45 consumer health questions, asked in English, Danish and German. 238 answers, 747 cited links. This page reports what the assistants cite. It gives no medical advice and makes no claims about any company’s products.
Scope of this release. Assistants covered so far: ChatGPT. 62 of 300 planned calls did not complete and are not in the numbers. Gemini and Claude run through the same pipeline and will be added to this page. Every number below is computed from the downloadable dataset.
Public health bodies
60%
of all cited links (445 of 747)
Pharma company sites
0%
of all cited links (0 of 747)
Share of citations by source type, all markets
Public health bodies
60%
Patient and professional orgs
23%
Journals and research
13%
Hospitals and health publishers
2.9%
Pharma company sites
0%
Wikipedia
0%
Press
0.3%
Forums and social media
0%
Unclassified
1.2%
747 cited links in 206 answers. Types with no citations are shown as 0%.
Three findings
1. The assistant cites institutions, not companies or crowds
60% of cited links go to public health bodies such as the NHS, sundhed.dk and gesundheitsinformation.de. Patient and professional organisations take 23%. Pharma company sites received 0 citations, Wikipedia 0 and forums 0, out of 747. For a company, this means its own website is not how it reaches these answers. The sources the assistant trusts are.
2. Sources are local to the market
The same question gets different sources in each language. In Germany, 49% of citations go to domains in the national top-level domain, led by gesundheitsinformation.de (26 of 241). In Denmark, 64% of citations go to domains in the national top-level domain, led by sundhed.dk (85 of 233). In United Kingdom, 71% of citations go to domains in the national top-level domain, led by nhs.uk (93 of 273). A visibility standard set in one market does not transfer to the next. Each market has its own short list of sources that decide what the assistant says.
3. The question type changes the source mix
For diagnosis questions, public health bodies take 73% of citations and research takes 3.2%. For lifestyle questions, public health bodies take 37%, patient and professional organisations 37%, and research 23%. Reporting one blended number per brand hides this. Prompt clusters need their own numbers.
Questions: 50 consumer health questions on diabetes, weight, heart health and general health, in six intent clusters. Each was written in English and translated to Danish and German. 45 are covered in this release.
Collection: each question was sent through the vendor API with web search switched on and the user location set to the market. Models: ChatGPT (gpt-5.5). Run date: 2026-09-19.
Repeats: every question was asked twice per model. For ChatGPT, the two runs shared 44% of their cited domains on average (Jaccard overlap). One run is a sample, not a fixed answer.
Extraction: each cited URL is reduced to its domain and matched against a rule list of source types. After one review pass, 1.2% of links remain unclassified. They are shown, not dropped.
Company mentions: answers were searched for 13 pharma and device company names. None was named in any answer. Product names were not searched.
Limits
An API answer with web search is close to, but not identical to, what a logged-in user sees in the chat app.
32 of 238 answers cited nothing. Those answers still shape what people read, and this study cannot say where their content came from.
Source types are assigned by domain. A press release hosted on a public body’s domain counts as that public body.
The translations were written by one person and not reviewed by native-speaking clinicians.
This is one run on one date. Shares will move as models and search indexes change.