# Medical thinking with multiple images

arXiv: https://arxiv.org/abs/2604.16506 · HTML: https://mlsanity.com/paper/2604.16506/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 22 of its 55 references that are in the map.
- First posted on arXiv 14 Apr 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 22 of 22)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://mlsanity.com/paper/2409.02813/) (2024)
- [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)
- [HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale](https://mlsanity.com/paper/2406.19280/) (2024)
- [Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions](https://mlsanity.com/paper/2402.18060/) (2024)
- [Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding](https://mlsanity.com/paper/2510.08668/) (2025)
- [GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI](https://mlsanity.com/paper/2408.03361/) (2024)
- [MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine](https://mlsanity.com/paper/2408.02900/) (2024)
- [MedRAX: Medical Reasoning Agent for Chest X-ray](https://mlsanity.com/paper/2502.02673/) (2025)
- [MIRAGE: The Illusion of Visual Understanding](https://mlsanity.com/paper/2603.21687/) (2026)
- [MedCoT: Medical Chain of Thought via Hierarchical Expert](https://mlsanity.com/paper/2412.13736/) (2024)
- [MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks](https://mlsanity.com/paper/2503.07459/) (2025)
- [Multimodal ChatGPT for Medical Applications: an Experimental Study of GPT-4V](https://mlsanity.com/paper/2310.19061/) (2023)
- [MedFrameQA: A Multi-Image Medical VQA Benchmark for Clinical Reasoning](https://mlsanity.com/paper/2505.16964/) (2025)
- [Hidden flaws behind expert-level accuracy of multimodal GPT-4 vision in medicine](https://mlsanity.com/paper/2401.08396/) (2024)
- [V2T-CoT: From Vision to Text Chain-of-Thought for Medical Reasoning and Diagnosis](https://mlsanity.com/paper/2506.19610/) (2025)
- [S-Chain: Structured Visual Chain-of-Thought For Medicine](https://mlsanity.com/paper/2510.22728/) (2025)
- [MultiViewDx: Evidence-Linked Multi-View Clinical Diagnosis](https://mlsanity.com/paper/2410.14948/) (2024)

## Built on by (most cited first, 4 of 4)

- [DDX-TRACE: A Benchmark for Medical Diagnostic Trajectories in VLMs](https://mlsanity.com/paper/2605.23629/) (2026)
- [Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI](https://mlsanity.com/paper/2610.09146/) (2026)
- [Rethinking Patient Education as Multi-turn Multi-modal Interaction](https://mlsanity.com/paper/2604.14656/) (2026)
- [MEDLAYXPLAIN: Benchmarking the Expert-Lay Gap in Medical Vision-Language Models](https://mlsanity.com/paper/2606.21194/) (2026)

## Abstract (arXiv)

Large language models perform well on many medical QA benchmarks, but real clinical reasoning often requires integrating evidence across multiple images rather than interpreting a single view. We introduce MedThinkVQA, an expert-annotated benchmark for thinking with multiple images, where models must interpret each image, combine cross-view evidence, and answer diagnostic questions with intermediate supervision and step-level evaluation. The dataset contains 8,067 cases, including 720 test cases, with an average of 6.62 images per case, substantially denser than prior work, whose expert-level benchmarks use at most 1.43 images per case. On the test set, the best closed-source models, Claude-4.6-Opus, Gemini-3-Pro, and GPT-5.2-xhigh, reach only 57.2%, 55.3%, and 54.9% accuracy, while GPT-5-mini and GPT-5-nano reach 39.7% and 30.8%. Strong open-source models lag behind, led by Qwen3.5-397B-A17B at 52.2% and Qwen3.5-27B at 50.6%. Further analysis identifies grounded multi-image reasoning as the main bottleneck: models often fail to extract, align, and compose evidence across views before higher-level inference can help. Providing expert single-image cues and cross-image summaries improves performance, whereas replacing them with self-generated intermediates reduces accuracy. Step-level analysis shows that over 70% of errors arise from image reading and cross-view integration. Scaling results further show that additional inference-time computation helps only when visual grounding is already reliable; when early evidence extraction is weak, longer reasoning yields limited or unstable gains and can amplify misread cues. These results suggest that the key challenge is not reasoning length alone, but reliable mechanisms for grounding, aligning, and composing distributed evidence across real-world multimodal clinical inputs.