AI SEO Statistics: Dog Boarding (2026-07 edition)
38 questions · 114 AI responses · 3 models · measured 2026-07-06
The question bank
The questions we tested — sampled from real buyer journeys in dog boarding.
Each model answered every question once, same wording, same day. These are the prompts behind every percentage on this page.
Show all 38 questions
Model by model
23-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 dog boarding buyers.
| ChatGPT | Claude | Gemini | Consensus | |
|---|---|---|---|---|
| Recommends hiring a professional | 53% | 66% | 40% | 68% |
| Suggests DIY first | 8% | 8% | 3% | 92% |
| Names specific providers | 13% | 45% | 42% | 53% |
| Gives price or cost info | 13% | 18% | 18% | 87% |
| Tells to check reviews | 29% | 29% | 3% | 53% |
| Tells to verify credentials | 34% | 18% | 11% | 55% |
| Mentions case studies / portfolio | 0% | 0% | 0% | 100% |
| Mentions local proximity | 37% | 29% | 16% | 66% |
| Gives selection criteria | 47% | 68% | 50% | 34% |
| Warns about red flags | 18% | 26% | 8% | 71% |
| Asks a clarifying question | 55% | 63% | 0% | 18% |
| Recommends multiple quotes | 5% | 13% | 0% | 87% |
By model
How each assistant handled Dog Boarding questions.
Reading the 114 answers model by model shows how differently the three assistants treat the same dog boarding questions. On the most consequential behavior — whether to send the buyer to a professional at all — the rate ranged from 65.8% (Claude) down to 39.5% (Gemini), a 26-point gap on an identical question set.
Across the 38 dog boarding answers it produced, ChatGPT recommended hiring a professional in 52.6% of them and suggested a DIY approach first 7.9% of the time. It named a specific provider in 13.2% of answers (about 0.4 distinct providers per answer) and included price or cost information 13.2% of the time. ChatGPT asked a clarifying question before answering in 55.3% of cases, warned about red flags or scams in 18.4%, and told the buyer to verify credentials in 34.2%, averaging 467 words per answer. On the remaining cues it told the buyer to check reviews in 28.9%, pointed to case studies or a portfolio in 0%, and framed the choice around local proximity in 36.8%; a selection-criteria checklist appeared in 47.4% of its answers and a recommendation to gather multiple quotes in 5.3%.
Across the 38 dog boarding answers it produced, Claude recommended hiring a professional in 65.8% of them and suggested a DIY approach first 7.9% of the time. It named a specific provider in 44.7% of answers (about 0.9 distinct providers per answer) and included price or cost information 18.4% of the time. Claude asked a clarifying question before answering in 63.2% of cases, warned about red flags or scams in 26.3%, and told the buyer to verify credentials in 18.4%, averaging 279 words per answer. On the remaining cues it told the buyer to check reviews in 28.9%, pointed to case studies or a portfolio in 0%, and framed the choice around local proximity in 28.9%; a selection-criteria checklist appeared in 68.4% of its answers and a recommendation to gather multiple quotes in 13.2%.
Across the 38 dog boarding answers it produced, Gemini recommended hiring a professional in 39.5% of them and suggested a DIY approach first 2.6% of the time. It named a specific provider in 42.1% of answers (about 0.9 distinct providers per answer) and included price or cost information 18.4% of the time. Gemini asked a clarifying question before answering in 0% of cases, warned about red flags or scams in 7.9%, and told the buyer to verify credentials in 10.5%, averaging 296 words per answer. On the remaining cues it told the buyer to check reviews in 2.6%, pointed to case studies or a portfolio in 0%, and framed the choice around local proximity in 15.8%; a selection-criteria checklist appeared in 50% of its answers and a recommendation to gather multiple quotes in 0%.
Taken together, Claude is the assistant most likely to route a dog boarding buyer to a professional (65.8%) and Gemini the least (39.5%). ChatGPT produced the longest answers, at 467 words on average. Specific providers were named most often by Claude (44.7%) — even there, roughly one answer in 2 carried a name.
Where they disagree
The behaviors where the choice of model changes the answer.
The divergence index for this study is 23.1 points — the average distance between the most and least likely model across the coded behaviors. The gaps below are where which assistant a dog boarding buyer happens to ask matters most:
- Asks a clarifying question: from 0% (Gemini) to 63.2% (Claude) — a 63-point spread.
