The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
The current state of artificial intelligence generative language models is more creative than humans on divergent thinking tasks
Open accessAbstract
The emergence of publicly accessible artificial intelligence (AI) large language models such as ChatGPT has given rise to global conversations on the implications of AI capabilities. Emergent research on AI has challenged the assumption that creative potential is a uniquely human trait thus, there seems to be a disconnect between human perception versus what AI is objectively capable of creating. Here, we aimed to assess the creative potential of humans in comparison to AI. In the present study, human participants (N = 151) and GPT-4 provided responses for the Alternative Uses Task, Consequences Task, and Divergent Associations Task. We found that AI was robustly more creative along each divergent thinking measurement in comparison to the human counterparts. Specifically, when controlling for fluency of responses, AI was more original and elaborate. The present findings suggest that the current state of AI language models demonstrate higher creative potential than human respondents.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
1 retracted
Kumar, Y., Koul, A., Singla, R., & Ijaz, M. F. (2023) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-021-03612-z · Cited by 1,040
RetractedThe associative basis of the creative process.
Mednick, S. (1962) · Psychological Review · doi:10.1037/h0048850 · Cited by 4,140
The standard definition of creativity
Runco, M. A., & Jaeger, G. J. (2012) · Creativity Research Journal · doi:10.1080/10400419.2012.650092 · Cited by 3,895
Natural language processing: state of the art, current trends and challenges
Khurana, D., Koli, A., Khatter, K., & Singh, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13428-4 · Cited by 1,823
Gao, C. A., Howard, F. M., Markov, N. S., Dyer, E. C., Ramesh, S., Luo, Y., & Pearson, A. T. (2022) · doi:10.1101/2022.12.23.521610 · Cited by 1,099 · cited 1×
“Indeed, AI has been found to generate novel connections in music 28 , science 26 , medicine 29 , and visual art 30 to name a few.”
BackgroundBoden, M. A. (2009) · AI Magazine · doi:10.1609/aimag.v30i3.2254 · Cited by 527
Best humans still outperform artificial intelligence in a creative divergent thinking task
Koivisto, M., & Grassini, S. (2023) · Scientific Reports · doi:10.1038/s41598-023-40858-3 · Cited by 247
Humans versus AI: whether and why we prefer human-created compared to AI-created artwork
Bellaiche, L., Shahi, R., Turpin, M. H., Ragnhildstveit, A., Sprockett, S., Barr, N., Christensen, A., & Seli, P. (2023) · Cognitive Research: Principles and Implications · doi:10.1186/s41235-023-00499-6 · Cited by 233
Artificial muses: Generative artificial intelligence chatbots have risen to human-level creativity
Haase, J., & Hanel, P. H. P. (2023) · Journal of Creativity · doi:10.1016/j.yjoc.2023.100066 · Cited by 233 · cited 4×
“Researchers have continued to demonstrate that the current state of LLM’s frequently score within the top 1% of human responses on standard divergent thinking tasks such as the Alternative Uses Task 32–34 .”
BackgroundInfluentialPutting the art in artificial: Aesthetic responses to computer-generated art.
Chamberlain, R., Mullin, C., Scheerlinck, B., & Wagemans, J. (2018) · Psychology of Aesthetics, Creativity, and the Arts · doi:10.1037/aca0000136 · Cited by 225 · cited 1×
“The expectancy that AI generated products or ideas are less creative or hold less aesthetic value than human-created artworks appear to depend on implicit anti-AI biases 22–24 , as AI has been found to be indistinguishable from human-created products 25–27 .”
Background
Research works printed but not linked: 36
- Rahaman, M. S., Ahsan, M. T., Anjum, N., Terano, H. J. R. & Rahman, M. M. From ChatGPT-3 to GPT-4: A significant advancement in ai-driven NLP tools. J. Eng. Emerg. Technol. 2(1), 1–11. https://doi.org/10.52631/jeet.v2i1.188 (2023). · DOI
- Lee, Y. H., & Lin, T. H. (2023). The feasibility study of AI image generator as shape convergent thinking tool. in International Conference on Human-Computer Interaction (pp. 575–589). https://doi.org/10.1007/978-3-031-35891-3_36. · doi:10.1007/978-3-031-35891-3_36
- Liu, H., Ning, R., Teng, Z., Liu, J., Zhou, Q., & Zhang, Y. (2023). Evaluating the logical reasoning ability of chatgpt and gpt-4. arXiv:2304.03439. · arXiv
- Cropley, A. In praise of convergent thinking. Creat. Res. J. 18(3), 391–404. https://doi.org/10.1207/s15326934crj1803_13 (2006). · DOI · Paper page
- Guilford, J. P. The Nature of Human Intelligence (McGraw-Hill, 1967).
