@inproceedings{he-etal-2025-flagevalmm,
    title = "{F}lag{E}val{MM}: A Flexible Framework for Comprehensive Multimodal Model Evaluation",
    author = "He, Zheqi  and
      Liu, Yesheng  and
      Zheng, Jing-Shu  and
      Li, Xuejing  and
      Yao, Jin-Ge  and
      Qin, Bowen  and
      Xuan, Richeng  and
      Yang, Xi",
    editor = "Mishra, Pushkar  and
      Muresan, Smaranda  and
      Yu, Tao",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-demo.6/",
    pages = "51--61",
    ISBN = "979-8-89176-253-4",
    abstract = "We present FlagEvalMM, an open-source evaluation framework designed to comprehensively assess multimodal models across a diverse range of vision-language understanding and generation tasks, such as visual question answering, text-to-image/video generation, and image-text retrieval. We decouple model inference from evaluation through an independent evaluation service, thus enabling flexible resource allocation and seamless integration of new tasks and models. Moreover, FlagEvalMM utilizes advanced inference acceleration tools (e.g., vLLM, SGLang) and asynchronous data loading to significantly enhance evaluation efficiency. Extensive experiments show that FlagEvalMM offers accurate and efficient insights into model strengths and limitations, making it a valuable tool for advancing multimodal research. The framework is publicly accessible at https://github.com/flageval-baai/FlagEvalMM, with a demonstration video available at https://youtu.be/L7EtacjoM0k."
}