- Names a specific provider: from 13.2% (ChatGPT) to 44.7% (Claude) — a 32-point spread.
- Recommends hiring a professional: from 39.5% (Gemini) to 65.8% (Claude) — a 26-point spread.
- Tells the buyer to check reviews: from 2.6% (Gemini) to 28.9% (ChatGPT) — a 26-point spread.
- Tells the buyer to verify credentials: from 10.5% (Gemini) to 34.2% (ChatGPT) — a 24-point spread.
The widest single gap — asks a clarifying question, 63 points — means a dog boarding 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 dog boarding market.
Where they agree
The points of near-consensus in Dog Boarding.
On other behaviors the three models move almost in lockstep — the points of near-consensus for dog boarding, where all three landed within a few points of each other:
- Mentions case studies or portfolio: 0% across all three models.
- Gives price or cost information: 13.2%–18.4% across all three (a 5-point spread).
- Suggests a DIY approach first: 2.6%–7.9% across all three (a 5-point spread).
- Recommends multiple quotes: 0%–13.2% 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" (18.4%).
Every behavior, measured
All twelve coded behaviors for Dog Boarding, averaged across the three models.
The behaviors AI models reproduce most often for dog boarding are gives selection criteria (55.3% on average), recommends hiring a professional (52.6%) and asks a clarifying question (39.5%); the rarest are mentions case studies or portfolio (0%), suggests a DIY approach first (6.1%) and recommends multiple quotes (6.2%). Each figure below is the share of a model's 38 answers in which the behavior appeared at least once, averaged across the 3 models with the full per-model range in parentheses:
- Gives selection criteria: 55.3% on average (ChatGPT 47.4%, Claude 68.4%, Gemini 50%) — a 21-point spread.
- Recommends hiring a professional: 52.6% on average (ChatGPT 52.6%, Claude 65.8%, Gemini 39.5%) — a 26-point spread.
- Asks a clarifying question: 39.5% on average (ChatGPT 55.3%, Claude 63.2%, Gemini 0%) — a 63-point spread.
- Names a specific provider: 33.3% on average (ChatGPT 13.2%, Claude 44.7%, Gemini 42.1%) — a 32-point spread.
- Mentions local proximity: 27.2% on average (ChatGPT 36.8%, Claude 28.9%, Gemini 15.8%) — a 21-point spread.
- Tells the buyer to verify credentials: 21% on average (ChatGPT 34.2%, Claude 18.4%, Gemini 10.5%) — a 24-point spread.
- Tells the buyer to check reviews: 20.1% on average (ChatGPT 28.9%, Claude 28.9%, Gemini 2.6%) — a 26-point spread.
- Warns about red flags or scams: 17.5% on average (ChatGPT 18.4%, Claude 26.3%, Gemini 7.9%) — a 18-point spread.
- Gives price or cost information: 16.7% on average (ChatGPT 13.2%, Claude 18.4%, Gemini 18.4%) — a 5-point spread.
- Recommends multiple quotes: 6.2% on average (ChatGPT 5.3%, Claude 13.2%, Gemini 0%) — a 13-point spread.
- Suggests a DIY approach first: 6.1% on average (ChatGPT 7.9%, Claude 7.9%, Gemini 2.6%) — 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 dog boarding buyer.
Beyond whether to hire, the rubric codes how carefully each assistant protects the dog boarding buyer once a decision is made. Telling the buyer to check reviews or ratings appeared in 20.1% of answers on average. Verifying credentials or certifications appeared in 21%. Warning about red flags or scams appeared in 17.5%.
On structuring the decision, a selection-criteria checklist showed up in 55.3% of answers on average and a recommendation to gather multiple quotes in 6.2%. The single least-reproduced protective signal for dog boarding is "recommends multiple quotes" at 6.2% 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 Dog Boarding providers?
For service providers the decisive question is whether these systems name anyone at all. Across 114 dog boarding answers, a specific provider was named in 33.3% of responses on average — roughly 0.7 distinct providers per answer. In practice the assistants behave far more as an explanatory layer than as a referral engine for dog boarding: visibility comes from being the reasoning a model reproduces, not from being the named recommendation.
The question set
What these 38 Dog Boarding questions cover.
The 38 questions behind every percentage on this page were drawn from real dog boarding (home 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 dog boarding 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 38 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 dog boarding 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.
38 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 →