AI SEO Statistics: Osteopaths (2026-07 edition)
40 questions · 120 AI responses · 3 models · measured 2026-07-06
The question bank
The questions we tested — sampled from real buyer journeys in osteopaths.
Each model answered every question once, same wording, same day. These are the prompts behind every percentage on this page.
Show all 40 questions
Model by model
17-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 osteopaths buyers.
| ChatGPT | Claude | Gemini | Consensus | |
|---|---|---|---|---|
| Recommends hiring a professional | 70% | 65% | 55% | 73% |
| Suggests DIY first | 15% | 8% | 0% | 85% |
| Names specific providers | 3% | 3% | 3% | 100% |
| Gives price or cost info | 3% | 3% | 3% | 100% |
| Tells to check reviews | 10% | 5% | 0% | 90% |
| Tells to verify credentials | 53% | 18% | 13% | 58% |
| Mentions case studies / portfolio | 0% | 0% | 0% | 100% |
| Mentions local proximity | 20% | 15% | 10% | 80% |
| Gives selection criteria | 58% | 33% | 25% | 60% |
| Warns about red flags | 38% | 23% | 3% | 58% |
| Asks a clarifying question | 88% | 80% | 0% | 5% |
| Recommends multiple quotes | 5% | 0% | 0% | 95% |
By model
How each assistant handled Osteopaths questions.
Reading the 120 answers model by model shows how differently the three assistants treat the same osteopaths questions. On the most consequential behavior — whether to send the buyer to a professional at all — the rate ranged from 70% (ChatGPT) down to 55% (Gemini), a 15-point gap on an identical question set.
Across the 40 osteopaths answers it produced, ChatGPT recommended hiring a professional in 70% of them and suggested a DIY approach first 15% of the time. It named a specific provider in 2.5% of answers (about 0.1 distinct providers per answer) and included price or cost information 2.5% of the time. ChatGPT asked a clarifying question before answering in 87.5% of cases, warned about red flags or scams in 37.5%, and told the buyer to verify credentials in 52.5%, averaging 404 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 20%; a selection-criteria checklist appeared in 57.5% of its answers and a recommendation to gather multiple quotes in 5%.
Across the 40 osteopaths answers it produced, Claude recommended hiring a professional in 65% of them and suggested a DIY approach first 7.5% of the time. It named a specific provider in 2.5% of answers (about 0.1 distinct providers per answer) and included price or cost information 2.5% of the time. Claude asked a clarifying question before answering in 80% of cases, warned about red flags or scams in 22.5%, and told the buyer to verify credentials in 17.5%, averaging 273 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 15%; a selection-criteria checklist appeared in 32.5% of its answers and a recommendation to gather multiple quotes in 0%.
Across the 40 osteopaths answers it produced, Gemini recommended hiring a professional in 55% of them and suggested a DIY approach first 0% of the time. It named a specific provider in 2.5% of answers (about 0.1 distinct providers per answer) and included price or cost information 2.5% of the time. Gemini asked a clarifying question before answering in 0% of cases, warned about red flags or scams in 2.5%, and told the buyer to verify credentials in 12.5%, averaging 291 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 10%; a selection-criteria checklist appeared in 25% of its answers and a recommendation to gather multiple quotes in 0%.
Taken together, ChatGPT is the assistant most likely to route an osteopaths buyer to a professional (70%) and Gemini the least (55%). ChatGPT produced the longest answers, at 404 words on average. Specific providers were named most often by ChatGPT (2.5%) — even there, roughly one answer in 40 carried a name.
Where they disagree
The behaviors where the choice of model changes the answer.
The divergence index for this study is 16.5 points — the average distance between the most and least likely model across the coded behaviors. The gaps below are where which assistant an osteopaths buyer happens to ask matters most:
- Asks a clarifying question: from 0% (Gemini) to 87.5% (ChatGPT) — a 88-point spread.
- Tells the buyer to verify credentials: from 12.5% (Gemini) to 52.5% (ChatGPT) — a 40-point spread.
