Chinese online medical question answering drawn from consumer health platforms.
Audited by MedCheckHe et al., BMC Medical Informatics 2019
Key facts
| What it measures | Chinese online medical question answering drawn from consumer health platforms. |
| Who should care | Teams building consumer health tools in Chinese. |
| Use it when | Consumer-facing Chinese health language evaluation. |
| Do not use it for | Clinical decision support. |
| Score scale | Answer selection and ranking metrics. |
| Grader method | unknown |
| First released | 2019 |
| Languages | Chinese |
| Use cases | patient communication |
| Citation | He et al., BMC Medical Informatics 2019 |
| Status | active |
Frequently asked questions
What does webMedQA measure?
Chinese online medical question answering drawn from consumer health platforms.
Who should use webMedQA?
Teams building consumer health tools in Chinese. Consumer-facing Chinese health language evaluation.
What should webMedQA not be used for?
Clinical decision support.
How are webMedQA scores reported?
Answer selection and ranking metrics. Scores from different benchmarks are not comparable to each other.
Is webMedQA independent?
No conflicts of interest have been verified for webMedQA in this registry as of 2026-08-05. Absence of a recorded conflict means none has been verified, not that none exists.
Compare with
Chinese-language evaluation of physical and mental health knowledge in large models.
Physician-written rubrics score open-ended answers to realistic health conversations, including patient-facing
Open public voting on model answers, filtered to a medicine and healthcare occupational category.
Practicing clinicians submit their own real questions and pick which of two model answers they prefer. Access
Medical questions paired with multiple valid expert explanations, so a model is judged on reasoning as well as
Tests models on 121 real clinical work tasks, not exam questions: summarizing records, drafting discharge inst
