# AI judges favor busier designs than people do in 400-pair test

> Original title: Same test on 400 pairs: judges picked the wordier site 66% of the time with real words, 64% with x's, and 56% with the text hidden, close...

- Source: Design Arena
- Published: 2026-11-01T19:31:52.000Z
- Bad Influence: https://badinfluence.news/items/uwnccpnqimqqyhppg42f98wqk
- Original: https://x.com/DesignArena/status/2116976537736302956

## Summary

Design Arena ran the same test on 400 site pairs and found AI judges picked the wordier site 66% of the time with real words, 64% with placeholder x's, and 56% with text hidden. Human raters chose the wordier site 54% of the time. The post concludes that grading design with an AI judge would push designs toward busier screens than people prefer.

## Post

Same test on 400 pairs: judges picked the wordier site 66% of the time with real words, 64% with x's, and 56% with the text hidden, close to people (54%). If you grade design with an AI judge, it'll push you toward busier screens than people want.

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2116974210639892480%2Fimg%2FFy3kMC-HIkceubIb.jpg&mode=thumb&exp=1793836800&sig=bd2f9f18f0f29789)