AI vendor recommendations can be narrow: what 40 ChatGPT and Gemini answers did (and didn’t) name

By Outranker · Published 2026-10-06 · Version 2

Sample: 40 AI answers to 20 questions · Engines: ChatGPT, Gemini · Collected 2026-10-06 – 2026-10-06

How the study was run Ask comparison and evaluation questions across engines; compare how often the brand and each tracked competitor are named. Mentions are detected by whole-word match; answers are stored verbatim. ## Scope - Questions: 20 - Engines: Gemini, ChatGPT - Verified answers: 40 - Repeats per question: 1; waves: 1 - Collection dates: — ## Limitations - AI answers vary between runs; each question is asked once per engine. - Plain-chat engines (ChatGPT, Claude, Gemini) report mentions only, not source links. - Only competitors saved on the Brand Visibility project are tracked. - No source-returning engine is available, so no citation metrics are planned. - Results are descriptive observations of AI answers, not proof of cause.

Limitations