AI SEO Statistics: Dry Cleaning (2026-07 edition)
38 questions · 114/114 expected AI responses · 3 models · measured 2026-07-06
Apply these findings to your dry cleaning 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 dry cleaning.
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 38 questions
Model by model
17.4% 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 38 dry cleaning benchmark questions, 2026-07 edition. Last column: equal-model mean.
| Behavior | ChatGPT | Claude | Gemini | Equal-model mean |
|---|---|---|---|---|
| Recommends hiring a professional | 73.7% | 65.8% | 60.5% | 66.7% |
| Suggests DIY first | 39.5% | 31.6% | 23.7% | 31.6% |
| Names specific providers | 2.6% | 7.9% | 15.8% | 8.8% |
| Gives price or cost info | 21.1% | 10.5% | 26.3% | 19.3% |
| Tells to check reviews | 13.2% | 13.2% | 2.6% | 9.7% |
| Tells to verify credentials | 13.2% | 10.5% | 7.9% | 10.5% |
| Mentions case studies / portfolio | 13.2% | 2.6% | 0% | 5.3% |
| Mentions local proximity | 36.8% | 31.6% | 28.9% | 32.4% |
| Gives selection criteria | 44.7% | 42.1% | 28.9% | 38.6% |
| Warns about red flags | 10.5% | 15.8% | 15.8% | 14% |
| Asks a clarifying question | 55.3% | 50% | 2.6% | 36% |
| Recommends multiple quotes | 10.5% | 7.9% | 0% | 6.1% |
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 38 benchmark questions.
| Behavior | All-model agreement |
|---|---|
| Recommends hiring a professional | 76.3% |
| Suggests DIY first | 71.1% |
| Names specific providers | 86.8% |
| Gives price or cost info | 73.7% |
| Tells to check reviews | 81.6% |
| Tells to verify credentials | 81.6% |
| Mentions case studies / portfolio | 86.8% |
| Mentions local proximity | 68.4% |
| Gives selection criteria | 63.2% |
| Warns about red flags | 81.6% |
| Asks a clarifying question | 31.6% |
| Recommends multiple quotes | 84.2% |
By model
How each assistant handled Dry Cleaning questions.
Reading the 114 answers model by model shows how differently the three assistants treat the same dry cleaning questions. On the most consequential behavior, whether to send the buyer to a professional at all, the rate ranged from 73.7% (ChatGPT) down to 60.5% (Gemini), a 13-point gap on an identical question set.
Across the 38 dry cleaning answers it produced, ChatGPT recommended hiring a professional in 73.7% of them and suggested a DIY approach first 39.5% of the time. It named a specific provider in 2.6% of answers (about 0.1 distinct providers per answer) and included price or cost information 21.1% of the time. ChatGPT asked a clarifying question before answering in 55.3% of cases, warned about red flags or scams in 10.5%, and told the buyer to verify credentials in 13.2%, averaging 385 words per answer. On the remaining cues it told the buyer to check reviews in 13.2%, pointed to case studies or a portfolio in 13.2%, and framed the choice around local proximity in 36.8%; a selection-criteria checklist appeared in 44.7% of its answers and a recommendation to gather multiple quotes in 10.5%.
Across the 38 dry cleaning answers it produced, Claude recommended hiring a professional in 65.8% of them and suggested a DIY approach first 31.6% of the time. It named a specific provider in 7.9% of answers (about 0.2 distinct providers per answer) and included price or cost information 10.5% of the time. Claude asked a clarifying question before answering in 50% of cases, warned about red flags or scams in 15.8%, and told the buyer to verify credentials in 10.5%, averaging 261 words per answer. On the remaining cues it told the buyer to check reviews in 13.2%, pointed to case studies or a portfolio in 2.6%, and framed the choice around local proximity in 31.6%; a selection-criteria checklist appeared in 42.1% of its answers and a recommendation to gather multiple quotes in 7.9%.
Across the 38 dry cleaning answers it produced, Gemini recommended hiring a professional in 60.5% of them and suggested a DIY approach first 23.7% of the time. It named a specific provider in 15.8% of answers (about 0.4 distinct providers per answer) and included price or cost information 26.3% of the time. Gemini asked a clarifying question before answering in 2.6% of cases, warned about red flags or scams in 15.8%, and told the buyer to verify credentials in 7.9%, averaging 294 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 28.9%; a selection-criteria checklist appeared in 28.9% 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 dry cleaning toward professional help (73.7%) and Gemini the least (60.5%). ChatGPT produced the longest answers, at 385 words on average. Specific providers were named most often by Gemini (15.8%). Even there, roughly one answer in 6 carried a name.
Where they disagree
The behaviors where the choice of model changes the answer.
Question-level model disagreement is 17.4%. 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 dry cleaning:
- Asks a clarifying question: from 2.6% (Gemini) to 55.3% (ChatGPT). The spread is 53 points.
