arbiter
JournalsAccount

Creativity and AI

Gary Charness & Daniela Grieco

The Economic Journal2026https://doi.org/10.1093/ej/ueag015article
AJG 4ABDC A*
Weight
0.50

Abstract

We investigate whether AI systems outperform humans in creative tasks that vary in their degree of “openness.” To this end, we generated creative responses using three versions of ChatGPT and recruited 738 participants to blindly evaluate six creative answers randomly drawn from three pools—comprising 160 responses each—generated by both humans and AI. This process yielded 4,428 individual evaluations. Our results show that, regardless of the GPT version employed, human-generated responses achieve significantly and substantially higher average scores than machine-generated responses in open tasks. Conversely, AI-generated responses outperform human ones in closed tasks. Furthermore, we estimate that human imagination accounts for between 22% and 45% of the creative score in open tasks.

Open via your library →

Cite this paper

https://doi.org/https://doi.org/10.1093/ej/ueag015

Or copy a formatted citation

@article{gary2026,
  title        = {{Creativity and AI}},
  author       = {Gary Charness & Daniela Grieco},
  journal      = {The Economic Journal},
  year         = {2026},
  doi          = {https://doi.org/https://doi.org/10.1093/ej/ueag015},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

Creativity and AI

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.