paper-with-me

Papers

Benchmarking GPT-5 for Zero-Shot Multimodal Medical Reasoning in Radiology and Radiation Oncology

2025-08-15 · Mingzhe Hu, Zach Eidex, Shansong Wang, Mojtaba Safari, Qiang Li, Xiaofeng Yang arxiv

Radiology, radiation oncology, and medical physics require decision-making that integrates medical images, textual reports, and quantitative data under high-stakes conditions. With the introduction of GPT-5, it is critical to assess whether recent advances in large multimodal models translate into measurable gains in these safety-critical domains. We present a targeted zero-shot evaluation of GPT-5 and its smaller variants (GPT-5-mini, GPT-5-nano) against GPT-4o across three representative tasks. We present a targeted zero-shot evaluation of GPT-5 and its smaller variants (GPT-5-mini, GPT-5-nano) against GPT-4o across three representative tasks: (1) VQA-RAD, a benchmark for visual question answering in radiology; (2) SLAKE, a semantically annotated, multilingual VQA dataset testing cross-modal grounding; and (3) a curated Medical Physics Board Examination-style dataset of 150 multiple-choice questions spanning treatment planning, dosimetry, imaging, and quality assurance. Across all datasets, GPT-5 achieved the highest accuracy, with substantial gains over GPT-4o up to +20.00% in challenging anatomical regions such as the chest-mediastinal, +13.60% in lung-focused questions, and +11.44% in brain-tissue interpretation. On the board-style physics questions, GPT-5 attained 90.7% accuracy (136/150), exceeding the estimated human passing threshold, while GPT-4o trailed at 78.0%. These results demonstrate that GPT-5 delivers consistent and often pronounced performance improvements over GPT-4o in both image-grounded reasoning and domain-specific numerical problem-solving, highlighting its potential to augment expert workflows in medical imaging and therapeutic physics.

📄 PDF Abstract BibTeX arXiv:2508.13192

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Question Answering

Similar Papers 제목 키워드 기반

MedMASLab: A Unified Orchestration Framework for Benchmarking Multimodal Medical Multi-Agent Systems

2026-03-10 · Yunhang Qian, Xiaobin Hu, Jiaquan Yu, Siyang Xin 외 arxiv

While Multi-Agent Systems (MAS) show potential for complex clinical decision support, the field remains hindered by architectural fragmentation and the lack of standardized multimodal integration. Current medical MAS res…

Visual Grounding

MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and MLLM Integration

2024-10-06 · Lai Wei, Wenkai Wang, Xiaoyu Shen, Yu Xie 외

In recent advancements, multimodal large language models (MLLMs) have been fine-tuned on specific medical image datasets to address medical visual question answering (Med-VQA) tasks. However, this common approach of task…

Medical Visual Question AnsweringQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Inquire, Interact, and Integrate: A Proactive Agent Collaborative Framework for Zero-Shot Multimodal Medical Reasoning

2024-05-19 · Zishan Gu, Fenglin Liu, Changchang Yin, Ping Zhang

The adoption of large language models (LLMs) in healthcare has attracted significant research interest. However, their performance in healthcare remains under-investigated and potentially limited, due to i) they lack ric…

Multimodal ReasoningQuestion AnsweringVisual Question Answering

Benchmarking Vision-Language Contrastive Methods for Medical Representation Learning

2024-06-11 · Shuvendu Roy, Yasaman Parhizkar, Franklin Ogidi, Vahid Reza Khazaie 외

We perform a comprehensive benchmarking of contrastive frameworks for learning multimodal representations in the medical domain. Through this study, we aim to answer the following research questions: (i) How transferable…

BenchmarkingContrastive LearningImage RetrievalImage to text+4

How Far Have Medical Vision-Language Models Come? A Comprehensive Benchmarking Study

2025-07-15 · Che Liu, Jiazhen Pan, Weixiang Shen, Wenjia Bai 외 arxiv

Vision-Language Models (VLMs) trained on web-scale corpora excel at natural image tasks and are increasingly repurposed for healthcare; however, their competence in medical tasks remains underexplored. We present a compr…