@inproceedings{hosain-morol-2025-b,
    title = "{B}-{REASO}: A Multi-Level Multi-Faceted {B}engali Evaluation Suite for Foundation Models",
    author = "Hosain, Md Tanzib  and
      Morol, Md Kishor",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.findings-emnlp.492/",
    doi = "10.18653/v1/2025.findings-emnlp.492",
    pages = "9260--9274",
    ISBN = "979-8-89176-335-7",
    abstract = "The fast growth of large language models (LLMs) necessitates the urgent need for new NLP benchmarks. We provide B-REASO, the first inclusive Bengali assessment suite created to evaluate advanced foundation model knowledge and reasoning skills in a Bengali language setup. The B-REASO includes multiple-choice questions with four different degrees of difficulty: professional, college, high school, and middle school. The questions cover 50 different fields, from science and engineering to the humanities. Alongside B-REASO, there is B-REASO HEAVY, a subset of extremely difficult B-REASO topics that need for sophisticated reasoning skills to answer. We do a thorough assessment of the most sophisticated LLMs on B-REASO, encompassing models with an English focus. Findings show that only Claude-3.5-Sonnet was able to get an average accuracy of more than 65{\%}, indicating that contemporary LLMs still have a long way to go. We hope that B-REASO will support the creation and expansion of foundation models for Bengali users by assisting in the analysis of significant advantages and disadvantages of these models. We open-source our code and data at https://github.com/kraritt/b-reaso."
}