AI SEO Statistics: Doctor ON Demand (2026-07 edition)
40 questions · 120/120 expected AI responses · 3 models · measured 2026-07-06
Apply these findings to your doctor on demand SEO strategy.
This benchmark explains how AI assistants advise buyers. The related service page turns those findings into the technical, content, authority, and conversion priorities for this market.
The question bank
The questions we tested: a frozen buyer-intent benchmark for doctor on demand.
The question set was curated from a predefined buyer-intent taxonomy and held constant for this edition. Each model received the same wording. These are the prompts behind every percentage on this page.
Show all 40 questions
Model by model
18.5% question-level model disagreement.
This rate is the average pairwise disagreement between binary behavior codes across questions and behaviors. It is not the gap between the highest and lowest aggregated model percentages.
Behavior prevalence across 40 doctor on demand benchmark questions, 2026-07 edition. Last column: equal-model mean.
| Behavior | ChatGPT | Claude | Gemini | Equal-model mean |
|---|---|---|---|---|
| Recommends hiring a professional | 60% | 57.5% | 47.5% | 55% |
| Suggests DIY first | 22.5% | 10% | 10% | 14.2% |
| Names specific providers | 17.5% | 42.5% | 57.5% | 39.2% |
| Gives price or cost info | 5% | 7.5% | 10% | 7.5% |
| Tells to check reviews | 5% | 10% | 0% | 5% |
| Tells to verify credentials | 20% | 10% | 10% | 13.3% |
| Mentions case studies / portfolio | 0% | 0% | 0% | 0% |
| Mentions local proximity | 32.5% | 32.5% | 27.5% | 30.8% |
| Gives selection criteria | 32.5% | 40% | 15% | 29.2% |
| Warns about red flags | 15% | 15% | 2.5% | 10.8% |
| Asks a clarifying question | 60% | 77.5% | 5% | 47.5% |
| Recommends multiple quotes | 0% | 2.5% | 0% | 0.8% |
Question-level agreement
How often all measured models received the same binary code.
Agreement is calculated question by question for each behavior. A high value can coexist with a low behavior prevalence; it means the models usually agreed on whether the behavior appeared.
All-model binary agreement by behavior across 40 benchmark questions.
| Behavior | All-model agreement |
|---|---|
| Recommends hiring a professional | 75% |
| Suggests DIY first | 80% |
| Names specific providers | 52.5% |
| Gives price or cost info | 95% |
| Tells to check reviews | 90% |
| Tells to verify credentials | 80% |
| Mentions case studies / portfolio | 100% |
| Mentions local proximity | 55% |
| Gives selection criteria | 52.5% |
| Warns about red flags | 75% |
| Asks a clarifying question | 15% |
| Recommends multiple quotes | 97.5% |
By model
How each assistant handled Doctor ON Demand questions.
Reading the 120 answers model by model shows how differently the three assistants treat the same doctor on demand questions. On the most consequential behavior, whether to send the buyer to a professional at all, the rate ranged from 60% (ChatGPT) down to 47.5% (Gemini), a 13-point gap on an identical question set.
Across the 40 doctor on demand answers it produced, ChatGPT recommended hiring a professional in 60% of them and suggested a DIY approach first 22.5% of the time. It named a specific provider in 17.5% of answers (about 0.6 distinct providers per answer) and included price or cost information 5% of the time. ChatGPT asked a clarifying question before answering in 60% of cases, warned about red flags or scams in 15%, and told the buyer to verify credentials in 20%, averaging 418 words per answer. On the remaining cues it told the buyer to check reviews in 5%, pointed to case studies or a portfolio in 0%, and framed the choice around local proximity in 32.5%; a selection-criteria checklist appeared in 32.5% of its answers and a recommendation to gather multiple quotes in 0%.
Across the 40 doctor on demand answers it produced, Claude recommended hiring a professional in 57.5% of them and suggested a DIY approach first 10% of the time. It named a specific provider in 42.5% of answers (about 1.5 distinct providers per answer) and included price or cost information 7.5% of the time. Claude asked a clarifying question before answering in 77.5% of cases, warned about red flags or scams in 15%, and told the buyer to verify credentials in 10%, averaging 274 words per answer. On the remaining cues it told the buyer to check reviews in 10%, pointed to case studies or a portfolio in 0%, and framed the choice around local proximity in 32.5%; a selection-criteria checklist appeared in 40% of its answers and a recommendation to gather multiple quotes in 2.5%.
Across the 40 doctor on demand answers it produced, Gemini recommended hiring a professional in 47.5% of them and suggested a DIY approach first 10% of the time. It named a specific provider in 57.5% of answers (about 2 distinct providers per answer) and included price or cost information 10% of the time. Gemini asked a clarifying question before answering in 5% of cases, warned about red flags or scams in 2.5%, and told the buyer to verify credentials in 10%, averaging 314 words per answer. On the remaining cues it told the buyer to check reviews in 0%, pointed to case studies or a portfolio in 0%, and framed the choice around local proximity in 27.5%; a selection-criteria checklist appeared in 15% of its answers and a recommendation to gather multiple quotes in 0%.
Taken together, ChatGPT is the assistant most likely to route a buyer researching doctor on demand toward professional help (60%) and Gemini the least (47.5%). ChatGPT produced the longest answers, at 418 words on average. Specific providers were named most often by Gemini (57.5%). Even there, roughly one answer in 2 carried a name.
Where they disagree
The behaviors where the choice of model changes the answer.
