# CellPath-Bench: A Multidimensional Benchmark for Whole-Slide Cellular Representations in Pathology Foundation Models

arXiv: https://arxiv.org/abs/2608.21060 · HTML: https://mlsanity.com/paper/2608.21060/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 152 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Builds on (most cited first, 11 of 11)

- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology](https://mlsanity.com/paper/2408.00738/) (2024)
- [Phikon-v2, A large and public feature extractor for biomarker prediction](https://mlsanity.com/paper/2409.09173/) (2024)
- [Hibou: A Family of Foundational Vision Transformers for Pathology](https://mlsanity.com/paper/2406.05074/) (2024)
- [Distilling foundation models for robust and efficient models in digital pathology](https://mlsanity.com/paper/2501.16239/) (2025)
- [PathBench: A comprehensive comparison benchmark for pathology foundation models towards precision oncology](https://mlsanity.com/paper/2505.20202/) (2025)
- [Towards Large-Scale Training of Pathology Foundation Models](https://mlsanity.com/paper/2404.15217/) (2024)
- [A Survey of Pathology Foundation Model: Progress and Future Directions](https://mlsanity.com/paper/2504.04045/) (2025)
- [Towards Spatial Transcriptomics-driven Pathology Foundation Models](https://mlsanity.com/paper/2602.14177/) (2026)
- [To What Extent Do Token-Level Representations from Pathology Foundation Models Improve Dense Prediction?](https://mlsanity.com/paper/2602.03887/) (2026)
- [Benchmarking Pathology Foundation Models for Spatial Domain Understanding](https://mlsanity.com/paper/2605.25764/) (2026)

## Abstract (arXiv)

Pathology foundation models (PFMs) are increasingly used as general-purpose backbones, yet existing benchmarks cannot systematically diagnose their whole-slide cellular representation capabilities, including the decodability of cell-type information and the transferability of such information across tissue sections, datasets, and anatomical organs. We introduce CellPath-Bench, a cellular-resolution benchmark that evaluates frozen PFMs themselves. Following quality control of 52 candidate Xenium datasets, we construct a panel of 25 spatially aligned H&E--Xenium tissue sections spanning 11 organs and 7,079,283 cells, harmonized into fine- and coarse-grained taxonomies. CellPath-Bench samples frozen WSI feature maps at registered nuclear coordinates and evaluates them using standardized multiclass linear probes. Cell Representation Advantage (CRA) measures the within-section advantage of nucleus-anchored representations over patch-level mean pooling, while Cell Representation Transferability (CRT) characterizes the generalization of cell-type decodability across tissue sections, datasets, and organs. We benchmark 30 pathology-specific and general-purpose foundation models through 304,920 runs across spatial readouts, magnifications, taxonomic granularities, and evaluation protocols. The results reveal substantial model-dependent differences in cell-type decodability and its cross-domain generalization, yielding distinct multidimensional capability profiles. CellPath-Bench provides a standardized framework for auditing cellular information in frozen PFM representations.