AI SEO Statistics: ED Clinic (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 ed clinic.
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
21-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 ed clinic buyers.
| ChatGPT | Claude | Gemini | Consensus | |
|---|---|---|---|---|
| Recommends hiring a professional | 65% | 68% | 35% | 50% |
| Suggests DIY first | 20% | 5% | 13% | 83% |
| Names specific providers | 10% | 13% | 28% | 73% |
| Gives price or cost info | 5% | 15% | 18% | 83% |
| Tells to check reviews | 13% | 13% | 3% | 83% |
| Tells to verify credentials | 28% | 23% | 10% | 70% |
| Mentions case studies / portfolio | 0% | 0% | 0% | 100% |
| Mentions local proximity | 28% | 18% | 10% | 68% |
| Gives selection criteria | 38% | 40% | 25% | 63% |
| Warns about red flags | 25% | 30% | 10% | 58% |
| Asks a clarifying question | 73% | 75% | 5% | 13% |
| Recommends multiple quotes | 5% | 13% | 3% | 88% |
By model
How each assistant handled ED Clinic questions.
Reading the 120 answers model by model shows how differently the three assistants treat the same ed clinic questions. On the most consequential behavior — whether to send the buyer to a professional at all — the rate ranged from 67.5% (Claude) down to 35% (Gemini), a 33-point gap on an identical question set.
Across the 40 ed clinic answers it produced, ChatGPT recommended hiring a professional in 65% of them and suggested a DIY approach first 20% of the time. It named a specific provider in 10% of answers (about 0.3 distinct providers per answer) and included price or cost information 5% of the time. ChatGPT asked a clarifying question before answering in 72.5% of cases, warned about red flags or scams in 25%, and told the buyer to verify credentials in 27.5%, averaging 412 words per answer. On the remaining cues it told the buyer to check reviews in 12.5%, 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 37.5% of its answers and a recommendation to gather multiple quotes in 5%.
Across the 40 ed clinic answers it produced, Claude recommended hiring a professional in 67.5% of them and suggested a DIY approach first 5% of the time. It named a specific provider in 12.5% of answers (about 0.4 distinct providers per answer) and included price or cost information 15% of the time. Claude asked a clarifying question before answering in 75% of cases, warned about red flags or scams in 30%, and told the buyer to verify credentials in 22.5%, averaging 273 words per answer. On the remaining cues it told the buyer to check reviews in 12.5%, pointed to case studies or a portfolio in 0%, and framed the choice around local proximity in 17.5%; a selection-criteria checklist appeared in 40% of its answers and a recommendation to gather multiple quotes in 12.5%.
Across the 40 ed clinic answers it produced, Gemini recommended hiring a professional in 35% of them and suggested a DIY approach first 12.5% of the time. It named a specific provider in 27.5% of answers (about 1.2 distinct providers per answer) and included price or cost information 17.5% of the time. Gemini asked a clarifying question before answering in 5% of cases, warned about red flags or scams in 10%, and told the buyer to verify credentials in 10%, averaging 262 words per answer. On the remaining cues it told the buyer to check reviews in 2.5%, 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 2.5%.
Taken together, Claude is the assistant most likely to route an ed clinic buyer to a professional (67.5%) and Gemini the least (35%). ChatGPT produced the longest answers, at 412 words on average. Specific providers were named most often by Gemini (27.5%) — even there, roughly one answer in 4 carried a name.
Where they disagree
The behaviors where the choice of model changes the answer.
The divergence index for this study is 20.7 points — the average distance between the most and least likely model across the coded behaviors. The gaps below are where which assistant an ed clinic buyer happens to ask matters most:
- Asks a clarifying question: from 5% (Gemini) to 75% (Claude) — a 70-point spread.
- Recommends hiring a professional: from 35% (Gemini) to 67.5% (Claude) — a 33-point spread.
- Warns about red flags or scams: from 10% (Gemini) to 30% (Claude) — a 20-point spread.
