Generative artificial intelligence models outperform students on divergent and convergent thinking assessments

Generative artificial intelligence (GenAI) has garnered significant attention for its remarkable capabilities and is now widely used in many creative domains, sparking scientific interest in its creative capacities. While previous studies have assessed GenAI on creativity tasks, there is no evidence comparing the latest GenAI models to the same sample of humans on both divergent and convergent thinking assessments. In this study, we compared the creative ability of human participants (n = 46) against three state-of-the-art GenAI chatbots—ChatGPT-4o, DeepSeek-V3, and Gemini 2.0—using the Alternate Uses Task (AUT) and the Remote Associates Test (RAT). For divergent thinking, we compared the median and maximum originality scores on the AUT, representing the level of originality of the ‘average’ and ‘best’ idea. We then compared performance on 57 RAT items as a measure of convergent thinking. All GenAI models outperformed human participants in both tasks: the ‘average’ and ‘best’ GenAI ideas were significantly more original than human-generated ideas. All GenAI models demonstrated superior RAT performance vs. humans. Among GenAI models, ChatGPT-4o consistently demonstrated the best scores on both tasks. These findings illustrate the immense creative potential of GenAI, but call into question the appropriateness of current creativity assessment methods in the study of GenAI creativity.