Question-level model disagreement is 18.5%. This is the average pairwise rate at which models received different binary codes across questions and behaviors. The observed rate spreads below are a separate measure showing where the choice of assistant matters most for a buyer researching doctor on demand:
- Asks a clarifying question: from 5% (Gemini) to 77.5% (Claude). The spread is 73 points.
- Names a specific provider: from 17.5% (ChatGPT) to 57.5% (Gemini). The spread is 40 points.
- Gives selection criteria: from 15% (Gemini) to 40% (Claude). The spread is 25 points.
- Recommends hiring a professional: from 47.5% (Gemini) to 60% (ChatGPT). The spread is 13 points.
- Suggests a DIY approach first: from 10% (Claude) to 22.5% (ChatGPT). The spread is 13 points.
The widest single gap concerns asks a clarifying question at 73 points. This means a buyer researching doctor on demand 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 on demand market.
Where they agree
The points of near-consensus in Doctor ON Demand.
On other behaviors the three models move almost in lockstep. The points of near-consensus for doctor on demand, where all three landed within a few points of each other:
- Mentions case studies or portfolio: 0% across all three models.
- Recommends multiple quotes: 0%–2.5% across all three (a 3-point spread).
- Gives price or cost information: 5%–10% across all three (a 5-point spread).
- Mentions local proximity: 27.5%–32.5% across all three (a 5-point spread).
Measured question by question, the three assistants coded a response the same way most consistently on "mentions case studies or portfolio" (identical coding in 100% of questions) and least consistently on "asks a clarifying question" (15%).
Every behavior, measured
All twelve coded behaviors for Doctor ON Demand, averaged across the three models.
The behaviors AI models reproduce most often for doctor on demand are recommends hiring a professional (55% on average), asks a clarifying question (47.5%) and names a specific provider (39.2%); the rarest are mentions case studies or portfolio (0%), recommends multiple quotes (0.8%) and tells the buyer to check reviews (5%). Each figure below is the share of a model's 40 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: 55% on average (ChatGPT 60%, Claude 57.5%, Gemini 47.5%). The spread is 13 points.
- Asks a clarifying question: 47.5% on average (ChatGPT 60%, Claude 77.5%, Gemini 5%). The spread is 73 points.
- Names a specific provider: 39.2% on average (ChatGPT 17.5%, Claude 42.5%, Gemini 57.5%). The spread is 40 points.
- Mentions local proximity: 30.8% on average (ChatGPT 32.5%, Claude 32.5%, Gemini 27.5%). The spread is 5 points.
- Gives selection criteria: 29.2% on average (ChatGPT 32.5%, Claude 40%, Gemini 15%). The spread is 25 points.
- Suggests a DIY approach first: 14.2% on average (ChatGPT 22.5%, Claude 10%, Gemini 10%). The spread is 13 points.
- Tells the buyer to verify credentials: 13.3% on average (ChatGPT 20%, Claude 10%, Gemini 10%). The spread is 10 points.
- Warns about red flags or scams: 10.8% on average (ChatGPT 15%, Claude 15%, Gemini 2.5%). The spread is 13 points.
- Gives price or cost information: 7.5% on average (ChatGPT 5%, Claude 7.5%, Gemini 10%). The spread is 5 points.
- Tells the buyer to check reviews: 5% on average (ChatGPT 5%, Claude 10%, Gemini 0%). The spread is 10 points.
- Recommends multiple quotes: 0.8% on average (ChatGPT 0%, Claude 2.5%, Gemini 0%). The spread is 3 points.
- Mentions case studies or portfolio: 0% on average (ChatGPT 0%, Claude 0%, Gemini 0%).
Trust signals
How well the models protect the doctor on demand buyer.
Beyond whether to hire, the rubric codes how carefully each assistant protects the doctor on demand buyer once a decision is made. Telling the buyer to check reviews or ratings appeared in 5% of answers on average. Verifying credentials or certifications appeared in 13.3%. Warning about red flags or scams appeared in 10.8%.
On structuring the decision, a selection-criteria checklist showed up in 29.2% of answers on average and a recommendation to gather multiple quotes in 0.8%. The single least-reproduced protective signal for doctor on demand is "recommends multiple quotes" at 0.8% on average. This is 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 ON Demand providers?
For service providers the decisive question is whether these systems name anyone at all. Across 120 doctor on demand answers, a specific provider was named in 39.2% of responses on average, or roughly 1.4 distinct providers per answer. In practice the assistants behave far more as an explanatory layer than as a referral engine for doctor on demand: visibility comes from being the reasoning a model reproduces, not from being the named recommendation.
The question set
What these 40 Doctor ON Demand questions cover.
The 40 questions behind every percentage on this page form a frozen doctor on demand (healthcare services; buyer hiring decisions for this specific service) buyer-intent benchmark. Each was put to all 3 models once, with identical wording, so the rates above describe how the assistants handled this exact doctor on demand question set rather than 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 40 answers in which the behavior appeared at least once. It is not a confidence score. Because each model answered every question exactly once on 2026-07-06, the figures describe this specific doctor on demand 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.
40 frozen benchmark questions, one expected response per model per question (ChatGPT API (gpt-5-mini), Claude API (claude-sonnet-5), Gemini API (gemini-3-flash-preview)), collected 2026-07-06 and coded against a fixed 12-behavior rubric. The pipeline validates the schema, recomputes aggregates and reports consistency issues. AI outputs vary with model version, location and time, so the figures describe this edition's exact sample and measurement window. Read the full methodology →
Citation
Cite this edition.
Authority Specialist. “AI SEO Statistics: Doctor ON Demand (2026-07 edition).” AuthoritySpecialist.com. https://authorityspecialist.com/research/ai-seo-statistics/services/health/doctor-on-demand