- Runco, M. A. & Acar, S. Divergent thinking as an indicator of creative potential. Creat. Res. J. 24(1), 66–75. https://doi.org/10.1080/10400419.2012.652929 (2012). · DOI · Paper page
- Torrance, E. P. The Torrance Tests of Creative Thinking: Norms-Technical Manual (Personal Press, 1974).
- Wilson, R. C., Guilford, J. P., Christensen, P. R. & Lewis, D. J. A factor-analytic study of creative-thinking abilities. Psychometrika 19(4), 297–311. https://doi.org/10.1007/bf02289230 (1954). · DOI · Paper page
- Runco, M. A. AI can only produce artificial creativity. J. Creat. 33(3), 100063. https://doi.org/10.1016/j.yjoc.2023.100063 (2023). · DOI · Paper page
- Finke, R. A. Imagery, creativity, and emergent structure. Conscious. Cogn. 5(3), 381–393. https://doi.org/10.1006/ccog.1996.0024 (1996). · DOI · Paper page
- Sarker, I. H. Deep learning: A comprehensive overview on techniques, taxonomy, applications and research directions. SN Comput. Sci. 2(6), 420. https://doi.org/10.1007/s42979-021-00815-1 (2021). · DOI · Paper page
- Zhou, M., Duan, N., Liu, S. & Shum, H.-Y. Progress in neural NLP: Modeling, learning, and reasoning. Engineering 6(3), 275–290. https://doi.org/10.1016/j.eng.2019.12.014 (2020). · DOI · Paper page
- Cardoso, A., Veale, T. & Wiggins, G. A. Converging on the divergent: The history (and future) of the international joint workshops in computational creativity. AI Mag. 30(3), 15. https://doi.org/10.1609/aimag.v30i3.2252 (2009). · DOI
- Kane, S. et al. Attention, affect, and creativity, from mindfulness to mind-wandering. In The Cambridge Handbook of Creativity and Emotions (eds Ivcevic, Z. et al.) 130–148 (Cambridge University Press, 2023). https://doi.org/10.1017/9781009031240.010. · doi:10.1017/9781009031240.010
- Chatterjee, A. Art in an age of artificial intelligence. Front. Psychol. 13, 1024449. https://doi.org/10.3389/fpsyg.2022.1024449 (2022). · DOI
- Chiarella, S. et al. Investigating the negative bias towards artificial intelligence: Effects of prior assignment of AI-authorship on the aesthetic appreciation of abstract paintings. Comput. Hum. Behav. 137, 107406. https://doi.org/10.1016/j.chb.2022.107406 (2022). · DOI
- Fortuna, P. & Modliński, A. A(I)rtist or counterfeiter? Artificial intelligence as (D) evaluating factor on the art market. J. Arts Manag. Law Soc. 51(3), 188–201. https://doi.org/10.1080/10632921.2021.1887032 (2021). · DOI
- Samo, A. & Highhouse, S. Artificial intelligence and art: Identifying the aesthetic judgment factors that distinguish human- and machine-generated artwork. Psychol. Aesthet. Creat. Arts. https://doi.org/10.1037/aca0000570 (2023). · DOI
- Yin, Z., Reuben, F., Stepney, S. & Collins, T. Deep learning’s shallow gains: A comparative evaluation of algorithms for automatic music generation. Mach. Learn. 112(5), 1785–1822. https://doi.org/10.1007/s10994-023-06309-w (2023). · DOI
- Anantrasirichai, N. & Bull, D. Artificial intelligence in the creative industries: A review. Artif. Intell. Rev. https://doi.org/10.1007/s10462-021-10039-7 (2022). · DOI · Paper page
- Cropley, D. Is artificial intelligence more creative than humans?: ChatGPT and the divergent association task. Learn. Lett. 2, 13–13. https://doi.org/10.59453/ll.v2.13 (2023). · DOI
- Chen, L., Sun, L. & Han, J. A comparison study of human and machine-generated creativity. J. Comput. Inf. Sci. Eng. 23(5), 051012. https://doi.org/10.1115/1.4062232 (2023). · DOI
- Sawyer, R. K. Explaining Creativity: The Science of Human Innovation (Oxford University Press, 2012).
