PulseAugur
EN
LIVE 08:24:19

AI models consistently overrate facial attractiveness, study finds

By PulseAugur Editorial · [1 sources] ·

A new study published on arXiv reveals that multimodal large language models (MLLMs) systematically overrate facial attractiveness compared to human judgments. Researchers compared ratings from 2,513 human participants with those from four commercial AI models: Claude, Gemini, GPT, and Grok. While the AI models showed strong correlations with human rank-ordering of attractiveness, they consistently rated faces more favorably and within a narrower range than humans. Only face age was a consistent predictor of attractiveness across both humans and MLLMs, with other factors like ethnicity and gender showing inconsistent patterns among the models. Grok, in particular, exhibited the lowest agreement with human ratings. AI

IMPACT Suggests current MLLMs may not be reliable for subjective tasks like beauty assessment, highlighting differences in AI and human perception.

RANK_REASON Research paper published on arXiv detailing findings about AI model capabilities. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

AI models consistently overrate facial attractiveness, study finds

How we ranked this

Signal score
17 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Research paper published on arXiv detailing findings about AI model capabilities. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.CV TIER_1 English(EN) · Santiago Grandas, Juan Sebastian Cely-Acosta, Mohit Mendiratta, Shafee Hassan, Macken Murphy ·

    Beauty is in the AI of the beholder: MLLMs systematically overrate facial attractiveness

    arXiv:2609.02512v1 Announce Type: new Abstract: Beauty assessments from Multimodal Large Language Models (MLLMs) are increasingly popular amongst users, companies, and aestheticians. This raises the question of whether these AI models can accurately reflect human judgments of att…

RELATED ENTITIES

RELATED TOPICS