Artificial intelligence models, including Alibaba's Tongyi Qianwen and OpenAI's GPT-4o, were tested on this year's Chinese national college entrance examination, known as the gaokao. Despite performing well in Chinese literature and English language, the AI models struggled significantly in mathematics. The highest score achieved by any model was 303 out of a total 420 points, with all models failing the math section. The Shanghai AI Laboratory tested seven models in total. Additionally, during the preliminary round of the 2024 Alibaba Global Mathematics Competition, 563 teams using AI failed to advance to the finals due to low scores.
Artificial intelligence has performed strongly on the subjects of Chinese literature and English language, but it scored poorly in mathematics, according to a study that used different chatbot tools to generate answers to this year's national college entrance exams, or #gaokao.… https://t.co/hZRehBWUjP
Chat GPT-4o, Six Other #AI Models Fail China’s College Entrance Maths Exam @AlibabaGroup @OpenAI https://t.co/CMO6slQIgo
The Shanghai AI Laboratory yesterday said it tested seven #AI models on this year's Chinese national college entrance examination, with #Alibaba's Tongyi Qianwen logging the best performance with 303 points, followed by OpenAI's GPT-4o. All the models failed the #math test, as… https://t.co/abdYoDXiQQ
The #gaokao is widely acknowledged as one of the most challenging college entrance exams globally. When #AI models were used to answer the exam questions, the highest scores only reached 303 out of the total score of 420, and all of them failed in the math section.… https://t.co/ZiAM01ZyVJ
During the preliminary round of the 2024 Alibaba Global Mathematics Competition, 563 teams used AI to answer questions. Much to the surprise of #AI advocates, none of the teams scored high enough to advance to the finals. https://t.co/dwgmge0Bbz https://t.co/LFn9L08Glq
Chinese language AI chatbots wish to be your emotional help As I reported final week, Baidu gre... https://t.co/2zHdY9ntIC