Original research · 2026-07 edition

AI SEO Statistics: Medical Practice (2026-07 edition)

15 questions · 45 AI responses · 3 models · measured 2026-07-04

See how AI talks about YOUR businessFull data table

The question bank

The questions we tested — sampled from real buyer journeys in medical practice.

Each model answered every question once, same wording, same day. These are the prompts behind every percentage on this page.

How do I know if I need a specialist for my chronic back pain or if a general practitioner can handle it?
Can I treat a sinus infection with over-the-counter meds, or is it time to see a doctor for antibiotics?
What are the most important things to look for in a pediatrician's patient reviews besides just the star rating?
How much should I expect to pay out of pocket for a standard physical therapy session if I'm out-of-network?
What is the main difference between seeing a family practice doctor versus an internal medicine specialist for an adult?
How can I find a local primary care physician who is actually accepting new patients and has appointments sooner than three months out?
What are some red flags that a medical clinic is more focused on upselling tests than on patient care?
Is a deep cut that won't stop bleeding something for urgent care, or should I go straight to the emergency room?
Show all 15 questions
I'm currently uninsured; what are my options for getting a basic wellness exam and blood work without breaking the bank?
Does it make any practical difference for my treatment if my doctor is a DO instead of an MD?
How can I search for a doctor who has a reputation for being particularly patient with people who have severe medical anxiety?
Which common health issues are better suited for a telehealth appointment rather than an in-person office visit?
What specific questions should I ask the front desk to ensure a new practice won't hit me with hidden facility fees?
I suspect I have a hormonal imbalance, so should I book an appointment with a specialist immediately or start with my regular doctor?
What is the professional way to request my medical records so I can get a second opinion from a different practice?

Model by model

14-point average divergence: which AI you ask changes the answer.

The divergence index is the average gap between the most and least likely model per behavior. Higher = the models disagree more about medical practice buyers.

Behavior rates across 15 medical practice buyer questions, 2026-07 edition. Last column: average across models.
ChatGPTClaudeGeminiConsensus
Recommends hiring a professional53%40%40%73%
Suggests DIY first33%33%33%100%
Names specific providers7%7%7%100%
Gives price or cost info7%13%20%87%
Tells to check reviews20%20%13%80%
Tells to verify credentials20%7%0%80%
Mentions case studies / portfolio0%0%0%100%
Mentions local proximity13%13%27%60%
Gives selection criteria53%60%47%60%
Warns about red flags13%20%20%93%
Asks a clarifying question53%53%0%27%
Recommends multiple quotes0%7%0%93%

By model

How each assistant handled Medical Practice questions.

Reading the 45 answers model by model shows how differently the three assistants treat the same medical practice questions. On the most consequential behavior — whether to send the buyer to a professional at all — the rate ranged from 53.3% (ChatGPT) down to 40% (Claude), a 13-point gap on an identical question set.

Across the 15 medical practice answers it produced, ChatGPT recommended hiring a professional in 53.3% of them and suggested a DIY approach first 33.3% of the time. It named a specific provider in 6.7% of answers (about 0.6 distinct providers per answer) and included price or cost information 6.7% of the time. ChatGPT asked a clarifying question before answering in 53.3% of cases, warned about red flags or scams in 13.3%, and told the buyer to verify credentials in 20%, averaging 482 words per answer. On the remaining cues it told the buyer to check reviews in 20%, pointed to case studies or a portfolio in 0%, and framed the choice around local proximity in 13.3%; a selection-criteria checklist appeared in 53.3% of its answers and a recommendation to gather multiple quotes in 0%.

Across the 15 medical practice answers it produced, Claude recommended hiring a professional in 40% of them and suggested a DIY approach first 33.3% of the time. It named a specific provider in 6.7% of answers (about 0.5 distinct providers per answer) and included price or cost information 13.3% of the time. Claude asked a clarifying question before answering in 53.3% of cases, warned about red flags or scams in 20%, and told the buyer to verify credentials in 6.7%, averaging 287 words per answer. On the remaining cues it told the buyer to check reviews in 20%, pointed to case studies or a portfolio in 0%, and framed the choice around local proximity in 13.3%; a selection-criteria checklist appeared in 60% of its answers and a recommendation to gather multiple quotes in 6.7%.

Across the 15 medical practice answers it produced, Gemini recommended hiring a professional in 40% of them and suggested a DIY approach first 33.3% of the time. It named a specific provider in 6.7% of answers (about 0.3 distinct providers per answer) and included price or cost information 20% of the time. Gemini asked a clarifying question before answering in 0% of cases, warned about red flags or scams in 20%, and told the buyer to verify credentials in 0%, averaging 270 words per answer. On the remaining cues it told the buyer to check reviews in 13.3%, pointed to case studies or a portfolio in 0%, and framed the choice around local proximity in 26.7%; a selection-criteria checklist appeared in 46.7% of its answers and a recommendation to gather multiple quotes in 0%.

Taken together, ChatGPT is the assistant most likely to route a medical practice buyer to a professional (53.3%) and Claude the least (40%). ChatGPT produced the longest answers, at 482 words on average. Specific providers were named most often by ChatGPT (6.7%) — even there, roughly one answer in 15 carried a name.

Where they disagree

The behaviors where the choice of model changes the answer.

