VLAgeBench (UTKFace): leaderboard
Metric: Mean absolute error in years between the predicted and labelled age on UTKFace face images (ages 0 to 116), zero-shot, a standardized prompt asking for a numeric age only; lower is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o (2024-08-06) | 4.93 | #326 |
| 2 | Claude 3.5 Sonnet (20241022) | 5.28 | #286 |
| 3 | Llama 3.2 11B Instruct | 7.58 | #1112 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=vlagebench-utkface · How It Works · Data refreshed daily, snapshot 2026-10-11.