AI SEO Statistics: Obgyn (2026-07 edition)
36 questions · 108 AI responses · 3 models · measured 2026-07-06
The question bank
The questions we tested — sampled from real buyer journeys in obgyn.
Each model answered every question once, same wording, same day. These are the prompts behind every percentage on this page.
Show all 36 questions
Model by model
20-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 obgyn buyers.
| ChatGPT | Claude | Gemini | Consensus | |
|---|---|---|---|---|
| Recommends hiring a professional | 58% | 56% | 47% | 64% |
| Suggests DIY first | 28% | 22% | 14% | 75% |
| Names specific providers | 8% | 17% | 17% | 83% |
| Gives price or cost info | 8% | 11% | 17% | 92% |
| Tells to check reviews | 19% | 31% | 8% | 67% |
| Tells to verify credentials | 11% | 8% | 17% | 78% |
| Mentions case studies / portfolio | 0% | 0% | 0% | 100% |
| Mentions local proximity | 39% | 36% | 11% | 53% |
| Gives selection criteria | 47% | 61% | 31% | 47% |
| Warns about red flags | 25% | 19% | 8% | 69% |
| Asks a clarifying question | 69% | 67% | 3% | 11% |
| Recommends multiple quotes | 3% | 6% | 0% | 94% |
By model
How each assistant handled Obgyn questions.
Reading the 108 answers model by model shows how differently the three assistants treat the same obgyn questions. On the most consequential behavior — whether to send the buyer to a professional at all — the rate ranged from 58.3% (ChatGPT) down to 47.2% (Gemini), a 11-point gap on an identical question set.
Across the 36 obgyn answers it produced, ChatGPT recommended hiring a professional in 58.3% of them and suggested a DIY approach first 27.8% of the time. It named a specific provider in 8.3% of answers (about 0.3 distinct providers per answer) and included price or cost information 8.3% of the time. ChatGPT asked a clarifying question before answering in 69.4% of cases, warned about red flags or scams in 25%, and told the buyer to verify credentials in 11.1%, averaging 495 words per answer. On the remaining cues it told the buyer to check reviews in 19.4%, pointed to case studies or a portfolio in 0%, and framed the choice around local proximity in 38.9%; a selection-criteria checklist appeared in 47.2% of its answers and a recommendation to gather multiple quotes in 2.8%.
Across the 36 obgyn answers it produced, Claude recommended hiring a professional in 55.6% of them and suggested a DIY approach first 22.2% of the time. It named a specific provider in 16.7% of answers (about 0.6 distinct providers per answer) and included price or cost information 11.1% of the time. Claude asked a clarifying question before answering in 66.7% of cases, warned about red flags or scams in 19.4%, and told the buyer to verify credentials in 8.3%, averaging 286 words per answer. On the remaining cues it told the buyer to check reviews in 30.6%, pointed to case studies or a portfolio in 0%, and framed the choice around local proximity in 36.1%; a selection-criteria checklist appeared in 61.1% of its answers and a recommendation to gather multiple quotes in 5.6%.
Across the 36 obgyn answers it produced, Gemini recommended hiring a professional in 47.2% of them and suggested a DIY approach first 13.9% of the time. It named a specific provider in 16.7% of answers (about 0.4 distinct providers per answer) and included price or cost information 16.7% of the time. Gemini asked a clarifying question before answering in 2.8% of cases, warned about red flags or scams in 8.3%, and told the buyer to verify credentials in 16.7%, averaging 276 words per answer. On the remaining cues it told the buyer to check reviews in 8.3%, pointed to case studies or a portfolio in 0%, and framed the choice around local proximity in 11.1%; a selection-criteria checklist appeared in 30.6% of its answers and a recommendation to gather multiple quotes in 0%.
Taken together, ChatGPT is the assistant most likely to route an obgyn buyer to a professional (58.3%) and Gemini the least (47.2%). ChatGPT produced the longest answers, at 495 words on average. Specific providers were named most often by Claude (16.7%) — even there, roughly one answer in 6 carried a name.
Where they disagree
The behaviors where the choice of model changes the answer.
The divergence index for this study is 20.4 points — the average distance between the most and least likely model across the coded behaviors. The gaps below are where which assistant an obgyn buyer happens to ask matters most:
- Asks a clarifying question: from 2.8% (Gemini) to 69.4% (ChatGPT) — a 67-point spread.