The divergence index for this study is 13.7 points — the average distance between the most and least likely model across the coded behaviors. The gaps below are where which assistant a medical practice buyer happens to ask matters most:

  • Asks a clarifying question: from 0% (Gemini) to 53.3% (ChatGPT) — a 53-point spread.
  • Tells the buyer to verify credentials: from 0% (Gemini) to 20% (ChatGPT) — a 20-point spread.
  • Mentions local proximity: from 13.3% (ChatGPT) to 26.7% (Gemini) — a 13-point spread.
  • Recommends hiring a professional: from 40% (Claude) to 53.3% (ChatGPT) — a 13-point spread.
  • Gives price or cost information: from 6.7% (ChatGPT) to 20% (Gemini) — a 13-point spread.

The widest single gap — asks a clarifying question, 53 points — means a medical practice buyer can receive materially different guidance on the same question depending only on which assistant they happen to open, so any visibility strategy built on a single model's behavior describes only part of the medical practice market.

Where they agree

The points of near-consensus in Medical Practice.

On other behaviors the three models move almost in lockstep — the points of near-consensus for medical practice, where all three landed within a few points of each other:

  • Suggests a DIY approach first: 33.3% across all three models.
  • Names a specific provider: 6.7% across all three models.
  • Mentions case studies or portfolio: 0% across all three models.
  • Tells the buyer to check reviews: 13.3%–20% across all three (a 7-point spread).

Measured question by question, the three assistants coded a response the same way most consistently on "suggests a DIY approach first" (identical coding in 100% of questions) and least consistently on "asks a clarifying question" (26.7%).

Every behavior, measured

All twelve coded behaviors for Medical Practice, averaged across the three models.

The behaviors AI models reproduce most often for medical practice are gives selection criteria (53.3% on average), recommends hiring a professional (44.4%) and asks a clarifying question (35.5%); the rarest are mentions case studies or portfolio (0%), recommends multiple quotes (2.2%) and names a specific provider (6.7%). Each figure below is the share of a model's 15 answers in which the behavior appeared at least once, averaged across the 3 models with the full per-model range in parentheses:

  • Gives selection criteria: 53.3% on average (ChatGPT 53.3%, Claude 60%, Gemini 46.7%) — a 13-point spread.
  • Recommends hiring a professional: 44.4% on average (ChatGPT 53.3%, Claude 40%, Gemini 40%) — a 13-point spread.
  • Asks a clarifying question: 35.5% on average (ChatGPT 53.3%, Claude 53.3%, Gemini 0%) — a 53-point spread.
  • Suggests a DIY approach first: 33.3% on average (ChatGPT 33.3%, Claude 33.3%, Gemini 33.3%).
  • Tells the buyer to check reviews: 17.8% on average (ChatGPT 20%, Claude 20%, Gemini 13.3%) — a 7-point spread.
  • Mentions local proximity: 17.8% on average (ChatGPT 13.3%, Claude 13.3%, Gemini 26.7%) — a 13-point spread.
  • Warns about red flags or scams: 17.8% on average (ChatGPT 13.3%, Claude 20%, Gemini 20%) — a 7-point spread.
  • Gives price or cost information: 13.3% on average (ChatGPT 6.7%, Claude 13.3%, Gemini 20%) — a 13-point spread.
  • Tells the buyer to verify credentials: 8.9% on average (ChatGPT 20%, Claude 6.7%, Gemini 0%) — a 20-point spread.
  • Names a specific provider: 6.7% on average (ChatGPT 6.7%, Claude 6.7%, Gemini 6.7%).
  • Recommends multiple quotes: 2.2% on average (ChatGPT 0%, Claude 6.7%, Gemini 0%) — a 7-point spread.
  • Mentions case studies or portfolio: 0% on average (ChatGPT 0%, Claude 0%, Gemini 0%).

Trust signals

How well the models protect the medical practice buyer.

Beyond whether to hire, the rubric codes how carefully each assistant protects the medical practice buyer once a decision is made. Telling the buyer to check reviews or ratings appeared in 17.8% of answers on average. Verifying credentials or certifications appeared in 8.9%. Warning about red flags or scams appeared in 17.8%.

On structuring the decision, a selection-criteria checklist showed up in 53.3% of answers on average and a recommendation to gather multiple quotes in 2.2%. The single least-reproduced protective signal for medical practice is "recommends multiple quotes" at 2.2% on average — the clearest opening for content that supplies it, since the models are not yet reliably surfacing that guidance on their own.

Referral behavior

Do AI models name Medical Practice providers?

For service providers the decisive question is whether these systems name anyone at all. Across 45 medical practice answers, a specific provider was named in 6.7% of responses on average — roughly 0.5 distinct providers per answer. In practice the assistants behave far more as an explanatory layer than as a referral engine for medical practice: visibility comes from being the reasoning a model reproduces, not from being the named recommendation.

The question set

What these 15 Medical Practice questions cover.

The 15 questions behind every percentage on this page were drawn from real medical practice (healthcare services; buyer hiring decisions for this specific service) buyer journeys. Each was put to all 3 models once, with identical wording, so the rates above describe how the assistants handled this exact medical practice question set — not a general prior or a hand-picked subset. The full list is shown earlier on this page; the coded percentages are what those specific questions produced.

How to read this

A note on the numbers.

A percentage here is the share of a model's 15 answers in which the behavior appeared at least once — not a confidence score. Because each model answered every question exactly once on 2026-07-04, the figures describe this specific medical practice question set and snapshot rather than a general prior. The full protocol and coding rubric are documented in the study methodology.

Methodology

A controlled snapshot, documented end to end.

15 standardized buyer questions per industry, one response per model per question (ChatGPT (gpt-5-mini), Claude (claude-sonnet-5), Gemini (gemini-3-flash-preview)), collected 2026-07-04, coded against a fixed 12-behavior rubric with human QA. AI outputs vary with model version, location and time — figures describe this sample and window, and are refreshed each edition. Read the full methodology →