Original research · 2026-07 edition

AI SEO Statistics: Carpenter (2026-07 edition)

15 questions · 45 AI responses · 3 models · measured 2026-07-04

See how AI talks about YOUR businessFull data table

The question bank

The questions we tested — sampled from real buyer journeys in carpenter.

Each model answered every question once, same wording, same day. These are the prompts behind every percentage on this page.

My kitchen cabinet hinges are pulling out of the particle board, can a carpenter actually fix that or do I need to buy new doors?
What is the average hourly rate for a finish carpenter in a mid-sized city right now?
I want to add a window seat with storage under a bay window, what kind of budget should I set aside for labor and materials?
Is it cheaper to buy pre-made stairs from a big box store or have a carpenter build custom ones for a basement renovation?
How can I verify if a carpenter is properly licensed and insured before they start working on a load-bearing wall?
The wood on my porch railing is starting to feel soft and spongy, is that something a carpenter can patch or does the whole thing need replacing?
What specific questions should I ask to make sure a carpenter has actual experience with historical home restoration?
I'm trying to decide between MDF and solid wood for some built-in bookshelves, which one is better for a house in a humid climate?
Show all 15 questions
Do carpenters usually charge by the project or by the hour for small repairs like fixing a squeaky floor or a sticking door?
Can a carpenter help me design a custom mudroom bench from scratch or do I need to have professional blueprints ready first?
What are some common red flags to look for in a contract for a large-scale custom woodworking project?
How much extra should I expect to pay for finish-grade lumber versus standard construction-grade timber for an indoor project?
I need a carpenter to install intricate crown molding in a room with vaulted ceilings, is that a specialized skill I should pay more for?
Is it standard practice for a carpenter to ask for a 50% deposit upfront for a custom furniture piece?
How do I find a local carpenter who specializes specifically in outdoor structures like pergolas and custom gazebos?

Model by model

28-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 carpenter buyers.

Behavior rates across 15 carpenter buyer questions, 2026-07 edition. Last column: average across models.
ChatGPTClaudeGeminiConsensus
Recommends hiring a professional73%67%40%60%
Suggests DIY first0%13%7%80%
Names specific providers0%0%7%93%
Gives price or cost info40%47%40%53%
Tells to check reviews27%13%0%73%
Tells to verify credentials33%20%13%53%
Mentions case studies / portfolio33%33%13%53%
Mentions local proximity53%40%13%47%
Gives selection criteria67%60%33%27%
Warns about red flags27%20%27%67%
Asks a clarifying question47%47%0%33%
Recommends multiple quotes33%27%0%60%

By model

How each assistant handled Carpenter questions.

Reading the 45 answers model by model shows how differently the three assistants treat the same carpenter questions. On the most consequential behavior — whether to send the buyer to a professional at all — the rate ranged from 73.3% (ChatGPT) down to 40% (Gemini), a 33-point gap on an identical question set.

Across the 15 carpenter answers it produced, ChatGPT recommended hiring a professional in 73.3% of them and suggested a DIY approach first 0% of the time. It named a specific provider in 0% of answers (about 0 distinct providers per answer) and included price or cost information 40% of the time. ChatGPT asked a clarifying question before answering in 46.7% of cases, warned about red flags or scams in 26.7%, and told the buyer to verify credentials in 33.3%, averaging 487 words per answer. On the remaining cues it told the buyer to check reviews in 26.7%, pointed to case studies or a portfolio in 33.3%, and framed the choice around local proximity in 53.3%; a selection-criteria checklist appeared in 66.7% of its answers and a recommendation to gather multiple quotes in 33.3%.

Across the 15 carpenter answers it produced, Claude recommended hiring a professional in 66.7% of them and suggested a DIY approach first 13.3% of the time. It named a specific provider in 0% of answers (about 0 distinct providers per answer) and included price or cost information 46.7% of the time. Claude asked a clarifying question before answering in 46.7% of cases, warned about red flags or scams in 20%, and told the buyer to verify credentials in 20%, averaging 283 words per answer. On the remaining cues it told the buyer to check reviews in 13.3%, pointed to case studies or a portfolio in 33.3%, and framed the choice around local proximity in 40%; a selection-criteria checklist appeared in 60% of its answers and a recommendation to gather multiple quotes in 26.7%.

Across the 15 carpenter answers it produced, Gemini recommended hiring a professional in 40% of them and suggested a DIY approach first 6.7% of the time. It named a specific provider in 6.7% of answers (about 0.1 distinct providers per answer) and included price or cost information 40% of the time. Gemini asked a clarifying question before answering in 0% of cases, warned about red flags or scams in 26.7%, and told the buyer to verify credentials in 13.3%, averaging 251 words per answer. On the remaining cues it told the buyer to check reviews in 0%, pointed to case studies or a portfolio in 13.3%, and framed the choice around local proximity in 13.3%; a selection-criteria checklist appeared in 33.3% of its answers and a recommendation to gather multiple quotes in 0%.

