This survey provides a comprehensive overview of the application and evaluation of Large Language Models (LLMs) in the medical industry. It highlights the potential of LLMs to transform healthcare through their capabilities in language understanding and generation, emphasizing the need for specialized evaluation frameworks to ensure ethical and effective deployment. The survey explores LLM applications across clinical settings, medical text data processing, research, education, and public health awareness. It details evaluations based on performance in tasks such as clinical diagnosis, medical text data processing, information retrieval, data analysis, and educational content generation. The survey discusses evaluation methods and metrics, including models, evaluators, and comparative experiments, and provides a categorized description of benchmarks for tasks like question answering, summarization, information extraction, bioinformatics, information retrieval, and general comprehensive benchmarks. The survey also addresses the challenges and specific issues in evaluating LLMs in healthcare, including technical, ethical, and legal challenges, and discusses potential strategies for improving evaluation frameworks. The survey evaluates the current state of LLM applications in the medical field, focusing on clinical applications, medical text data processing, medical research, medical education, and public health awareness. It highlights the performance of various LLMs in specialized medical fields such as endocrinology, ophthalmology, orthopedics, reproductive medicine, and mental health, and discusses their potential in enhancing patient engagement, improving diagnostic accuracy, and offering personalized treatment plans. The survey also addresses the challenges of integrating LLMs into healthcare, including data privacy, ethical considerations, and the verification of AI-generated information. The survey concludes that while LLMs show great potential in healthcare, their deployment requires rigorous evaluation to ensure their reliability, safety, efficiency, and ethical integrity.This survey provides a comprehensive overview of the application and evaluation of Large Language Models (LLMs) in the medical industry. It highlights the potential of LLMs to transform healthcare through their capabilities in language understanding and generation, emphasizing the need for specialized evaluation frameworks to ensure ethical and effective deployment. The survey explores LLM applications across clinical settings, medical text data processing, research, education, and public health awareness. It details evaluations based on performance in tasks such as clinical diagnosis, medical text data processing, information retrieval, data analysis, and educational content generation. The survey discusses evaluation methods and metrics, including models, evaluators, and comparative experiments, and provides a categorized description of benchmarks for tasks like question answering, summarization, information extraction, bioinformatics, information retrieval, and general comprehensive benchmarks. The survey also addresses the challenges and specific issues in evaluating LLMs in healthcare, including technical, ethical, and legal challenges, and discusses potential strategies for improving evaluation frameworks. The survey evaluates the current state of LLM applications in the medical field, focusing on clinical applications, medical text data processing, medical research, medical education, and public health awareness. It highlights the performance of various LLMs in specialized medical fields such as endocrinology, ophthalmology, orthopedics, reproductive medicine, and mental health, and discusses their potential in enhancing patient engagement, improving diagnostic accuracy, and offering personalized treatment plans. The survey also addresses the challenges of integrating LLMs into healthcare, including data privacy, ethical considerations, and the verification of AI-generated information. The survey concludes that while LLMs show great potential in healthcare, their deployment requires rigorous evaluation to ensure their reliability, safety, efficiency, and ethical integrity.