WeDoctor's Medical Large Model Tops CMB Leaderboard, Leading the Digital Upgrade of Medical AI

WeDoctor's Medical Large Model Tops CMB Leaderboard, Leading the Digital Upgrade of Medical AIRecently, CMB (Comprehensive Medical Benchmarking in Chinese), a leading domestic medical large model evaluation platform, updated its Chinese medical model evaluation (CMB-Exam) rankings. WeDoctor's medical large model, with its outstanding performance, topped the list with an average score of 91

WeDoctor's Medical Large Model Tops CMB Leaderboard, Leading the Digital Upgrade of Medical AI

Recently, CMB (Comprehensive Medical Benchmarking in Chinese), a leading domestic medical large model evaluation platform, updated its Chinese medical model evaluation (CMB-Exam) rankings. WeDoctor's medical large model, with its outstanding performance, topped the list with an average score of 91.71. This achievement not only showcases WeDoctor's technological leadership in the medical AI field but also further validates its crucial role in driving the digital upgrade of the traditional healthcare service industry.

CMB, designed specifically for the Chinese medical environment, is a comprehensive, multi-level medical benchmark test covering over 280,000 questions and complex case consultations. By simulating real medical scenarios, it comprehensively assesses the medical knowledge and clinical consultation capabilities of large models. WeDoctor's medical large model's excellent performance in this evaluation demonstrates its powerful capabilities in handling complex medical issues and providing accurate medical consultations.

WeDoctor has been deeply involved in the medical AI field for many years. Relying on its powerful large model capabilities, it has built a full-cycle closed loop of AI-enabled "medicine, pharmaceuticals, examination, health management, and administration," providing patients with comprehensive health management services from pre-diagnosis, during diagnosis, to post-diagnosis. Based on this, WeDoctor has taken the lead in opening up the 2H2C (from hospital to consumer) commercialization path, exploring new market space for the medical AI industry. According to media reports, WeDoctor's revenue continues to grow, and is expected to reach nearly 10 billion yuan this year.

In terms of improving large model performance, WeDoctor has significantly enhanced the large model's adaptability and problem-solving skills in dialogue scenarios through strategies such as aligned training, supervised training for role dialogue, and reinforcement learning based on human feedback. At the same time, with diverse real-world application scenarios such as intelligent hospitals and AI-powered healthcare communities, WeDoctor's medical large model demonstrates exceptional performance in multiple dimensions, including training data, performance evaluation, and practical application, further solidifying its leading position in the medical AI track.

On the application level, WeDoctor's independently developed "AI doctors, AI pharmacists, AI health management, AI intelligence control" four intelligent agents have been applied on a large scale in multiple medical institutions, forming a full-cycle application closed loop covering pre-diagnosis, during diagnosis, and post-diagnosis. These intelligent agents play a significant role in healthcare communities and intelligent hospitals, effectively improving healthcare service efficiency and quality.

In terms of data, the WeDoctor platform has accumulated over 400 million dialogue data, 200 million case files, and 200,000 doctor diagnosis data, providing a solid foundation for the deep learning and effective application of AI products. This data not only helps WeDoctor continuously optimize and enhance the performance of its large model, but also provides strong support for WeDoctor's continuous innovation in the medical AI field.

It is worth mentioning that WeDoctor, relying on models such as "AI healthcare communities" and intelligent hospitals, has successfully opened up the 2H2C commercialization path, becoming the first mature commercial model implemented in the medical AI industry. Taking Tianjin as an example, Tianjin WeDoctor Intelligent Hospital, as the leading unit, has jointly established Tianjin's primary digital healthcare community with multiple community health service centers and sites, as well as clinics across the city. Through a unified cloud management, cloud service, cloud pharmacy, and cloud inspection platform, it provides Tianjin residents with online-offline integrated healthcare services. Enabled by AI, Tianjin's healthcare community serves over 18,000 people daily, and the basic service scale continues to grow steadily.

Furthermore, WeDoctor is actively promoting the construction of medical large model evaluation platforms and the formulation of industry standards for medical large models. Through close cooperation with partners such as Zhejiang University and the Second Affiliated Hospital of Zhejiang University School of Medicine, WeDoctor has achieved significant results in the field of medical imaging AI and has been recognized as a provincial key laboratory in Zhejiang province. These efforts not only contribute to enhancing WeDoctor's competitiveness in the medical AI field but also play a positive role in promoting the healthy development of the entire industry.

Looking ahead, as WeDoctor's medical AI "circle of friends" continues to expand, more innovative service scenarios and business models will emerge. WeDoctor will continue to use medical large models as its technological foundation, leveraging its extensive medical service scenarios as its application foundation, accelerating the resolution of challenges facing traditional healthcare, injecting new impetus into the digital upgrade of the healthcare industry, and promoting the intelligent transformation of the industry.

Disclaimer: The content of this article is sourced from the internet. The copyright of the text, images, and other materials belongs to the original author. The platform reprints the materials for the purpose of conveying more information. The content of the article is for reference and learning only, and should not be used for commercial purposes. If it infringes on your legitimate rights and interests, please contact us promptly and we will handle it as soon as possible! We respect copyright and are committed to protecting it. Thank you for sharing.(Email:[email protected])