In this paper, we release the largest three-level hierarchical cervical dataset (HiCervix), and propose a hierarchical vision transformer-based classification benchmark method (HierSwin). HiCervix Dataset: HiCervix includes 40,229 cervical cells and is categorized into 29 annotated classes. These classes are organized within a three-level hierarchical tree to capture fine-grained subtype information. Citation Please use below to cite this paper if you find our work useful in your research. Cai D, Chen J, Zhao J, Xue Y, Yang S, Yuan W, Feng M, Weng H, Liu S, Peng Y, Zhu J, Wang K, Jackson C, Tang H, Huang J, Wang X. HiCervix: An Extensive Hierarchical Dataset and Benchmark for Cervical Cytology Classification. IEEE Trans Med Imaging. 2024 Jun 26;PP. doi: 10.1109/TMI.2024.3419697. Epub ahead of print. PMID: 38923481.