Medical LLM - Medium

**Medical LLM - Medium** model is an advanced clinical decision-support system built for structured medical reasoning rather than simple knowledge retrieval. <p><br/></p> It analyzes symptoms, diagnostics, and longitudinal patient histories to guide complex diagnostic and treatment decisions in line with established clinical guidelines. <p><br/></p> With multimodal vision capabilities, it can also interpret medical images and visual documents alongside text, broadening the range of clinical inputs it can reason over. Now grounded in curated, specialty-specific medical knowledge bases, it anchors conclusions to vetted clinical evidence for greater factual reliability. It delivers transparent, step-aware reasoning, weighs competing hypotheses, and communicates uncertainty to support risk-aware clinical judgment. <br/>**Key Capabilities:** - Achieves 93.0% average across OpenMed benchmarks; - Medical genetics: 99%; professional medicine: 98%; - Clinical knowledge comprehension: 94%; college biology mastery: 99%; - College medicine: 90.5%; anatomy: 92%; - Achieves 93.5% on MedQA and 78% on PubMedQA; - Safety & reliability: 94.5% on hallucination detection, inappropriate-content , refusal of unethical/illegal requests; - Fairness & bias: 98% pass rate on name bias, 93% on racial bias , and 91.67% on anchoring-bias resistance

搜集汇总

背景与挑战

背景概述

Medical LLM - Medium 是一个高性能的临床决策支持系统，专注于结构化医疗推理，能够分析症状、诊断和患者历史以指导复杂决策。它具备多模态能力，可处理医学图像和文本，并基于专业医学知识库确保事实可靠性，提供透明推理以支持临床判断。