# EviPathBench: Benchmarking Evidence Acquisition and Reasoning in Vision-Language Models for Whole-Slide Pathology

arXiv: https://arxiv.org/abs/2607.19261 · HTML: https://mlsanity.com/paper/2607.19261/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 0 of its 42 references that are in the map.
- First posted on arXiv 21 Jul 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Built on by (most cited first, 3 of 3)

- [Agentic Visual Reasoning in Whole-Slide Pathology Images via Active Perception](https://mlsanity.com/paper/2608.08648/) (2026)
- [SlideBank: A Persistent Hierarchical Evidence Bank for Consistent Whole-Slide Reasoning](https://mlsanity.com/paper/2609.00342/) (2026)
- [PathoArgus: Advancing Evidence-Grounded Long-Context Visual Reasoning across Gigapixel Whole-Slide and Multi-Slide Case Contexts](https://mlsanity.com/paper/2608.17607/) (2026)

## Abstract (arXiv)

Whole-slide image (WSI) diagnosis requires identifying diagnostically relevant regions, examining them across magnifications, and integrating multi-scale evidence. However, most pathology benchmarks evaluate models on pre-cropped patches or pre-extracted slide features, leaving their ability to acquire evidence from gigapixel WSIs largely untested. We introduce EviPathBench, a benchmark for evaluating evidence acquisition and reasoning in vision-language models (VLMs) for whole-slide pathology. It evaluates four capabilities: image-to-text matching for evidence interpretation, text-to-image retrieval for evidence verification, diagnostic-region localization for evidence acquisition, and multi-scale reasoning for evidence integration. The benchmark is organized as a diagnostic tree linking nested regions across magnifications with scale-specific findings and path-level diagnoses. It contains 1,822 TCGA WSIs and 17,135 diagnostic paths annotated by ten board-certified pathologists. A private cohort of 190 breast cancer WSIs with detailed annotations further evaluates autonomous whole-slide exploration. We evaluate 19 VLMs spanning general-purpose, medical, and pathology-specialized families, plus one text-only reference model. Leading open-weight models achieve over 93% accuracy in multi-scale reasoning and over 50% in both cross-modal matching tasks. In contrast, diagnostic-region localization remains challenging: the best text-guided mean intersection-over-union is below 0.09, underperforming a center-based heuristic. During autonomous exploration, the unconditional hit rate drops from 0.522 at low magnification to 0.185 at intermediate magnification and 0.020 at high magnification. These results reveal a pronounced gap between reasoning over curated evidence and acquiring it from WSIs. EviPathBench provides a unified framework for measuring and improving both capabilities.