- Gives selection criteria: from 30.6% (Gemini) to 61.1% (Claude) — a 31-point spread.
- Mentions local proximity: from 11.1% (Gemini) to 38.9% (ChatGPT) — a 28-point spread.
- Tells the buyer to check reviews: from 8.3% (Gemini) to 30.6% (Claude) — a 22-point spread.
- Warns about red flags or scams: from 8.3% (Gemini) to 25% (ChatGPT) — a 17-point spread.
The widest single gap — asks a clarifying question, 67 points — means an obgyn 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 obgyn market.
Where they agree
The points of near-consensus in Obgyn.
On other behaviors the three models move almost in lockstep — the points of near-consensus for obgyn, 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%–5.6% across all three (a 6-point spread).
- Names a specific provider: 8.3%–16.7% across all three (a 8-point spread).
- Gives price or cost information: 8.3%–16.7% across all three (a 8-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" (11.1%).
Every behavior, measured
All twelve coded behaviors for Obgyn, averaged across the three models.
The behaviors AI models reproduce most often for obgyn are recommends hiring a professional (53.7% on average), gives selection criteria (46.3%) and asks a clarifying question (46.3%); the rarest are mentions case studies or portfolio (0%), recommends multiple quotes (2.8%) and tells the buyer to verify credentials (12%). Each figure below is the share of a model's 36 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: 53.7% on average (ChatGPT 58.3%, Claude 55.6%, Gemini 47.2%) — a 11-point spread.
- Gives selection criteria: 46.3% on average (ChatGPT 47.2%, Claude 61.1%, Gemini 30.6%) — a 31-point spread.
- Asks a clarifying question: 46.3% on average (ChatGPT 69.4%, Claude 66.7%, Gemini 2.8%) — a 67-point spread.
- Mentions local proximity: 28.7% on average (ChatGPT 38.9%, Claude 36.1%, Gemini 11.1%) — a 28-point spread.
- Suggests a DIY approach first: 21.3% on average (ChatGPT 27.8%, Claude 22.2%, Gemini 13.9%) — a 14-point spread.
- Tells the buyer to check reviews: 19.4% on average (ChatGPT 19.4%, Claude 30.6%, Gemini 8.3%) — a 22-point spread.
- Warns about red flags or scams: 17.6% on average (ChatGPT 25%, Claude 19.4%, Gemini 8.3%) — a 17-point spread.
- Names a specific provider: 13.9% on average (ChatGPT 8.3%, Claude 16.7%, Gemini 16.7%) — a 8-point spread.
- Gives price or cost information: 12% on average (ChatGPT 8.3%, Claude 11.1%, Gemini 16.7%) — a 8-point spread.
- Tells the buyer to verify credentials: 12% on average (ChatGPT 11.1%, Claude 8.3%, Gemini 16.7%) — a 8-point spread.
- Recommends multiple quotes: 2.8% on average (ChatGPT 2.8%, Claude 5.6%, Gemini 0%) — a 6-point spread.
- Mentions case studies or portfolio: 0% on average (ChatGPT 0%, Claude 0%, Gemini 0%).
Trust signals
How well the models protect the obgyn buyer.
Beyond whether to hire, the rubric codes how carefully each assistant protects the obgyn buyer once a decision is made. Telling the buyer to check reviews or ratings appeared in 19.4% of answers on average. Verifying credentials or certifications appeared in 12%. Warning about red flags or scams appeared in 17.6%.
On structuring the decision, a selection-criteria checklist showed up in 46.3% of answers on average and a recommendation to gather multiple quotes in 2.8%. The single least-reproduced protective signal for obgyn is "recommends multiple quotes" at 2.8% 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 Obgyn providers?
For service providers the decisive question is whether these systems name anyone at all. Across 108 obgyn answers, a specific provider was named in 13.9% of responses on average — roughly 0.4 distinct providers per answer. In practice the assistants behave far more as an explanatory layer than as a referral engine for obgyn: visibility comes from being the reasoning a model reproduces, not from being the named recommendation.
The question set
What these 36 Obgyn questions cover.
The 36 questions behind every percentage on this page were drawn from real obgyn (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 obgyn 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 36 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 obgyn 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.
36 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 →