How we measure Microsoft Copilot
We send your questions and your country to Microsoft Copilot through a data provider and collect the answer. Copilot fails more often than the other systems. The evidence is one test on 4 November 2026: all 6 attempts failed, and the other five systems gave answers. That may have been a provider outage, but this is not proven. Failed runs are shown as failed and do not count.
Does Microsoft Copilot show sources?
Unknown. No Copilot answer has been recorded in our test, so we cannot say whether Copilot answers in a scan list sources. Microsoft says Copilot answers based on web search carry hyperlinked citations below the text.
What can go wrong with Microsoft Copilot
Copilot is unproven, because we have not yet seen a working route. The backup route has not been tested, and it does not send your country, so an answer from it may not reflect your country. Microsoft also says Copilot can make mistakes.
If Microsoft Copilot gives no answer, we retry and use a backup route. Failed answers stay out of the count, and a system with too few answers is labelled Not measured.
Which scan includes Microsoft Copilot
Microsoft Copilot is only in the paid scan, which asks each question five times. Because it is unproven, it may show as Not measured in your report.
How to read the result
You see a count: named in X of Y answers. Each cell opens the full answer from Microsoft Copilot, with your name marked and any sources that came with it.
What we do not promise
Nobody controls what an AI system says. We show what it says now and what you can change. Read our method