- Warns about red flags or scams: from 2.5% (Gemini) to 37.5% (ChatGPT) — a 35-point spread.
- Gives selection criteria: from 25% (Gemini) to 57.5% (ChatGPT) — a 33-point spread.
- Recommends hiring a professional: from 55% (Gemini) to 70% (ChatGPT) — a 15-point spread.
The widest single gap — asks a clarifying question, 88 points — means an osteopaths 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 osteopaths market.
Where they agree
The points of near-consensus in Osteopaths.
On other behaviors the three models move almost in lockstep — the points of near-consensus for osteopaths, where all three landed within a few points of each other:
- Names a specific provider: 2.5% across all three models.
- Gives price or cost information: 2.5% across all three models.
- Mentions case studies or portfolio: 0% across all three models.
- Recommends multiple quotes: 0%–5% across all three (a 5-point spread).
Measured question by question, the three assistants coded a response the same way most consistently on "names a specific provider" (identical coding in 100% of questions) and least consistently on "asks a clarifying question" (5%).
Every behavior, measured
All twelve coded behaviors for Osteopaths, averaged across the three models.
The behaviors AI models reproduce most often for osteopaths are recommends hiring a professional (63.3% on average), asks a clarifying question (55.8%) and gives selection criteria (38.3%); the rarest are mentions case studies or portfolio (0%), recommends multiple quotes (1.7%) and gives price or cost information (2.5%). 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: 63.3% on average (ChatGPT 70%, Claude 65%, Gemini 55%) — a 15-point spread.
- Asks a clarifying question: 55.8% on average (ChatGPT 87.5%, Claude 80%, Gemini 0%) — a 88-point spread.
- Gives selection criteria: 38.3% on average (ChatGPT 57.5%, Claude 32.5%, Gemini 25%) — a 33-point spread.
- Tells the buyer to verify credentials: 27.5% on average (ChatGPT 52.5%, Claude 17.5%, Gemini 12.5%) — a 40-point spread.
- Warns about red flags or scams: 20.8% on average (ChatGPT 37.5%, Claude 22.5%, Gemini 2.5%) — a 35-point spread.
- Mentions local proximity: 15% on average (ChatGPT 20%, Claude 15%, Gemini 10%) — a 10-point spread.
- Suggests a DIY approach first: 7.5% on average (ChatGPT 15%, Claude 7.5%, Gemini 0%) — a 15-point spread.
- Tells the buyer to check reviews: 5% on average (ChatGPT 10%, Claude 5%, Gemini 0%) — a 10-point spread.
- Names a specific provider: 2.5% on average (ChatGPT 2.5%, Claude 2.5%, Gemini 2.5%).
- Gives price or cost information: 2.5% on average (ChatGPT 2.5%, Claude 2.5%, Gemini 2.5%).
- Recommends multiple quotes: 1.7% on average (ChatGPT 5%, Claude 0%, Gemini 0%) — a 5-point spread.
- Mentions case studies or portfolio: 0% on average (ChatGPT 0%, Claude 0%, Gemini 0%).
Trust signals
How well the models protect the osteopaths buyer.
Beyond whether to hire, the rubric codes how carefully each assistant protects the osteopaths 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 27.5%. Warning about red flags or scams appeared in 20.8%.
On structuring the decision, a selection-criteria checklist showed up in 38.3% of answers on average and a recommendation to gather multiple quotes in 1.7%. The single least-reproduced protective signal for osteopaths is "recommends multiple quotes" at 1.7% 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 Osteopaths providers?
For service providers the decisive question is whether these systems name anyone at all. Across 120 osteopaths answers, a specific provider was named in 2.5% 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 osteopaths: visibility comes from being the reasoning a model reproduces, not from being the named recommendation.
The question set
What these 40 Osteopaths questions cover.
The 40 questions behind every percentage on this page were drawn from real osteopaths (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 osteopaths 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 40 answers in which the behavior appeared at least once — not a confidence score. Because each model answered every question exactly once on 2026-07-06, the figures describe this specific osteopaths 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 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 2026-07-06, 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 →