- Names a specific provider: from 10% (ChatGPT) to 27.5% (Gemini) — a 18-point spread.
- Tells the buyer to verify credentials: from 10% (Gemini) to 27.5% (ChatGPT) — a 18-point spread.
The widest single gap — asks a clarifying question, 70 points — means an ed clinic 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 ed clinic market.
Where they agree
The points of near-consensus in ED Clinic.
On other behaviors the three models move almost in lockstep — the points of near-consensus for ed clinic, where all three landed within a few points of each other:
- Mentions case studies or portfolio: 0% across all three models.
- Tells the buyer to check reviews: 2.5%–12.5% across all three (a 10-point spread).
- Recommends multiple quotes: 2.5%–12.5% across all three (a 10-point spread).
- Gives price or cost information: 5%–17.5% across all three (a 13-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" (12.5%).
Every behavior, measured
All twelve coded behaviors for ED Clinic, averaged across the three models.
The behaviors AI models reproduce most often for ed clinic are recommends hiring a professional (55.8% on average), asks a clarifying question (50.8%) and gives selection criteria (34.2%); the rarest are mentions case studies or portfolio (0%), recommends multiple quotes (6.7%) and tells the buyer to check reviews (9.2%). 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: 55.8% on average (ChatGPT 65%, Claude 67.5%, Gemini 35%) — a 33-point spread.
- Asks a clarifying question: 50.8% on average (ChatGPT 72.5%, Claude 75%, Gemini 5%) — a 70-point spread.
- Gives selection criteria: 34.2% on average (ChatGPT 37.5%, Claude 40%, Gemini 25%) — a 15-point spread.
- Warns about red flags or scams: 21.7% on average (ChatGPT 25%, Claude 30%, Gemini 10%) — a 20-point spread.
- Tells the buyer to verify credentials: 20% on average (ChatGPT 27.5%, Claude 22.5%, Gemini 10%) — a 18-point spread.
- Mentions local proximity: 18.3% on average (ChatGPT 27.5%, Claude 17.5%, Gemini 10%) — a 18-point spread.
- Names a specific provider: 16.7% on average (ChatGPT 10%, Claude 12.5%, Gemini 27.5%) — a 18-point spread.
- Suggests a DIY approach first: 12.5% on average (ChatGPT 20%, Claude 5%, Gemini 12.5%) — a 15-point spread.
- Gives price or cost information: 12.5% on average (ChatGPT 5%, Claude 15%, Gemini 17.5%) — a 13-point spread.
- Tells the buyer to check reviews: 9.2% on average (ChatGPT 12.5%, Claude 12.5%, Gemini 2.5%) — a 10-point spread.
- Recommends multiple quotes: 6.7% on average (ChatGPT 5%, Claude 12.5%, Gemini 2.5%) — a 10-point spread.
- Mentions case studies or portfolio: 0% on average (ChatGPT 0%, Claude 0%, Gemini 0%).
Trust signals
How well the models protect the ed clinic buyer.
Beyond whether to hire, the rubric codes how carefully each assistant protects the ed clinic buyer once a decision is made. Telling the buyer to check reviews or ratings appeared in 9.2% of answers on average. Verifying credentials or certifications appeared in 20%. Warning about red flags or scams appeared in 21.7%.
On structuring the decision, a selection-criteria checklist showed up in 34.2% of answers on average and a recommendation to gather multiple quotes in 6.7%. The single least-reproduced protective signal for ed clinic is "recommends multiple quotes" at 6.7% 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 ED Clinic providers?
For service providers the decisive question is whether these systems name anyone at all. Across 120 ed clinic answers, a specific provider was named in 16.7% of responses on average — roughly 0.6 distinct providers per answer. In practice the assistants behave far more as an explanatory layer than as a referral engine for ed clinic: visibility comes from being the reasoning a model reproduces, not from being the named recommendation.
The question set
What these 40 ED Clinic questions cover.
The 40 questions behind every percentage on this page were drawn from real ed clinic (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 ed clinic 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 ed clinic 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 →