Original research · 2026-07 edition

AI SEO Statistics: Gas Engineers (2026-07 edition)

40 questions · 120/120 expected AI responses · 3 models · measured 2026-07-06

From research to execution

Apply these findings to your gas engineers 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 gas engineers.

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.

Why is my boiler making a loud banging noise every time the heating turns on?
Is it safe to try and relight a pilot light myself or should I call a professional?
How much does a standard annual boiler service cost on average?
What is the difference between a Gas Safe registered engineer and a general plumber?
My radiators are cold at the bottom but hot at the top, do I need an engineer for that?
Can a gas engineer install a smart thermostat or do I need an electrician for that?
What specific questions should I ask a gas engineer before they start a boiler installation?
How do I verify if a gas engineer's ID card is actually valid and current?
Show all 40 questions
Is it worth repairing a 12-year-old boiler or should I just invest in a new one?
What are the physical signs of a carbon monoxide leak I should look out for in my home?
How much extra should I expect to pay for an emergency gas engineer on a Sunday night?
Do gas engineers usually charge a call-out fee just to give me a quote?
My boiler keeps losing pressure every few days, what could be causing the leak?
How much work is involved in moving a boiler from the kitchen to an upstairs cupboard?
What exactly is included in a gas safety certificate for a rental property?
Why does my hot water work perfectly but the central heating won't come on at all?
How long does a typical combi boiler installation take from start to finish?
Are there any current government grants available for replacing an old gas boiler?
What should I do immediately if I smell a faint scent of gas near my meter?
Is it legal to use a gas engineer who isn't on the official register if they have great reviews?
How often should a gas fireplace be serviced to ensure it's venting properly?
What are the major red flags to watch for when a gas engineer is giving me a quote?
My boiler is showing a low pressure error code, is this something I can fix myself?
Why is my gas bill suddenly so much higher even though we haven't changed our habits?
Can a gas engineer also fix a leaking water pipe under my kitchen sink?
What does it mean if a gas engineer says they need to cap off my supply for safety?
Should I get a power flush for my radiators before installing a brand new boiler?
How can I tell if my gas hob was installed correctly and isn't leaking slowly?
What is the typical hourly rate for a heating engineer in a major city?
Is a fixed-price repair deal better than paying an hourly rate for a complex boiler fix?
Can I install a gas cooker myself if I buy the correct flexible hose from a DIY store?
Why is there black soot appearing around the edges of my gas water heater?
What is the best type of boiler for a large house with four bathrooms?
Do I need a specific type of engineer to work on LPG tanks versus standard mains gas?
How can I tell if my boiler's heat exchanger is cracked without taking it apart?
Will a gas engineer provide the replacement parts or should I order them online myself?
What official documentation should I receive after a new boiler has been installed?
My condensate pipe is frozen in the winter, how do I thaw it safely without a call-out?
Can a gas engineer help me balance the flow in an underfloor heating system?
How do I find a local specialist who knows how to service older back boilers safely?

Model by model

19.9% 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 matrixModel-by-model evidence
Measured

Behavior prevalence across 40 gas engineers benchmark questions, 2026-07 edition. Last column: equal-model mean.

Behavior prevalence across 40 gas engineers benchmark questions, 2026-07 edition. Last column: equal-model mean.
BehaviorChatGPTClaudeGeminiEqual-model mean
Recommends hiring a professional90%90%65%81.7%
Suggests DIY first25%25%22.5%24.2%
Names specific providers0%5%12.5%5.8%
Gives price or cost info17.5%15%15%15.8%
Tells to check reviews17.5%5%0%7.5%
Tells to verify credentials62.5%55%40%52.5%
Mentions case studies / portfolio5%5%0%3.3%
Mentions local proximity32.5%12.5%12.5%19.2%
Gives selection criteria45%35%20%33.3%
Warns about red flags15%15%10%13.3%
Asks a clarifying question80%75%0%51.7%
Recommends multiple quotes15%12.5%0%9.2%

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.