Taken together, ChatGPT is the assistant most likely to route a carpenter buyer to a professional (73.3%) and Gemini the least (40%). ChatGPT produced the longest answers, at 487 words on average. Specific providers were named most often by Gemini (6.7%) — even there, roughly one answer in 15 carried a name.

Where they disagree

The behaviors where the choice of model changes the answer.

The divergence index for this study is 27.8 points — the average distance between the most and least likely model across the coded behaviors. The gaps below are where which assistant a carpenter buyer happens to ask matters most:

  • Asks a clarifying question: from 0% (Gemini) to 46.7% (ChatGPT) — a 47-point spread.
  • Mentions local proximity: from 13.3% (Gemini) to 53.3% (ChatGPT) — a 40-point spread.
  • Gives selection criteria: from 33.3% (Gemini) to 66.7% (ChatGPT) — a 33-point spread.
  • Recommends hiring a professional: from 40% (Gemini) to 73.3% (ChatGPT) — a 33-point spread.
  • Recommends multiple quotes: from 0% (Gemini) to 33.3% (ChatGPT) — a 33-point spread.

The widest single gap — asks a clarifying question, 47 points — means a carpenter 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 carpenter market.

Where they agree

The points of near-consensus in Carpenter.

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

  • Names a specific provider: 0%–6.7% across all three (a 7-point spread).
  • Gives price or cost information: 40%–46.7% across all three (a 7-point spread).
  • Warns about red flags or scams: 20%–26.7% across all three (a 7-point spread).
  • Suggests a DIY approach first: 0%–13.3% across all three (a 13-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 93.3% of questions) and least consistently on "gives selection criteria" (26.7%).

Every behavior, measured

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

The behaviors AI models reproduce most often for carpenter are recommends hiring a professional (60% on average), gives selection criteria (53.3%) and gives price or cost information (42.2%); the rarest are names a specific provider (2.2%), suggests a DIY approach first (6.7%) and tells the buyer to check reviews (13.3%). Each figure below is the share of a model's 15 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: 60% on average (ChatGPT 73.3%, Claude 66.7%, Gemini 40%) — a 33-point spread.
  • Gives selection criteria: 53.3% on average (ChatGPT 66.7%, Claude 60%, Gemini 33.3%) — a 33-point spread.
  • Gives price or cost information: 42.2% on average (ChatGPT 40%, Claude 46.7%, Gemini 40%) — a 7-point spread.
  • Mentions local proximity: 35.5% on average (ChatGPT 53.3%, Claude 40%, Gemini 13.3%) — a 40-point spread.
  • Asks a clarifying question: 31.1% on average (ChatGPT 46.7%, Claude 46.7%, Gemini 0%) — a 47-point spread.
  • Mentions case studies or portfolio: 26.6% on average (ChatGPT 33.3%, Claude 33.3%, Gemini 13.3%) — a 20-point spread.
  • Warns about red flags or scams: 24.5% on average (ChatGPT 26.7%, Claude 20%, Gemini 26.7%) — a 7-point spread.
  • Tells the buyer to verify credentials: 22.2% on average (ChatGPT 33.3%, Claude 20%, Gemini 13.3%) — a 20-point spread.
  • Recommends multiple quotes: 20% on average (ChatGPT 33.3%, Claude 26.7%, Gemini 0%) — a 33-point spread.
  • Tells the buyer to check reviews: 13.3% on average (ChatGPT 26.7%, Claude 13.3%, Gemini 0%) — a 27-point spread.
  • Suggests a DIY approach first: 6.7% on average (ChatGPT 0%, Claude 13.3%, Gemini 6.7%) — a 13-point spread.
  • Names a specific provider: 2.2% on average (ChatGPT 0%, Claude 0%, Gemini 6.7%) — a 7-point spread.

Trust signals

How well the models protect the carpenter buyer.

Beyond whether to hire, the rubric codes how carefully each assistant protects the carpenter buyer once a decision is made. Telling the buyer to check reviews or ratings appeared in 13.3% of answers on average. Verifying credentials or certifications appeared in 22.2%. Warning about red flags or scams appeared in 24.5%.

On structuring the decision, a selection-criteria checklist showed up in 53.3% of answers on average and a recommendation to gather multiple quotes in 20%. The single least-reproduced protective signal for carpenter is "tells the buyer to check reviews" at 13.3% 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 Carpenter providers?

For service providers the decisive question is whether these systems name anyone at all. Across 45 carpenter answers, a specific provider was named in 2.2% of responses on average — roughly 0 distinct providers per answer. In practice the assistants behave far more as an explanatory layer than as a referral engine for carpenter: visibility comes from being the reasoning a model reproduces, not from being the named recommendation.

The question set

What these 15 Carpenter questions cover.

The 15 questions behind every percentage on this page were drawn from real carpenter (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 carpenter 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 15 answers in which the behavior appeared at least once — not a confidence score. Because each model answered every question exactly once on 2026-07-04, the figures describe this specific carpenter 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.

15 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 2026-07-04, 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 →