Original research · 2026-07 edition

AI SEO Statistics: Doctor (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 doctor.

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

I've had a dull headache for three days and ibuprofen isn't helping; should I see a GP or go straight to a specialist?
Can I treat a minor skin rash at home with OTC cream or is it time to book a dermatologist?
What specific certifications should I look for when choosing a new primary care physician for an elderly parent?
How do I find out if a doctor's office actually accepts my specific insurance plan before I show up for an appointment?
I don't have health insurance right now; how much does a typical office visit for a physical cost out-of-pocket?
What is the difference between seeing a Nurse Practitioner and a Medical Doctor for routine annual checkups?
My kid has a high fever and our regular pediatrician is closed; should I go to a 24-hour urgent care or the ER?
What are some red flags I should look for during a first consultation with a new family doctor?
Show all 15 questions
I am looking for a doctor who specializes in integrative medicine for chronic fatigue; how do I vet their credentials?
Are online doctor reviews generally reliable, or should I be looking at different metrics to judge a surgeon's skill?
I'm feeling sudden chest tightness but it feels mild; is this an appointment next week thing or a go to the hospital now thing?
Is a telehealth appointment effective for diagnosing a persistent cough, or do I really need to be seen in person for a physical exam?
I just moved to a new city; what is the most reliable way to find a highly-rated doctor who is actually taking new patients?
Is it normal for a specialist's office to charge a separate new patient administrative fee on top of my regular co-pay?
I have a list of three local cardiologists from my insurance; what specific questions should I ask their staff to see which one is best for managing high blood pressure?

Model by model

16-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 doctor buyers.

Behavior rates across 15 doctor buyer questions, 2026-07 edition. Last column: average across models.
ChatGPTClaudeGeminiConsensus
Recommends hiring a professional53%47%47%80%
Suggests DIY first20%20%20%100%
Names specific providers0%0%7%93%
Gives price or cost info0%0%13%87%
Tells to check reviews7%13%7%87%
Tells to verify credentials13%20%20%80%
Mentions case studies / portfolio0%0%0%100%
Mentions local proximity20%13%13%53%
Gives selection criteria40%60%40%67%
Warns about red flags27%33%13%60%
Asks a clarifying question67%80%0%13%
Recommends multiple quotes7%7%0%87%

By model

How each assistant handled Doctor questions.

Reading the 45 answers model by model shows how differently the three assistants treat the same doctor 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 46.7% (Claude), a 7-point gap on an identical question set.

Across the 15 doctor answers it produced, ChatGPT recommended hiring a professional in 53.3% of them and suggested a DIY approach first 20% of the time. It named a specific provider in 0% of answers (about 0 distinct providers per answer) and included price or cost information 0% of the time. ChatGPT asked a clarifying question before answering in 66.7% of cases, warned about red flags or scams in 26.7%, and told the buyer to verify credentials in 13.3%, averaging 516 words per answer. On the remaining cues it told the buyer to check reviews in 6.7%, pointed to case studies or a portfolio in 0%, and framed the choice around local proximity in 20%; a selection-criteria checklist appeared in 40% of its answers and a recommendation to gather multiple quotes in 6.7%.

Across the 15 doctor answers it produced, Claude recommended hiring a professional in 46.7% of them and suggested a DIY approach first 20% of the time. It named a specific provider in 0% of answers (about 0 distinct providers per answer) and included price or cost information 0% of the time. Claude asked a clarifying question before answering in 80% of cases, warned about red flags or scams in 33.3%, and told the buyer to verify credentials in 20%, averaging 308 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 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 doctor answers it produced, Gemini recommended hiring a professional in 46.7% of them and suggested a DIY approach first 20% 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 13.3% of the time. Gemini asked a clarifying question before answering in 0% of cases, warned about red flags or scams in 13.3%, and told the buyer to verify credentials in 20%, averaging 288 words per answer. On the remaining cues it told the buyer to check reviews in 6.7%, 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 40% of its answers and a recommendation to gather multiple quotes in 0%.

