# PathBench: A comprehensive comparison benchmark for pathology foundation models towards precision oncology

arXiv: https://arxiv.org/abs/2505.20202 · HTML: https://mlsanity.com/paper/2505.20202/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 40 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology](https://mlsanity.com/paper/2408.00738/) (2024)
- [Artificial Intelligence for Digital and Computational Pathology](https://mlsanity.com/paper/2401.06148/) (2023)
- [Phikon-v2, A large and public feature extractor for biomarker prediction](https://mlsanity.com/paper/2409.09173/) (2024)
- [Cross-Modal Translation and Alignment for Survival Analysis](https://mlsanity.com/paper/2309.12855/) (2023)
- [A Clinical Benchmark of Public Self-Supervised Pathology Foundation Models](https://mlsanity.com/paper/2407.06508/) (2024)
- [Hibou: A Family of Foundational Vision Transformers for Pathology](https://mlsanity.com/paper/2406.05074/) (2024)
- [A Multimodal Knowledge-enhanced Whole-slide Pathology Foundation Model](https://mlsanity.com/paper/2407.15362/) (2024)
- [Benchmarking foundation models as feature extractors for weakly-supervised computational pathology](https://mlsanity.com/paper/2408.15823/) (2024)
- [Towards A Generalizable Pathology Foundation Model via Unified Knowledge Distillation](https://mlsanity.com/paper/2407.18449/) (2024)
- [Foundation Models in Computational Pathology: A Review of Challenges, Opportunities, and Impact](https://mlsanity.com/paper/2502.08333/) (2025)
- [Benchmarking Pathology Foundation Models: Adaptation Strategies and Scenarios](https://mlsanity.com/paper/2410.16038/) (2024)
- [A Comprehensive Evaluation of Histopathology Foundation Models for Ovarian Cancer Subtype Classification](https://mlsanity.com/paper/2405.09990/) (2024)
- [Foundation Models -- A Panacea for Artificial Intelligence in Pathology?](https://mlsanity.com/paper/2502.21264/) (2025)
- [Evaluating Computational Pathology Foundation Models for Prostate Cancer Grading under Distribution Shifts](https://mlsanity.com/paper/2410.06723/) (2024)
- [How Good is my Histopathology Vision-Language Foundation Model? A Holistic Benchmark](https://mlsanity.com/paper/2503.12990/) (2025)

## Built on by (most cited first, 25 of 25)

- [A Large-Scale Benchmark of Cross-Modal Learning for Histology and Gene Expression in Spatial Transcriptomics](https://mlsanity.com/paper/2508.01490/) (2025)
- [OTSurv: A Novel Multiple Instance Learning Framework for Survival Prediction with Heterogeneity-aware Optimal Transport](https://mlsanity.com/paper/2506.20741/) (2025)
- [MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning](https://mlsanity.com/paper/2602.03320/) (2026)
- [TICON: A Slide-Level Tile Contextualizer for Histopathology Representation Learning](https://mlsanity.com/paper/2512.21331/) (2025)
- [Towards Robust Foundation Models for Digital Pathology](https://mlsanity.com/paper/2507.17845/) (2025)
- [Ensemble learning of pathology foundation models for precision oncology](https://mlsanity.com/paper/2508.16085/) (2025)
- [PathFound: An Agentic Multimodal Model Activating Evidence-seeking Pathological Diagnosis](https://mlsanity.com/paper/2512.23545/) (2025)
- [Benchmarking Foundation Models for Mitotic Figure Classification](https://mlsanity.com/paper/2508.04441/) (2025)
- [A Unified Low-level Foundation Model for Enhancing Pathology Image Quality](https://mlsanity.com/paper/2509.01071/) (2025)
- [nnMIL: A generalizable multiple instance learning framework for computational pathology](https://mlsanity.com/paper/2511.14907/) (2025)
- [MambaMIL+: Modeling Long-Term Contextual Patterns for Gigapixel Whole Slide Image](https://mlsanity.com/paper/2512.17726/) (2025)
- [A Deployment-Friendly Foundational Framework for Efficient Computational Pathology](https://mlsanity.com/paper/2602.14010/) (2026)
- [A Comprehensive Benchmark of Histopathology Foundation Models for Kidney Digital Pathology Images](https://mlsanity.com/paper/2603.15967/) (2026)
- [Plug-and-Play Logit Fusion for Heterogeneous Pathology Foundation Models](https://mlsanity.com/paper/2604.07779/) (2026)
- [Benchmarking Pathology Foundation Models for Breast Cancer Survival Prediction](https://mlsanity.com/paper/2604.24679/) (2026)
- [A Clinically Validated Foundation Model for Comprehensive Lung Pathology Interpretation](https://mlsanity.com/paper/2605.25878/) (2026)
- [Democratizing and accelerating AI-driven pathology research through agentic intelligence](https://mlsanity.com/paper/2606.20677/) (2026)
- [PANDA-PLUS-Bench: A Clinical Benchmark for Evaluating Robustness of AI Foundation Models in Prostate Cancer Diagnosis](https://mlsanity.com/paper/2512.14922/) (2025)
- [BRIGHT: A Collaborative Generalist-Specialist Foundation Model for Breast Pathology](https://mlsanity.com/paper/2603.03030/) (2026)
- [Spatial Transcriptomics-Guided Alignment Enhances Molecular Profiling in Pathology Foundation Model](https://mlsanity.com/paper/2606.03644/) (2026)
- [A Pathology Foundation Model for Gastric Cancer with Real-World Validation](https://mlsanity.com/paper/2606.04792/) (2026)
- [CellPath-Bench: A Multidimensional Benchmark for Whole-Slide Cellular Representations in Pathology Foundation Models](https://mlsanity.com/paper/2608.21060/) (2026)
- [Can You Trust Frozen Hematology Foundation Models under Acquisition Shift?](https://mlsanity.com/paper/2608.25148/) (2026)
- [PathLang: A Language-Centered Benchmark for Vision-Language Models in Computational Pathology](https://mlsanity.com/paper/2610.11329/) (2026)
- [Scaling Multi-Teacher Distillation for Digital Pathology](https://mlsanity.com/paper/2610.12574/) (2026)

## Abstract (arXiv)

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.