Behavior matrixModel-by-model evidence
Measured

All-model binary agreement by behavior across 40 benchmark questions.

All-model binary agreement by behavior across 40 benchmark questions.
BehaviorAll-model agreement
Recommends hiring a professional60%
Suggests DIY first92.5%
Names specific providers85%
Gives price or cost info72.5%
Tells to check reviews82.5%
Tells to verify credentials60%
Mentions case studies / portfolio92.5%
Mentions local proximity67.5%
Gives selection criteria62.5%
Warns about red flags82.5%
Asks a clarifying question5%
Recommends multiple quotes80%

By model

How each assistant handled Gas Engineers questions.

Reading the 120 answers model by model shows how differently the three assistants treat the same gas engineers questions. On the most consequential behavior, whether to send the buyer to a professional at all, the rate ranged from 90% (ChatGPT) down to 65% (Gemini), a 25-point gap on an identical question set.

Across the 40 gas engineers answers it produced, ChatGPT recommended hiring a professional in 90% of them and suggested a DIY approach first 25% of the time. It named a specific provider in 0% of answers (about 0 distinct providers per answer) and included price or cost information 17.5% of the time. ChatGPT asked a clarifying question before answering in 80% of cases, warned about red flags or scams in 15%, and told the buyer to verify credentials in 62.5%, averaging 434 words per answer. On the remaining cues it told the buyer to check reviews in 17.5%, pointed to case studies or a portfolio in 5%, and framed the choice around local proximity in 32.5%; a selection-criteria checklist appeared in 45% of its answers and a recommendation to gather multiple quotes in 15%.

Across the 40 gas engineers answers it produced, Claude recommended hiring a professional in 90% of them and suggested a DIY approach first 25% of the time. It named a specific provider in 5% of answers (about 0.1 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 15%, and told the buyer to verify credentials in 55%, averaging 288 words per answer. On the remaining cues it told the buyer to check reviews in 5%, pointed to case studies or a portfolio in 5%, and framed the choice around local proximity in 12.5%; a selection-criteria checklist appeared in 35% of its answers and a recommendation to gather multiple quotes in 12.5%.

Across the 40 gas engineers answers it produced, Gemini recommended hiring a professional in 65% of them and suggested a DIY approach first 22.5% of the time. It named a specific provider in 12.5% of answers (about 0.3 distinct providers per answer) and included price or cost information 15% of the time. Gemini asked a clarifying question before answering in 0% of cases, warned about red flags or scams in 10%, and told the buyer to verify credentials in 40%, averaging 293 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 12.5%; a selection-criteria checklist appeared in 20% of its answers and a recommendation to gather multiple quotes in 0%.

Taken together, ChatGPT is the assistant most likely to route a gas engineers buyer to a professional (90%) and Gemini the least (65%). ChatGPT produced the longest answers, at 434 words on average. Specific providers were named most often by Gemini (12.5%). Even there, roughly one answer in 8 carried a name.

Where they disagree

The behaviors where the choice of model changes the answer.

Question-level model disagreement is 19.9%. 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 which assistant a gas engineers buyer happens to ask matters most:

  • Asks a clarifying question: from 0% (Gemini) to 80% (ChatGPT). The spread is 80 points.
  • Recommends hiring a professional: from 65% (Gemini) to 90% (ChatGPT). The spread is 25 points.
  • Gives selection criteria: from 20% (Gemini) to 45% (ChatGPT). The spread is 25 points.
  • Tells the buyer to verify credentials: from 40% (Gemini) to 62.5% (ChatGPT). The spread is 23 points.
  • Mentions local proximity: from 12.5% (Claude) to 32.5% (ChatGPT). The spread is 20 points.

The widest single gap concerns asks a clarifying question at 80 points. This means a gas engineers 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 gas engineers market.

Where they agree

The points of near-consensus in Gas Engineers.

