Can generative synthetic intelligence techniques like ChatGPT genuinely create authentic concepts? A brand new examine led by Professor Karim Jerbi from the Division of Psychology on the Université de Montréal, with participation from famend AI researcher Yoshua Bengio, takes on that query at an unprecedented scale. The analysis is the biggest direct comparability ever carried out between human creativity and the creativity of huge language fashions.
The examine, printed in Scientific Reviews (Nature Portfolio), factors to a major shift. Generative AI techniques have now reached a degree the place they will outperform the typical human on sure creativity measures. On the identical time, probably the most inventive folks nonetheless present a transparent and constant benefit over even the strongest AI fashions.
AI Reaches Common Human Creativity Ranges
Researchers evaluated a number of main massive language fashions, together with ChatGPT, Claude, Gemini, and others, and in contrast their efficiency with outcomes from greater than 100,000 human contributors. The findings spotlight a transparent turning level. Some AI techniques, together with GPT-4, exceeded common human scores on duties designed to measure divergent linguistic creativity.
“Our examine reveals that some AI techniques based mostly on massive language fashions can now outperform common human creativity on well-defined duties,” explains Professor Karim Jerbi. “This consequence could also be shocking — even unsettling — however our examine additionally highlights an equally vital statement: even one of the best AI techniques nonetheless fall wanting the degrees reached by probably the most inventive people.”
Additional evaluation by the examine’s co-first authors, postdoctoral researcher Antoine Bellemare-Pépin (Université de Montréal) and PhD candidate François Lespinasse (Université Concordia), revealed a putting sample. Whereas some AI fashions now outperform the typical individual, peak creativity stays firmly human.
In actual fact, when researchers examined probably the most inventive half of contributors, their common scores surpassed these of each AI mannequin examined. The hole grew even bigger among the many prime 10 p.c of probably the most inventive people.
“We developed a rigorous framework that permits us to match human and AI creativity utilizing the identical instruments, based mostly on information from greater than 100,000 contributors, in collaboration with Jay Olson from the College of Toronto,” says Professor Karim Jerbi, who can be an affiliate professor at Mila.
How Scientists Measure Creativity in People and AI
To guage creativity pretty throughout people and machines, the analysis staff used a number of strategies. The first device was the Divergent Affiliation Job (DAT), a extensively used psychological check that measures divergent creativity, or the flexibility to generate various and authentic concepts from a single immediate.
Created by examine co-author Jay Olson, the DAT asks contributors, whether or not human or AI, to checklist ten phrases which can be as unrelated in which means as attainable. An instance of a extremely inventive response contains phrases like “galaxy, fork, freedom, algae, harmonica, quantum, nostalgia, velvet, hurricane, photosynthesis.”
Efficiency on this job is strongly linked to outcomes on different established creativity assessments utilized in writing, thought era, and artistic drawback fixing. Though the duty is language-based, it goes properly past vocabulary. It engages broader cognitive processes concerned in inventive pondering throughout many domains. The DAT additionally has sensible benefits, because it takes solely two to 4 minutes to finish and will be accessed on-line by most people.
From Phrase Lists to Actual Inventive Writing
The researchers then explored whether or not AI success on this straightforward phrase affiliation job may prolong to extra advanced and reasonable inventive actions. To check this, they in contrast AI techniques and human contributors on inventive writing challenges corresponding to composing haiku (a brief three-line poetic type), writing film plot summaries, and producing brief tales.
The outcomes adopted a well-recognized sample. Whereas AI techniques typically exceeded the efficiency of common people, probably the most expert human creators persistently delivered stronger and extra authentic work.
Can AI Creativity Be Adjusted?
These findings raised one other vital query. Is AI creativity fastened, or can it’s formed? The examine reveals that creativity in AI will be adjusted by altering technical settings, notably the mannequin’s temperature. This parameter controls how predictable or adventurous the generated responses are.
At decrease temperature settings, AI produces safer and extra standard outputs. At increased temperatures, responses turn out to be extra various, much less predictable, and extra exploratory, permitting the system to maneuver past acquainted concepts.
The researchers additionally discovered that creativity is strongly influenced by how directions are written. For instance, prompts that encourage fashions to consider phrase origins and construction utilizing etymology result in extra surprising associations and better creativity scores. These outcomes emphasize that AI creativity relies upon closely on human steering, making interplay and prompting a central a part of the inventive course of.
Will AI Substitute Human Creators?
The examine gives a balanced perspective on fears that synthetic intelligence may exchange inventive professionals. Whereas AI techniques can now match or exceed common human creativity on sure duties, they nonetheless have clear limitations and depend on human path.
“Regardless that AI can now attain human-level creativity on sure assessments, we have to transfer past this deceptive sense of competitors,” says Professor Karim Jerbi. “Generative AI has above all turn out to be a particularly highly effective device within the service of human creativity: it won’t exchange creators, however profoundly rework how they think about, discover, and create — for individuals who select to make use of it.”
Relatively than signaling the tip of inventive careers, the findings recommend a future the place AI serves as a inventive assistant. By increasing concepts and opening new paths for exploration, AI could assist amplify human creativeness slightly than exchange it.
“By immediately confronting human and machine capabilities, research like ours push us to rethink what we imply by creativity,” concludes Professor Karim Jerbi.
Concerning the Research
The paper titled “Divergent creativity in people and huge language fashions” was printed in Scientific Reviews on January 21, 2026. The analysis introduced collectively scientists from Université de Montréal, Université Concordia, College of Toronto Mississauga, Mila (Quebec AI Institute), and Google DeepMind.
Professor Karim Jerbi led the examine, with Antoine Bellemare-Pépin (Université de Montréal) and François Lespinasse (Université Concordia) serving as co-first authors. The analysis staff additionally included Yoshua Bengio, founding father of Mila and LoiZéro, and a pioneer of deep studying, the know-how behind trendy AI techniques corresponding to ChatGPT.