AI SEO Statistics: Solicitor (2026-07 edition)
15 questions · 45 AI responses · 3 models · measured 2026-07-04
The question bank
The questions we tested — sampled from real buyer journeys in solicitor.
Each model answered every question once, same wording, same day. These are the prompts behind every percentage on this page.
Show all 15 questions
Model by model
24-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 solicitor buyers.
| ChatGPT | Claude | Gemini | Consensus | |
|---|---|---|---|---|
| Recommends hiring a professional | 87% | 80% | 53% | 53% |
| Suggests DIY first | 20% | 13% | 7% | 87% |
| Names specific providers | 7% | 7% | 7% | 100% |
| Gives price or cost info | 13% | 27% | 47% | 60% |
| Tells to check reviews | 13% | 27% | 0% | 73% |
| Tells to verify credentials | 20% | 33% | 7% | 60% |
| Mentions case studies / portfolio | 7% | 13% | 0% | 87% |
| Mentions local proximity | 27% | 47% | 20% | 60% |
| Gives selection criteria | 47% | 73% | 33% | 33% |
| Warns about red flags | 7% | 20% | 13% | 73% |
| Asks a clarifying question | 60% | 53% | 0% | 33% |
| Recommends multiple quotes | 27% | 53% | 0% | 40% |
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 →