Why do LLM pelicans look like this?
Design Creativity Bench finds frontier models lag human designers, with GPT-6 Astra scoring 65.5 versus 92.3.
Researchers introduced Design Creativity Bench to measure UI design creativity across originality, creative range, and appropriateness. They evaluated 16 frontier models on 80 open-ended tasks, each adapted to two product domains, alongside human designer references. The top model, OpenAI GPT-6 Astra, scored 65.5 compared with a human reference of 92.3. A leaderboard, paper, Hugging Face dataset, and evaluation code were released.
- The benchmark tests 16 frontier models on 80 open-ended UI tasks.
- Scores cover originality, creative range, and functional appropriateness.
- GPT-6 Astra leads models at 65.5, below the human reference of 92.3.
- Vendors
- OpenAI
- AI models
- GPT-6 Astra
From the original article
1 min read at arcfu.com
⚠️ Frontier AI models still fall significantly short of human designers on design creativity. ⚠️ Introducing Design Creativity Bench, a new benchmark evaluating AI models’ creativity on UI design tasks. Despite rapid advances in their ability to generate functional websites and product UIs, leading AI models still struggle to make creative design decisions.
By pcwelder · arcfu.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.