@inproceedings{wang-etal-2026-morphobench,
    title = "{M}orpho{B}ench: A Benchmark with Difficulty Adaptive to Model Reasoning",
    author = "Wang, Xukai  and
      Liu, Xuanbo  and
      Chen, Mingrui  and
      Zhong, Haitian  and
      Yang, Xuanlin  and
      Zeng, Bohan  and
      Hu, Jinbo  and
      Liang, Hao  and
      Niu, Junbo  and
      Li, Xuchen  and
      Wu, Ruitao  and
      An, Ruichuan  and
      Shi, Yang  and
      Liu, Liu  and
      Liu, Qiang  and
      Lin, Zhouchen  and
      Zhang, Xu-Yao  and
      Zhang, Wentao  and
      Dong, Bin",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1171/",
    pages = "23387--23411",
    ISBN = "979-8-89176-395-1",
    abstract = "With the advancement of powerful large-scale reasoning models, effectively evaluating the reasoning capabilities of these models has become increasingly important. However, existing benchmarks designed to assess the reasoning abilities of large models tend to be limited in scope and lack the flexibility to adapt their difficulty according to the evolving reasoning capacities of the models. To address this, we propose MorphoBench, a benchmark that incorporates multidisciplinary questions to evaluate the reasoning capabilities of large models and can adjust and update question difficulty based on the reasoning abilities of advanced models. Specifically, we curate the benchmark by selecting and collecting complex reasoning questions from existing benchmarks and sources such as Olympiad-level competitions. Additionally, MorphoBench adaptively modifies the analytical challenge of questions by leveraging key statements generated during the model{'}s reasoning process. Furthermore, it includes questions generated using simulation software, enabling dynamic adjustment of benchmark difficulty with minimal resource consumption. We have gathered over 1,300 test questions and iteratively adjusted the difficulty of MorphoBench based on the reasoning capabilities of models such as GPT-5 and Gemini-3-Pro. MorphoBench enhances the comprehensiveness and validity of model reasoning evaluation, providing reliable guidance for improving both the reasoning abilities and scientific robustness of large models."
}