iFlytek’s LLM dominates domestic chatbot competition, top study finds

iFlytek's xinghuo renzhi scored the highest among peers on metrics like IQ and efficiency, with the study's authors crediting this model for "obvious advantages in bolstering work efficiency."

China’s AI titan iFlytek (科大讯飞) is leading the nation’s large language model (LLM) race as its ChatGPT-like chatbot service came at the top of a high-profile recent survey.

The study, published on August 12 by the China Enterprise Development Research Center, a think tank affiliated to state-run Xinhua Institute, found that iFlytek’s xinghuo renzhi, came in first, followed by Baidu’s Ernie Bot, SenseTime’s SenseChat and ChatGLM from Zhipu AI, an AI startup.

The study assesses and grades mainstream LLMs developed by Chinese companies on four dimensions, including basic capability, IQ, EQ and efficiency, based on their value in daily life and industrial application.

iFlytek’s xinghuo renzhi scored the highest among peers on metrics like IQ and efficiency, with the study’s authors crediting this model for “obvious advantages in bolstering work efficiency.”

As a comparison, Baidu’s Ernie Bot ranked first in basic capability while SenseChat was a top scorer on EQ. ChatGLM achieved overall outstanding performance.

iFlytek’s xinghuo renzhi possesses cross-disciplinary knowledge and linguistic ability. It can understand and implement commands based on natural language communication.

The model came out first in May and received several updates to the latest version V1.5. A further upgrade is scheduled for tomorrow.

According to iFlytek, the model has seven core abilities, ranging from textual creation and language comprehension to knowledge Q&A and math capability, from coding and programming to multi-modal capacity.

Despite significant inroads by China’s LLMs, the survey points out that humans still “apparently” outwit AI in IQ.

According to its authors, AI does help bolster work efficiency since it processes information way faster than mankind, but in the face of some complicated and creative tasks, AI still cannot compare with human wisdom or imagination, let alone replace it.

The survey concludes that Chinese LLMs have come a long way since June 2023. Nonetheless, they still lag behind humans in IQ, EQ and other major aspects, it says.

Avatar photo
Ni Tao

Ni Tao is the founder and editor-in-chief of cnrobopedia. Prior to cnrobopedia, he had a full decade of experience with a major state-run English-language newspaper as a tech reporter and opinion writer. He is also a communications specialist, having provided consultancy services to established firms like Siemens, Philips, ABinBev, Diageo, Trip.com Group (Nasdaq: TCOM, HK: 9961), Jianpu Technology (NYSE: JT) and a handful of domestic startups. A graduate of Fudan University, he writes widely about China's business and tech scenes and other topics for global publications including South China Morning Post, SupChina, The Diplomat, CGTN, Banking Technology, among others, and tries to impart his experience to students at Fudan University Journalism School, where he is a part-time lecturer. When he's not writing about robotics, you can expect him to be on his beloved Yanagisawa saxophones, trying to play some jazz riffs, often in vain and occasionally against the protests of an angry neighbor. Get in touch with him by dropping a line at nitao0927@gmail.com.

Articles: 662