Overview
Who this competition fits
Builders comfortable with Chinese or bilingual ModelScope contest pages and open model workflows.
Read the original official blurb
本次大赛设“硅基智能体 X 碳基医学生”双赛道，基于 OpenHospital 底座，构建高度拟真的全科诊疗 Arena。这里没有标准单选题，只有 12,000 名鲜活的智能体患者与上千种错综复杂的疾病网络，覆盖多发病、罕见病及复杂共病。这是一场让 "硅基智能体"与"碳基医学生"同台竞技 的临床试炼——评判标准回归医疗本质：问得更准、查得更精、治得更好。 Official category: 应用开发赛. Participants: 2. Organizers: 魔搭社区, 浙江大学, 浙江工商大学.
Resources
What this competition gives you
There is a baseline you can run as-is — starting from it is usually far faster than building from scratch.
- DataTraining server with patient agents, test results, evaluation, and standard answers
- DataVisual platform with patient agents, results, evaluation, and standard answers
- BaselineForkable, tunable doctor-agent baseline
- TutorialUser manual for platform, baseline use, and platform tutorial
- TutorialBaseline documentation and FAQ
- Training sessionPre-event live competition briefing with baseline demonstration and Q&A
- Support channelOfficial discussion area and WeChat Q&A group
- Free computeEvaluation-stage compute provided by the competition platform
Preparation
From registration to a first submission
- 01
Can read Chinese or English competition pages
- 02
Comfortable submitting a baseline
- 03
Basic familiarity with LLM tooling or agent workflows
Before you commit: Task details, eligibility, and scoring rules live mainly on the official ModelScope page and may change between seasons.
Source
How this page was assembled
Competition information is structured from the official page. Scores are platform estimates for decision support; official rules take precedence.
- Official competition page
- ModelScope
- Registration
- Open signup form
- Last checked
- Jun 3, 2026