- Nusbaum, E. C., Silvia, P. J. & Beaty, R. E. Ready, set, create: What instructing people to “be creative” reveals about the meaning and mechanisms of divergent thinking. Psychol. Aesthet. Creat. Arts 8(4), 423. https://doi.org/10.1037/a0036549 (2014). · DOI · Paper page
- Acar, S. et al. Applying automated originality scoring to the verbal form of Torrance tests of creative thinking. Gift. Child Q. 67(1), 3–17. https://doi.org/10.1177/00169862211061874 (2021). · DOI
- Hass, R. W. & Beaty, R. E. Use or consequences: Probing the cognitive difference between two measures of divergent thinking. Front. Psychol. 9, 2327. https://doi.org/10.3389/fpsyg.2018.02327 (2018). · DOI
- Urban, M. & Urban, K. Orientation toward intrinsic motivation mediates the relationship between metacognition and creativity. J. Creat. Behav. 57(1), 6–16. https://doi.org/10.1002/jocb.558 (2023). · DOI
- Day, B. et al. Ordering effects and choice set awareness in repeat-response stated preference studies. J. Environ. Econ. Manag. 63(1), 73–91. https://doi.org/10.1016/j.jeem.2011.09.001 (2012). · DOI · Paper page
- Igorov, M., Predoiu, R., Predoiu, A. & Igorov, A. Creativity, resistance to mental fatigue and coping strategies in junior women handball players. Eur. Proc. Soc. Behav. Sci. https://doi.org/10.15405/epsbs.2016.06.39 (2016). · doi:10.15405/epsbs.2016.06.39
- Beaty, R. E., Johnson, D. R., Zeitlen, D. C. & Forthmann, B. Semantic distance and the alternate uses task: Recommendations for reliable automated assessment of originality. Creat. Res. J. 34(3), 245–260. https://doi.org/10.1080/10400419.2022.2025720 (2022). · DOI
- Pennington, J., Socher, R. & Manning, C. Glove: Global vectors for word representation. in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 1532–1543 (2014). · DOI · Paper page
- Vinchon, F., Gironnay, V., & Lubart, T. The Creative AI-Land: Exploring new forms of creativity. In Review. (2023). · doi:10.21203/rs.3.rs-3226749/v1
- Beaty, R. E. & Silvia, P. J. Why do ideas get more creative across time? An executive interpretation of the serial order effect in divergent thinking tasks. Psychol. Aesthet. Creat. Arts 6(4), 309–319. https://doi.org/10.1037/a0029171 (2012). · DOI · Paper page
- Carson, S. H., Peterson, J. B. & Higgins, D. M. Reliability, validity, and factor structure of the creative achievement questionnaire. Creat. Res. J. 17(1), 37–50. https://doi.org/10.1207/s15326934crj1701_4 (2005). · DOI · Paper page
- Jauk, E., Benedek, M. & Neubauer, A. C. The road to creative achievement: A latent variable model of ability and personality predictors. Pers. Individ. Diff. https://doi.org/10.1016/j.paid.2013.07.129 (2014). · DOI
- Chevalier, A., Dommes, A. & Marquié, J.-C. Strategy and accuracy during information search on the web: Effects of age and complexity of the search questions. Comput. Hum. Behav. 53, 305–315. https://doi.org/10.1016/j.chb.2015.07.017 (2015). · DOI
Cited by
An empirical investigation of the impact of ChatGPT on creativity
Lee, B. C., & Chung, J. (2024) · Nature Human Behaviour · doi:10.1038/s41562-024-01953-1 · Cited by 179
AI and Its Impact on Creativity and Diversity: An Empirical Study of LLM-Generated Product Ideas
Terwiesch, C., Meincke, L., Girotra, K., Mollick, E. R., Nave, G., & Ulrich, K. T. (2023) · doi:10.2139/ssrn.4526071 · Cited by 174
Conceptualizing generative AI as style engines: Application archetypes and implications
Riemer, K., & Peter, S. (2024) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2024.102824 · Cited by 63
Xie, Y., & Wang, S. (2025) · Scientific Reports · doi:10.1038/s41598-025-09545-3 · Cited by 56
Human Creativity in the Age of LLMs: Randomized Experiments on Divergent and Convergent Thinking
Kumar, H., Vincentius, J., Jordan, E., & Anderson, A. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714198 · Cited by 129
“However, they still fall short when compared to the best human performers, particularly experts [31, 33].”
Metadata
- Authors
- Hubert, K. F., Awa, K. N., & Zabelina, D. L.
- Venue
- Scientific Reports
- Published
- 2024-02-10
- Volume
- 14
- Issue
- 1
- Pages
- 3440-3440
- ISSN
- 2045-2322 (ISSN-L)
- OpenAlex
- W4391713912
- Cited by
- 221
- References
- 16
- FWCI
- 88.54
- Type
- journal article
- Language
- en
- Open access
- gold
- Licence
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: The current state of artificial intelligence generative language models is more creative than humans on divergent thinking tasks. https://app.cochat.ai/papers/10.1038/s41598-024-53303-w
- The paper
- Hubert, K. F., Awa, K. N., & Zabelina, D. L. (2024). The current state of artificial intelligence generative language models is more creative than humans on divergent thinking tasks. Scientific Reports. https://doi.org/10.1038/s41598-024-53303-w
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.