We introduce AudioCapBench, a benchmark for evaluating audio captioning capabilities of large multimodal models. \method covers three distinct audio domains, including environmental sound, music, and speech, with 1,000 curated evaluation samples drawn from established datasets. We evaluate 13 models across two providers (OpenAI, Google Gemini) using both reference-based metrics (METEOR, BLEU, ROUGE-L) and an LLM-as-Judge framework that scores predictions on three orthogonal dimensions: \textit{accuracy} (semantic correctness), \textit{completeness} (coverage of reference content), and \textit{hallucination} (absence of fabricated content). Our results reveal that Gemini models generally outperform OpenAI models on overall captioning quality, with Gemini~3~Pro achieving the highest overall score (6.00/10), while OpenAI models exhibit lower hallucination rates. All models perform best on speech captioning and worst on music captioning. We release the benchmark as well as evaluation code to facilitate reproducible audio understanding research.
@article{arxiv.2602.23649,
title = {AudioCapBench: Quick Evaluation on Audio Captioning across Sound, Music, and Speech},
author = {Jielin Qiu and Jianguo Zhang and Zixiang Chen and Liangwei Yang and Ming Zhu and Juntao Tan and Haolin Chen and Wenting Zhao and Rithesh Murthy and Roshan Ram and Akshara Prabhakar and Shelby Heinecke and Caiming and Xiong and Silvio Savarese and Huan Wang},
journal= {arXiv preprint arXiv:2602.23649},
year = {2026}
}