ChatGPT better than undergraduates at solving SAT problems, study suggests

Researchers at UCLA found GPT-3 solved 80% of reasoning problems correctly compared with 60% of humans

ChatGPT can solve problems at a level that matches or surpasses an undergraduate student, according to a new study.

Researchers found that the GPT-3 large language model that underpins the chatbot performed about as well as US college undergraduates when asked to solve reasoning problems that appear on intelligence tests or exams such as the American college admission test, the SAT.

artificial intelligence (ai) chatbot chatgpt computing found gpt gpt-3 language language model large language large language model reasoning research researchers study technology ucla undergraduate