@inproceedings{zheng-etal-2025-flageval,
    title = "{F}lag{E}val-Arena: A Side-by-Side Comparative Evaluation Platform for Large Language Models and Text-Driven {AIGC}",
    author = "Zheng, Jing-Shu  and
      Xuan, Richeng  and
      Qin, Bowen  and
      He, Zheqi  and
      Tongshuai.ren, Tongshuai.ren  and
      Li, Xuejing  and
      Yao, Jin-Ge  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.56/",
    pages = "583--591",
    ISBN = "979-8-89176-253-4",
    abstract = "We introduce FlagEval-Arena, an evaluation platform for side-by-side comparisons of large language models and text-driven AIGC systems.Compared with the well-known LM Arena (LMSYS Chatbot Arena), we reimplement our own framework with the flexibility to introduce new mechanisms or features. Our platform enables side-by-side evaluation not only for language models or vision-language models, but also text-to-image or text-to-video synthesis. We specifically target at Chinese audience with a more focus on the Chinese language, more models developed by Chinese institutes, and more general usage beyond the technical community. As a result, we currently observe very interesting differences from usual results presented by LM Arena. Our platform is available via this URL: \url{https://flageval.baai.org/#/arena}."
}