Original research · 2026-07 edition

AI SEO Statistics: Addiction Treatment (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 addiction treatment.

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

What are the warning signs that my spouse's drinking has crossed the line into needing professional medical intervention?
Is it possible to safely detox from opioids at home, or is a medically supervised facility always required?
How do I compare the success rates of different residential treatment centers when they all claim to be the best?
What is the average out-of-pocket cost for a 30-day inpatient program if my insurance only covers a portion?
My daughter is struggling with pills and has a co-occurring anxiety disorder; what specific certifications should I look for in a facility?
What is the difference between a standard detox center and a long-term residential rehab program?
Are there any red flags I should watch out for when touring a local addiction treatment clinic?
How can I tell if an intensive outpatient program (IOP) is enough for someone who has relapsed twice before?
Show all 15 questions
What questions should I ask a facility to make sure they use evidence-based therapies like CBT instead of just holistic methods?
We need to find a bed for a family member today; what's the fastest way to verify if a center takes our specific insurance plan?
Is a luxury rehab actually more effective for recovery, or are you just paying for the amenities?
What are the legal or privacy protections for my job if I decide to take a leave of absence for a 28-day treatment program?
My son refuses to go to treatment; what are the pros and cons of hiring a professional interventionist?
How do I find a rehab that specializes in veteran-specific trauma and substance abuse?
What happens during a typical day in an inpatient facility, and how much contact will I have with my family?

Model by model

20-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 addiction treatment buyers.

Behavior rates across 15 addiction treatment buyer questions, 2026-07 edition. Last column: average across models.
ChatGPTClaudeGeminiConsensus
Recommends hiring a professional60%40%33%53%
Suggests DIY first20%27%13%67%
Names specific providers13%7%0%87%
Gives price or cost info7%13%7%80%
Tells to check reviews13%13%0%87%
Tells to verify credentials40%40%13%73%
Mentions case studies / portfolio7%0%0%93%
Mentions local proximity40%0%0%60%
Gives selection criteria53%47%40%60%
Warns about red flags27%33%20%80%
Asks a clarifying question67%67%0%13%
Recommends multiple quotes7%0%0%93%

By model

How each assistant handled Addiction Treatment questions.

Reading the 45 answers model by model shows how differently the three assistants treat the same addiction treatment questions. On the most consequential behavior — whether to send the buyer to a professional at all — the rate ranged from 60% (ChatGPT) down to 33.3% (Gemini), a 27-point gap on an identical question set.

Across the 15 addiction treatment answers it produced, ChatGPT recommended hiring a professional in 60% of them and suggested a DIY approach first 20% of the time. It named a specific provider in 13.3% of answers (about 0.3 distinct providers per answer) and included price or cost information 6.7% of the time. ChatGPT asked a clarifying question before answering in 66.7% of cases, warned about red flags or scams in 26.7%, and told the buyer to verify credentials in 40%, averaging 603 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 6.7%, and framed the choice around local proximity in 40%; a selection-criteria checklist appeared in 53.3% of its answers and a recommendation to gather multiple quotes in 6.7%.

Across the 15 addiction treatment answers it produced, Claude recommended hiring a professional in 40% of them and suggested a DIY approach first 26.7% 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 13.3% of the time. Claude asked a clarifying question before answering in 66.7% of cases, warned about red flags or scams in 33.3%, and told the buyer to verify credentials in 40%, averaging 308 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 0%, and framed the choice around local proximity in 0%; a selection-criteria checklist appeared in 46.7% of its answers and a recommendation to gather multiple quotes in 0%.

Across the 15 addiction treatment answers it produced, Gemini recommended hiring a professional in 33.3% 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 6.7% of the time. Gemini asked a clarifying question before answering in 0% of cases, warned about red flags or scams in 20%, and told the buyer to verify credentials in 13.3%, averaging 252 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 0%; a selection-criteria checklist appeared in 40% of its answers and a recommendation to gather multiple quotes in 0%.

Taken together, ChatGPT is the assistant most likely to route an addiction treatment buyer to a professional (60%) and Gemini the least (33.3%). ChatGPT produced the longest answers, at 603 words on average. Specific providers were named most often by ChatGPT (13.3%) — even there, roughly one answer in 8 carried a name.

Where they disagree

The behaviors where the choice of model changes the answer.

