on Chinese and contains over 13,000 multiple-choice questions covering more than 50 different subjects. Ernie 3.5 was ahead of ChatGPT and GPT 4 in this evaluation.

A third test contains questions on various subjects such as science and humanities and was developed by a group of U.S. universities. Ernie 3.5 was behind both ChatGPT and GPT 4.