Abstract

The emergence of pathology foundation models has revolutionized computational histopathology, enabling highly accurate, generalized whole-slide image analysis for improved cancer diagnosis, and prognosis assessment. While these models show remarkable potential across cancer diagnostics and prognostics, their clinical translation faces critical challenges including variability in optimal model across cancer types, potential data leakage in evaluation, and lack of standardized benchmarks. Without rigorous, unbiased evaluation, even the most advanced PFMs risk remaining confined to research settings, delaying their life-saving applications. Existing benchmarking efforts remain limited by narrow cancer-type focus, potential pretraining data overlaps, or incomplete task coverage. We present PathBench, the first comprehensive benchmark addressing these gaps through: multi-center in-hourse datasets spanning common cancers with rigorous leakage prevention, evaluation across the full clinical spectrum from diagnosis to prognosis, and an automated leaderboard system for continuous model assessment. Our framework incorporates large-scale data, enabling objective comparison of PFMs while reflecting real-world clinical complexity. All evaluation data comes from private medical providers, with strict exclusion of any pretraining usage to avoid data leakage risks. We have collected 15,888 WSIs from 8,549 patients across 10 hospitals, encompassing over 64 diagnosis and prognosis tasks. Currently, our evaluation of 19 PFMs shows that Virchow2 and H-Optimus-1 are the most effective models overall. This work provides researchers with a robust platform for model development and offers clinicians actionable insights into PFM performance across diverse clinical scenarios, ultimately accelerating the translation of these transformative technologies into routine pathology practice.

For the technical detail, please refer to the original paper.

Downloads

Arxiv Preprint: click here

Live Leaderboard: click here

Reference

@article{ma2025pathbench,
      title={PathBench: A comprehensive comparison benchmark for pathology foundation models towards precision oncology},
      author={Ma, Jiabo and Xu, Yingxue and Zhou, Fengtao and Wang, Yihui and Jin, Cheng and Guo, Zhengrui and Wu, Jianfeng and Tang, On Ki and Zhou, Huajun and Wang, Xi and Luo, Luyang and Zhang, Zhengyu and Cai, Du and Gao, Zizhao and Wang, Wei and Liu, Yueping and He, Jiankun and Cui, Jing and Li, Zhenhui and Zhang, Jing and Gao, Feng and Zhang, Xiuming and Liang, Li and Chan, Ronald Cheong Kin and Wang, Zhe and Chen, Hao},
      journal={arXiv preprint arXiv:2505.20202},
      year={2025}
}