The divergence index for this study is 19.6 points — the average distance between the most and least likely model across the coded behaviors. The gaps below are where which assistant an addiction treatment buyer happens to ask matters most:

  • Asks a clarifying question: from 0% (Gemini) to 66.7% (ChatGPT) — a 67-point spread.
  • Mentions local proximity: from 0% (Claude) to 40% (ChatGPT) — a 40-point spread.
  • Recommends hiring a professional: from 33.3% (Gemini) to 60% (ChatGPT) — a 27-point spread.
  • Tells the buyer to verify credentials: from 13.3% (Gemini) to 40% (ChatGPT) — a 27-point spread.
  • Suggests a DIY approach first: from 13.3% (Gemini) to 26.7% (Claude) — a 13-point spread.

The widest single gap — asks a clarifying question, 67 points — means an addiction treatment 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 addiction treatment market.

Where they agree

The points of near-consensus in Addiction Treatment.

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

  • Gives price or cost information: 6.7%–13.3% across all three (a 7-point spread).
  • Mentions case studies or portfolio: 0%–6.7% across all three (a 7-point spread).
  • Recommends multiple quotes: 0%–6.7% across all three (a 7-point spread).
  • Names a specific provider: 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 "mentions case studies or portfolio" (identical coding in 93.3% of questions) and least consistently on "asks a clarifying question" (13.3%).

Every behavior, measured

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

The behaviors AI models reproduce most often for addiction treatment are gives selection criteria (46.7% on average), asks a clarifying question (44.5%) and recommends hiring a professional (44.4%); the rarest are recommends multiple quotes (2.2%), mentions case studies or portfolio (2.2%) and names a specific provider (6.7%). 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:

  • Gives selection criteria: 46.7% on average (ChatGPT 53.3%, Claude 46.7%, Gemini 40%) — a 13-point spread.
  • Asks a clarifying question: 44.5% on average (ChatGPT 66.7%, Claude 66.7%, Gemini 0%) — a 67-point spread.
  • Recommends hiring a professional: 44.4% on average (ChatGPT 60%, Claude 40%, Gemini 33.3%) — a 27-point spread.
  • Tells the buyer to verify credentials: 31.1% on average (ChatGPT 40%, Claude 40%, Gemini 13.3%) — a 27-point spread.
  • Warns about red flags or scams: 26.7% on average (ChatGPT 26.7%, Claude 33.3%, Gemini 20%) — a 13-point spread.
  • Suggests a DIY approach first: 20% on average (ChatGPT 20%, Claude 26.7%, Gemini 13.3%) — a 13-point spread.
  • Mentions local proximity: 13.3% on average (ChatGPT 40%, Claude 0%, Gemini 0%) — a 40-point spread.
  • Gives price or cost information: 8.9% on average (ChatGPT 6.7%, Claude 13.3%, Gemini 6.7%) — a 7-point spread.
  • Tells the buyer to check reviews: 8.9% on average (ChatGPT 13.3%, Claude 13.3%, Gemini 0%) — a 13-point spread.
  • Names a specific provider: 6.7% on average (ChatGPT 13.3%, Claude 6.7%, Gemini 0%) — a 13-point spread.
  • Mentions case studies or portfolio: 2.2% on average (ChatGPT 6.7%, Claude 0%, Gemini 0%) — a 7-point spread.
  • Recommends multiple quotes: 2.2% on average (ChatGPT 6.7%, Claude 0%, Gemini 0%) — a 7-point spread.

Trust signals

How well the models protect the addiction treatment buyer.

Beyond whether to hire, the rubric codes how carefully each assistant protects the addiction treatment buyer once a decision is made. Telling the buyer to check reviews or ratings appeared in 8.9% of answers on average. Verifying credentials or certifications appeared in 31.1%. Warning about red flags or scams appeared in 26.7%.

On structuring the decision, a selection-criteria checklist showed up in 46.7% of answers on average and a recommendation to gather multiple quotes in 2.2%. The single least-reproduced protective signal for addiction treatment is "recommends multiple quotes" at 2.2% 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 Addiction Treatment providers?

For service providers the decisive question is whether these systems name anyone at all. Across 45 addiction treatment answers, a specific provider was named in 6.7% of responses on average — roughly 0.1 distinct providers per answer. In practice the assistants behave far more as an explanatory layer than as a referral engine for addiction treatment: visibility comes from being the reasoning a model reproduces, not from being the named recommendation.

The question set

What these 15 Addiction Treatment questions cover.

The 15 questions behind every percentage on this page were drawn from real addiction treatment (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 addiction treatment 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 addiction treatment 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 →