Finding 4 of 4
Do Gemini and ChatGPT cite the same websites a week later?
About half the cited websites recurred a week later.
- 55.8% of the websites Gemini cited for a question in the first window were cited for it again a week later
- 54.2% of the websites ChatGPT cited for a question in the first window were cited for it again a week later
- 0.40 median overlap per question for Gemini (0 = no shared websites, 1 = the same set)
- 0.35 median overlap per question for ChatGPT
What we found
When the same questions were asked again a week later, 55.8% (Gemini) and 54.2% (ChatGPT) of the websites cited for each question in the first window were cited for it again, so the study's working hypothesis that fewer than half would recur did not hold. Part of the change that did occur is ordinary variation between runs rather than change over time, and two windows show no trend.
A 2026 survey of published studies notes that commercial audits report "substantial run-to-run variability".
A single check of what an assistant says is a snapshot. A fixed set of questions asked on a schedule gives a fairer picture.
How we counted
42 English questions about 7 kinds of marketing service in Malaysia, asking whom to hire, how a service works or what it costs, each put to Gemini and to ChatGPT 3 times in each of two windows a week apart (26 September 2026 to 27 September 2026, and 4 October 2026).
The overlap is computed over the questions with a citation in either window: 29 for Gemini and 42 for ChatGPT.
English questions about marketing services in Malaysia, asked of Gemini and ChatGPT through their APIs in two windows (26 to 27 September and 4 October 2026).
What you can do with this
If you want your own business to be found
Measure visibility with the platforms' own reports, and do not mistake it for traffic. Use Search Console's generative AI report, Bing's AI Performance report and a fixed set of questions asked on a schedule, because the cited set varied between runs and between two windows a week apart. Treat a citation as visibility, not as traffic or enquiries.
About the study
The questions were written for this study, not sampled from what businesses ask, and the engines ran through their developer APIs with fixed model versions rather than through the consumer apps. For ChatGPT, the audit counts the inline citations attached to each answer, not every page it read. The results describe this panel on these dates and show what was cited, not why.
ALIQ Studio sells AI-visibility services, so it has a commercial interest in this topic. Its own website was among the five most-cited agency websites in this audit.
Read the full section of the paper →
How to cite this finding
Yik Jinn, ALIQ Studio (2026). What AI answer engines cite when Malaysian SMEs ask for marketing help, v1.1. Finding: About half the cited websites recurred a week later. https://studio.aliqgroup.com/en/research/ai-answer-citations-malaysia-2026/ai-cited-websites-change-week-to-week/. DOI: 10.5281/zenodo.23970962. CC BY 4.0.