# CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays

arXiv: https://arxiv.org/abs/2505.18087 · HTML: https://mlsanity.com/paper/2505.18087/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 20 of its 32 references that are in the map.
- First posted on arXiv 23 May 2025.

## 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/)

## Builds on (most cited first, 20 of 20)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms](https://mlsanity.com/paper/1905.13319/) (2019)
- [MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs](https://mlsanity.com/paper/1901.07042/) (2019)
- [BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs](https://mlsanity.com/paper/2303.00915/) (2023)
- [PathVQA: 30000+ Questions for Medical Visual Question Answering](https://mlsanity.com/paper/2003.10286/) (2020)
- [PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering](https://mlsanity.com/paper/2305.10415/) (2023)
- [MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding](https://mlsanity.com/paper/2501.18362/) (2025)
- [Pixtral 12B](https://mlsanity.com/paper/2410.07073/) (2024)
- [MAIRA-2: Grounded Radiology Report Generation](https://mlsanity.com/paper/2406.04449/) (2024)
- [HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation](https://mlsanity.com/paper/2502.09838/) (2025)
- [Chest ImaGenome Dataset for Clinical Reasoning](https://mlsanity.com/paper/2108.00316/) (2021)
- [A Vision-Language Foundation Model to Enhance Efficiency of Chest X-ray Interpretation](https://mlsanity.com/paper/2401.12208/) (2024)
- [PadChest-GR: A Bilingual Chest X-ray Dataset for Grounded Radiology Report Generation](https://mlsanity.com/paper/2411.05085/) (2024)
- [GEMeX: A Large-Scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosis](https://mlsanity.com/paper/2411.16778/) (2024)
- [Accurate Fine-Grained Segmentation of Human Anatomy in Radiographs via Volumetric Pseudo-Labeling](https://mlsanity.com/paper/2306.03934/) (2023)
- [RadVLM: A Multitask Conversational Vision-Language Model for Radiology](https://mlsanity.com/paper/2502.03333/) (2025)

## Built on by (most cited first, 6 of 6)

- [RadAgents: Multimodal Agentic Reasoning for Chest X-ray Interpretation with Radiologist-like Workflows](https://mlsanity.com/paper/2509.20490/) (2025)
- [Instruction-Guided Lesion Segmentation for Chest X-rays with Automatically Generated Large-Scale Dataset](https://mlsanity.com/paper/2511.15186/) (2025)
- [CXReasonAgent: Evidence-Grounded Diagnostic Reasoning Agent for Chest X-rays](https://mlsanity.com/paper/2602.23276/) (2026)
- [MI-CXR: A Benchmark for Longitudinal Reasoning over Multi-Interval Chest X-rays](https://mlsanity.com/paper/2605.15574/) (2026)
- [CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement](https://mlsanity.com/paper/2608.03890/) (2026)
- [BrainTRACE: Tracing Longitudinal, Multimodal, and Volumetric Evidence in Brain MRI Clinical Reasoning](https://mlsanity.com/paper/2610.06571/) (2026)

## Abstract (arXiv)

Recent progress in Large Vision-Language Models (LVLMs) has enabled promising applications in medical tasks, such as report generation and visual question answering. However, existing benchmarks focus mainly on the final diagnostic answer, offering limited insight into whether models engage in clinically meaningful reasoning. To address this, we present CheXStruct and CXReasonBench, a structured pipeline and benchmark built on the publicly available MIMIC-CXR-JPG dataset. CheXStruct automatically derives a sequence of intermediate reasoning steps directly from chest X-rays, such as segmenting anatomical regions, deriving anatomical landmarks and diagnostic measurements, computing diagnostic indices, and applying clinical thresholds. CXReasonBench leverages this pipeline to evaluate whether models can perform clinically valid reasoning steps and to what extent they can learn from structured guidance, enabling fine-grained and transparent assessment of diagnostic reasoning. The benchmark comprises 18,988 QA pairs across 12 diagnostic tasks and 1,200 cases, each paired with up to 4 visual inputs, and supports multi-path, multi-stage evaluation including visual grounding via anatomical region selection and diagnostic measurements. Even the strongest of 12 evaluated LVLMs struggle with structured reasoning and generalization, often failing to link abstract knowledge with anatomically grounded visual interpretation. The code is available at https://github.com/ttumyche/CXReasonBench