Taken together, ChatGPT is the assistant most likely to route a doctor buyer to a professional (53.3%) and Claude the least (46.7%). ChatGPT produced the longest answers, at 516 words on average. Specific providers were named most often by Gemini (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 16.3 points — the average distance between the most and least likely model across the coded behaviors. The gaps below are where which assistant a doctor buyer happens to ask matters most:

  • Asks a clarifying question: from 0% (Gemini) to 80% (Claude) — a 80-point spread.
  • Gives selection criteria: from 40% (ChatGPT) to 60% (Claude) — a 20-point spread.
  • Warns about red flags or scams: from 13.3% (Gemini) to 33.3% (Claude) — a 20-point spread.
  • Gives price or cost information: from 0% (ChatGPT) to 13.3% (Gemini) — a 13-point spread.
  • Names a specific provider: from 0% (ChatGPT) to 6.7% (Gemini) — a 7-point spread.

The widest single gap — asks a clarifying question, 80 points — means a doctor 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 doctor market.

Where they agree

The points of near-consensus in Doctor.

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

  • Suggests a DIY approach first: 20% across all three models.
  • Mentions case studies or portfolio: 0% across all three models.
  • Recommends hiring a professional: 46.7%–53.3% across all three (a 7-point spread).
  • Tells the buyer to check reviews: 6.7%–13.3% 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" (13.3%).

Every behavior, measured

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

The behaviors AI models reproduce most often for doctor are recommends hiring a professional (48.9% on average), asks a clarifying question (48.9%) and gives selection criteria (46.7%); the rarest are mentions case studies or portfolio (0%), names a specific provider (2.2%) and gives price or cost information (4.4%). 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:

  • Recommends hiring a professional: 48.9% on average (ChatGPT 53.3%, Claude 46.7%, Gemini 46.7%) — a 7-point spread.
  • Asks a clarifying question: 48.9% on average (ChatGPT 66.7%, Claude 80%, Gemini 0%) — a 80-point spread.
  • Gives selection criteria: 46.7% on average (ChatGPT 40%, Claude 60%, Gemini 40%) — a 20-point spread.
  • Warns about red flags or scams: 24.4% on average (ChatGPT 26.7%, Claude 33.3%, Gemini 13.3%) — a 20-point spread.
  • Suggests a DIY approach first: 20% on average (ChatGPT 20%, Claude 20%, Gemini 20%).
  • Tells the buyer to verify credentials: 17.8% on average (ChatGPT 13.3%, Claude 20%, Gemini 20%) — a 7-point spread.
  • Mentions local proximity: 15.5% on average (ChatGPT 20%, Claude 13.3%, Gemini 13.3%) — a 7-point spread.
  • Tells the buyer to check reviews: 8.9% on average (ChatGPT 6.7%, Claude 13.3%, Gemini 6.7%) — a 7-point spread.
  • Recommends multiple quotes: 4.5% on average (ChatGPT 6.7%, Claude 6.7%, Gemini 0%) — a 7-point spread.
  • Gives price or cost information: 4.4% on average (ChatGPT 0%, Claude 0%, Gemini 13.3%) — a 13-point spread.
  • Names a specific provider: 2.2% on average (ChatGPT 0%, Claude 0%, Gemini 6.7%) — 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 doctor buyer.

Beyond whether to hire, the rubric codes how carefully each assistant protects the doctor buyer once a decision is made. Telling the buyer to check reviews or ratings appeared in 8.9% of answers on average. Verifying credentials or certifications appeared in 17.8%. Warning about red flags or scams appeared in 24.4%.

On structuring the decision, a selection-criteria checklist showed up in 46.7% of answers on average and a recommendation to gather multiple quotes in 4.5%. The single least-reproduced protective signal for doctor is "recommends multiple quotes" at 4.5% 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 Doctor providers?

For service providers the decisive question is whether these systems name anyone at all. Across 45 doctor answers, a specific provider was named in 2.2% of responses on average — roughly 0.1 distinct providers per answer. In practice the assistants behave far more as an explanatory layer than as a referral engine for doctor: visibility comes from being the reasoning a model reproduces, not from being the named recommendation.

The question set

What these 15 Doctor questions cover.

The 15 questions behind every percentage on this page were drawn from real doctor (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 doctor 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 doctor 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 →