Generative artificial intelligence models outperform students on divergent and convergent thinking assessments
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".