- Suggests a DIY approach first: from 23.7% (Gemini) to 39.5% (ChatGPT). The spread is 16 points.
- Gives price or cost information: from 10.5% (Claude) to 26.3% (Gemini). The spread is 16 points.
- Gives selection criteria: from 28.9% (Gemini) to 44.7% (ChatGPT). The spread is 16 points.
- Recommends hiring a professional: from 60.5% (Gemini) to 73.7% (ChatGPT). The spread is 13 points.
The widest single gap concerns asks a clarifying question at 53 points. This means a buyer researching dry cleaning 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 dry cleaning market.
Where they agree
The points of near-consensus in Dry Cleaning.
On other behaviors the three models move almost in lockstep. The points of near-consensus for dry cleaning, where all three landed within a few points of each other:
- Tells the buyer to verify credentials: 7.9%–13.2% across all three (a 5-point spread).
- Warns about red flags or scams: 10.5%–15.8% across all three (a 5-point spread).
- Mentions local proximity: 28.9%–36.8% across all three (a 8-point spread).
- Recommends multiple quotes: 0%–10.5% across all three (a 11-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 86.8% of questions) and least consistently on "asks a clarifying question" (31.6%).
Every behavior, measured
All twelve coded behaviors for Dry Cleaning, averaged across the three models.
The behaviors AI models reproduce most often for dry cleaning are recommends hiring a professional (66.7% on average), gives selection criteria (38.6%) and asks a clarifying question (36%); the rarest are mentions case studies or portfolio (5.3%), recommends multiple quotes (6.1%) and names a specific provider (8.8%). 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:
- Recommends hiring a professional: 66.7% on average (ChatGPT 73.7%, Claude 65.8%, Gemini 60.5%). The spread is 13 points.
- Gives selection criteria: 38.6% on average (ChatGPT 44.7%, Claude 42.1%, Gemini 28.9%). The spread is 16 points.
- Asks a clarifying question: 36% on average (ChatGPT 55.3%, Claude 50%, Gemini 2.6%). The spread is 53 points.
- Mentions local proximity: 32.4% on average (ChatGPT 36.8%, Claude 31.6%, Gemini 28.9%). The spread is 8 points.
- Suggests a DIY approach first: 31.6% on average (ChatGPT 39.5%, Claude 31.6%, Gemini 23.7%). The spread is 16 points.
- Gives price or cost information: 19.3% on average (ChatGPT 21.1%, Claude 10.5%, Gemini 26.3%). The spread is 16 points.
- Warns about red flags or scams: 14% on average (ChatGPT 10.5%, Claude 15.8%, Gemini 15.8%). The spread is 5 points.
- Tells the buyer to verify credentials: 10.5% on average (ChatGPT 13.2%, Claude 10.5%, Gemini 7.9%). The spread is 5 points.
- Tells the buyer to check reviews: 9.7% on average (ChatGPT 13.2%, Claude 13.2%, Gemini 2.6%). The spread is 11 points.
- Names a specific provider: 8.8% on average (ChatGPT 2.6%, Claude 7.9%, Gemini 15.8%). The spread is 13 points.
- Recommends multiple quotes: 6.1% on average (ChatGPT 10.5%, Claude 7.9%, Gemini 0%). The spread is 11 points.
- Mentions case studies or portfolio: 5.3% on average (ChatGPT 13.2%, Claude 2.6%, Gemini 0%). The spread is 13 points.
Trust signals
How well the models protect the dry cleaning buyer.
Beyond whether to hire, the rubric codes how carefully each assistant protects the dry cleaning buyer once a decision is made. Telling the buyer to check reviews or ratings appeared in 9.7% of answers on average. Verifying credentials or certifications appeared in 10.5%. Warning about red flags or scams appeared in 14%.
On structuring the decision, a selection-criteria checklist showed up in 38.6% of answers on average and a recommendation to gather multiple quotes in 6.1%. The single least-reproduced protective signal for dry cleaning is "recommends multiple quotes" at 6.1% 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 Dry Cleaning providers?
For service providers the decisive question is whether these systems name anyone at all. Across 114 dry cleaning answers, a specific provider was named in 8.8% of responses on average, or roughly 0.2 distinct providers per answer. In practice the assistants behave far more as an explanatory layer than as a referral engine for dry cleaning: visibility comes from being the reasoning a model reproduces, not from being the named recommendation.
The question set
What these 38 Dry Cleaning questions cover.
The 38 questions behind every percentage on this page form a frozen dry cleaning (home 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 dry cleaning 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 38 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 dry cleaning 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 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: Dry Cleaning (2026-07 edition).” AuthoritySpecialist.com. https://authorityspecialist.com/research/ai-seo-statistics/services/home/dry-cleaning