Kombai's Design Creativity Bench ranks frontier AI models below human designers on UI
Overview
Kombai releases Design Creativity Bench, which scores 16 frontier models on 80 open-ended UI design tasks across two product domains.
The benchmark rates originality, creative range, and appropriateness. Kombai reports that the top model, OpenAI's GPT-6 Astra, scores 65.5, against a human designer reference of 92.3.
The leaderboard, methodology, and evaluation framework are published on the project's website, arXiv, Hugging Face, and GitHub. Dipanjan Dey introduced the benchmark.
Written by AI from the articles below · updated Oct 14, 7:45 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- Hacker News · AI (150+ points)BlogDesign Creativity Bench finds frontier AI models trail human designers on UI creativity
AIKombai introduces Design Creativity Bench, which evaluates 16 frontier models on 80 open-ended UI design tasks across two product domains. It scores originality, creative range, and appropriateness, and reports that the best model, GPT-6 Astra, reaches 65.5 against a human reference of 92.3. The leaderboard, methodology, and evaluation framework are published on the project's website, arXiv, Hugging Face, and GitHub.
Heat trend
Not enough continuous observations to show a trend yet.