DesignTaste: Benchmarking AI-Generator Visual Design Against Award-Wining Works
Text-to-image benchmarks commonly assess text-image alignment or overall preference. Whether models can produce good designs when a brief leaves the appearance open remains less well understood. We introduce DesignTaste, a visual design benchmark that compares generated images with award-winning works. From these works and their publicly available context, we derive 403 design briefs: 100 poster tasks from 100 Beste Plakate 2025 and 303 tasks spanning 20 categories from ADC 2026. Six leading commercial text-to-image models each generate an image from the same brief. A single model judge scores each output and the corresponding award-winning work independently on five evaluation dimensions. On each dataset, only ArtArk achieves a higher mean overall score than the award-winning works. All six models score lower in Creative Originality on both datasets. These results show that producing finished, visually appealing images does not imply that a model can develop good design solutions.
Authors
- 孝雅楠
- D. A. Pan (ORCID: https://orcid.org/0000-0003-2986-4614)
- Zhou Chen (ORCID: https://orcid.org/0000-0002-8250-0265)
- Kai Kong
- Jiaxiang Li
- Ye Li
- YuanYuan Ding
- TianRui Yang
- LiXin Sun
- Xinwen Xu
- Zhiqiang Li
- Min Zhou
- HuiTang Du
- JianYuan Li
- Anqi Liu
- Dong Zhao
- EnBao Zhang
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-11-12
- DOI
- https://doi.org/10.48550/arxiv.2611.16442
- Primary Topic
- Generative Adversarial Networks and Image Synthesis
- Type
- preprint