On other behaviors the three models move almost in lockstep. The points of near-consensus for gas engineers, where all three landed within a few points of each other:

  • Suggests a DIY approach first: 22.5%–25% across all three (a 3-point spread).
  • Gives price or cost information: 15%–17.5% across all three (a 3-point spread).
  • Mentions case studies or portfolio: 0%–5% across all three (a 5-point spread).
  • Warns about red flags or scams: 10%–15% across all three (a 5-point spread).

Measured question by question, the three assistants coded a response the same way most consistently on "suggests a DIY approach first" (identical coding in 92.5% of questions) and least consistently on "asks a clarifying question" (5%).

Every behavior, measured

All twelve coded behaviors for Gas Engineers, averaged across the three models.

The behaviors AI models reproduce most often for gas engineers are recommends hiring a professional (81.7% on average), tells the buyer to verify credentials (52.5%) and asks a clarifying question (51.7%); the rarest are mentions case studies or portfolio (3.3%), names a specific provider (5.8%) and tells the buyer to check reviews (7.5%). 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: 81.7% on average (ChatGPT 90%, Claude 90%, Gemini 65%). The spread is 25 points.
  • Tells the buyer to verify credentials: 52.5% on average (ChatGPT 62.5%, Claude 55%, Gemini 40%). The spread is 23 points.
  • Asks a clarifying question: 51.7% on average (ChatGPT 80%, Claude 75%, Gemini 0%). The spread is 80 points.
  • Gives selection criteria: 33.3% on average (ChatGPT 45%, Claude 35%, Gemini 20%). The spread is 25 points.
  • Suggests a DIY approach first: 24.2% on average (ChatGPT 25%, Claude 25%, Gemini 22.5%). The spread is 3 points.
  • Mentions local proximity: 19.2% on average (ChatGPT 32.5%, Claude 12.5%, Gemini 12.5%). The spread is 20 points.
  • Gives price or cost information: 15.8% on average (ChatGPT 17.5%, Claude 15%, Gemini 15%). The spread is 3 points.
  • Warns about red flags or scams: 13.3% on average (ChatGPT 15%, Claude 15%, Gemini 10%). The spread is 5 points.
  • Recommends multiple quotes: 9.2% on average (ChatGPT 15%, Claude 12.5%, Gemini 0%). The spread is 15 points.
  • Tells the buyer to check reviews: 7.5% on average (ChatGPT 17.5%, Claude 5%, Gemini 0%). The spread is 18 points.
  • Names a specific provider: 5.8% on average (ChatGPT 0%, Claude 5%, Gemini 12.5%). The spread is 13 points.
  • Mentions case studies or portfolio: 3.3% on average (ChatGPT 5%, Claude 5%, Gemini 0%). The spread is 5 points.

Trust signals

How well the models protect the gas engineers buyer.

Beyond whether to hire, the rubric codes how carefully each assistant protects the gas engineers buyer once a decision is made. Telling the buyer to check reviews or ratings appeared in 7.5% of answers on average. Verifying credentials or certifications appeared in 52.5%. Warning about red flags or scams appeared in 13.3%.

On structuring the decision, a selection-criteria checklist showed up in 33.3% of answers on average and a recommendation to gather multiple quotes in 9.2%. The single least-reproduced protective signal for gas engineers is "tells the buyer to check reviews" at 7.5% 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 Gas Engineers providers?

For service providers the decisive question is whether these systems name anyone at all. Across 120 gas engineers answers, a specific provider was named in 5.8% of responses on average, or roughly 0.1 distinct providers per answer. In practice the assistants behave far more as an explanatory layer than as a referral engine for gas engineers: visibility comes from being the reasoning a model reproduces, not from being the named recommendation.

The question set

What these 40 Gas Engineers questions cover.

The 40 questions behind every percentage on this page form a frozen gas engineers (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 gas engineers 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 40 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 gas engineers 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 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: Gas Engineers (2026-07 edition).” AuthoritySpecialist.com. https://authorityspecialist.com/research/ai-seo-statistics/services/home/gas-engineers