Image captioning has been a longstanding challenge in vision-language research. With the rise of LLMs, modern Vision-Language Models (VLMs) generate detailed and comprehensive image descriptions. However, benchmarking the quality of such captions remains unresolved. This paper addresses two key questions: (1) How well do current VLMs actually perform on image captioning, particularly compared to humans? We built CapArena, a platform with over 6000 pairwise caption battles and high-quality human preference votes. Our arena-style evaluation marks a milestone, showing that leading models like GPT-4o achieve or even surpass human performance, while most open-source models lag behind. (2) Can automated metrics reliably assess detailed caption quality? Using human annotations from CapArena, we evaluate traditional and recent captioning metrics, as well as VLM-as-a-Judge. Our analysis reveals that while some metrics (e.g., METEOR) show decent caption-level agreement with humans, their systematic biases lead to inconsistencies in model ranking. In contrast, VLM-as-a-Judge demonstrates robust discernment at both the caption and model levels. Building on these insights, we release CapArena-Auto, an accurate and efficient automated benchmark for detailed captioning, achieving 94.3% correlation with human rankings at just
View on arXiv@article{cheng2025_2503.12329,
title={ CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era },
author={ Kanzhi Cheng and Wenpo Song and Jiaxin Fan and Zheng Ma and Qiushi Sun and Fangzhi Xu and Chenyang Yan and Nuo Chen and Jianbing Zhang and Jiajun Chen },
journal={arXiv preprint arXiv:2503.12329},
year={ 2025 }
}