How we measure who ChatGPT recommends

These rankings aren't opinions, votes, or paid placements. They are a record of what ChatGPT actually answered when we asked — the same way a patient would — who to see.

The five steps, in plain language

1. 1

   We ask the questions real patients ask.

   In each metro we asked ChatGPT for a dentist 5 different ways — everyday phrasings like "Who is the best dentist near me?", "Which dentist should I go to for a dental implant?", and "Who does the best cosmetic dentistry in my city?". No trick prompts, no leading questions. 20 metros × 5 questions = 100 checks for this edition.

2. 2

   We record every practice it names.

   Each answer gets logged exactly as given. We then match every recommendation against the 4,320 Florida practices in our dataset. When ChatGPT names a business with multiple locations, we credit it once — one winner per named business, so no practice is double-counted.

3. 3

   We publish the count, not a number one.

   We tested this. Running the identical questions on the identical list a second time, the same day, changed which practice came out on top in more than a third of markets — and in most markets the top spot was already shared by two to five of them. What did NOT move was the count: a practice named in most checks was named in most checks again. So the page shows how many of the 5 checks named each one. Practices with the same count are shown together, alphabetically, because the measurement does not separate them.

4. 4

   Named once doesn't make the list.

   Practices named in exactly one check reappeared less than half the time when we re-ran the same questions. That is a coin flip, not a recommendation, so we keep the data and don't publish the name. Two mentions came back 86% of the time; four came back every time. Each metro page shows only the practices ChatGPT named more than once. We never publish a bottom list and never name who didn't make it.

5. 5

   We re-run it quarterly.

   The same benchmark, the same way, every quarter. Practices that improve their AI visibility can appear in the next edition — and the run date is printed on every page. This edition: August 2026.

This edition

Measured August 5, 2026 on ChatGPT (gpt-4o, with web search): 20 metros × 5 question phrasings = 100 checks. No other AI system is included in these numbers.

Earlier editions of this board were measured on a different AI assistant and also covered five Texas metros. This edition is ChatGPT only and covers 20 Florida metros, so the names and percentages here can differ from an older screenshot of this page — the market didn't change, the measurement did.

What this is — and what it isn't

Being on this list means ChatGPT recommended that practice when we asked, in this edition, in that metro. It is a measurement of AI visibility — not a judgment of the quality of anyone's work, and not a claim that unlisted dentists are worse at what they do. AI answers also change over time, which is exactly why we re-measure quarterly and date every edition.