# VLAgeBench: Benchmarking Large Vision-Language Models for Zero-Shot Human Age Estimation

arXiv: https://arxiv.org/abs/2603.26015 · HTML: https://mlsanity.com/paper/2603.26015/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social bias and fairness in VLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 16 of its 28 references that are in the map.
- First posted on arXiv 27 Mar 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Social bias and fairness in VLMs](https://mlsanity.com/mllm/social-bias-and-fairness-in-vlms/)

## Builds on (most cited first, 16 of 16)

- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [An Introduction to Vision-Language Modeling](https://mlsanity.com/paper/2405.17247/) (2024)
- [VLP: A Survey on Vision-Language Pre-training](https://mlsanity.com/paper/2202.09061/) (2022)
- [Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions](https://mlsanity.com/paper/2209.03430/) (2022)
- [FairCLIP: Harnessing Fairness in Vision-Language Learning](https://mlsanity.com/paper/2403.19949/) (2024)
- [Distribution-Aware Prompt Tuning for Vision-Language Models](https://mlsanity.com/paper/2309.03406/) (2023)
- [Teach CLIP to Develop a Number Sense for Ordinal Regression](https://mlsanity.com/paper/2408.03574/) (2024)
- [Robust Subjective Visual Property Prediction from Crowdsourced Pairwise Labels](https://mlsanity.com/paper/1501.06202/) (2015)
- [Zero-shot Building Age Classification from Facade Image Using GPT-4](https://mlsanity.com/paper/2404.09921/) (2024)
- [A Deep Learning Framework to Reconstruct Face under Mask](https://mlsanity.com/paper/2203.12482/) (2022)
- [Modeling of Facial Aging and Kinship: A Survey](https://mlsanity.com/paper/1802.04636/) (2018)
- [Exploring Vision Language Models for Facial Attribute Recognition: Emotion, Race, Gender, and Age](https://mlsanity.com/paper/2410.24148/) (2024)
- [Prompt Tuning Vision Language Models with Margin Regularizer for Few-Shot Learning under Distribution Shifts](https://mlsanity.com/paper/2505.15506/) (2025)
- [Generalizable Prompt Tuning for Vision-Language Models](https://mlsanity.com/paper/2410.03189/) (2024)

## Abstract (arXiv)

Human age estimation from facial images represents a challenging computer vision task with significant applications in biometrics, healthcare, and human-computer interaction. While traditional deep learning approaches require extensive labeled datasets and domain-specific training, recent advances in large vision-language models (LVLMs) offer the potential for zero-shot age estimation. This study presents a comprehensive zero-shot evaluation of state-of-the-art Large Vision-Language Models (LVLMs) for facial age estimation, a task traditionally dominated by domain-specific convolutional networks and supervised learning. We assess the performance of GPT-4o, Claude 3.5 Sonnet, and LLaMA 3.2 Vision on two benchmark datasets, UTKFace and FG-NET, without any fine-tuning or task-specific adaptation. Using eight evaluation metrics, including MAE, MSE, RMSE, MAPE, MBE, R2, CCC, and ±5-year accuracy, we demonstrate that general-purpose LVLMs can deliver competitive performance in zero-shot settings. Our findings highlight the emergent capabilities of LVLMs for accurate biometric age estimation and position these models as promising tools for real-world applications. Additionally, we highlight performance disparities linked to image quality and demographic subgroups, underscoring the need for fairness-aware multimodal inference. This work introduces a reproducible benchmark and positions LVLMs as promising tools for real-world applications in forensic science, healthcare monitoring, and human-computer interaction. The benchmark focuses on strict zero-shot inference without fine-tuning and highlights remaining challenges related to prompt sensitivity, interpretability, computational cost, and demographic fairness.