{"ID":2834855,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.00818","arxiv_id":"2512.00818","title":"Med-CMR: A Fine-Grained Benchmark Integrating Visual Evidence and Clinical Logic for Medical Complex Multimodal Reasoning","abstract":"MLLMs MLLMs are beginning to appear in clinical workflows, but their ability to perform complex medical reasoning remains unclear. We present Med-CMR, a fine-grained Medical Complex Multimodal Reasoning benchmark. Med-CMR distinguishes from existing counterparts by three core features: 1) Systematic capability decomposition, splitting medical multimodal reasoning into fine-grained visual understanding and multi-step reasoning to enable targeted evaluation; 2) Challenging task design, with visual understanding across three key dimensions (small-object detection, fine-detail discrimination, spatial understanding) and reasoning covering four clinically relevant scenarios (temporal prediction, causal reasoning, long-tail generalization, multi-source integration); 3) Broad, high-quality data coverage, comprising 20,653 Visual Question Answering (VQA) pairs spanning 11 organ systems and 12 imaging modalities, validated via a rigorous two-stage (human expert + model-assisted) review to ensure clinical authenticity. We evaluate 18 state-of-the-art MLLMs with Med-CMR, revealing GPT-5 as the top-performing commercial model: 57.81 accuracy on multiple-choice questions (MCQs) and a 48.70 open-ended score, outperforming Gemini 2.5 Pro (49.87 MCQ accuracy, 45.98 open-ended score) and leading open-source model Qwen3-VL-235B-A22B (49.34 MCQ accuracy, 42.62 open-ended score). However, specialized medical MLLMs do not reliably outperform strong general models, and long-tail generalization emerges as the dominant failure mode. Med-CMR thus provides a stress test for visual-reasoning integration and rare-case robustness in medical MLLMs, and a rigorous yardstick for future clinical systems.","short_abstract":"MLLMs MLLMs are beginning to appear in clinical workflows, but their ability to perform complex medical reasoning remains unclear. We present Med-CMR, a fine-grained Medical Complex Multimodal Reasoning benchmark. Med-CMR distinguishes from existing counterparts by three core features: 1) Systematic capability decompos...","url_abs":"https://arxiv.org/abs/2512.00818","url_pdf":"https://arxiv.org/pdf/2512.00818v2","authors":"[\"Haozhen Gong\",\"Xiaozhong Ji\",\"Yuansen Liu\",\"Wenbin Wu\",\"Xiaoxiao Yan\",\"Jingjing Liu\",\"Kai Wu\",\"Jiazhen Pan\",\"Bailiang Jian\",\"Jiangning Zhang\",\"Xiaobin Hu\",\"Hongwei Bran Li\"]","published":"2025-11-30T09:56:50Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CV\"]","methods":"[\"Large Language Model\",\"Generative Adversarial Network\"]","has_code":false}