---
title: "Comment by Aldo on \"AI Search Showdown: Perplexity vs ChatGPT Search vs Google AI Mode\" | Hashnode"
description: "One useful extra control is to treat each query run as a sample, not a verdict: hold wording, locale, language, signed-in state, and mode constant, then repeat"
url: "https://hashnode.com/posts/perplexity-vs-chatgpt-search-vs-google-ai-mode/6af7c6748cbf6d1eb5394e97/comment/6af83b48ec7b027a28806c17"
---

[Discussion](https://hashnode.com/posts/perplexity-vs-chatgpt-search-vs-google-ai-mode/6af7c6748cbf6d1eb5394e97)

Comment [AI Search Showdown: Perplexity vs ChatGPT Search vs Google AI Mode](https://hashnode.com/posts/perplexity-vs-chatgpt-search-vs-google-ai-mode/6af7c6748cbf6d1eb5394e97)

[Aldo](https://hashnode.com/@aldoquantic)

[3d ago](https://hashnode.com/posts/perplexity-vs-chatgpt-search-vs-google-ai-mode/6af7c6748cbf6d1eb5394e97/comment/6af83b48ec7b027a28806c17)

One useful extra control is to treat each query run as a sample, not a verdict: hold wording, locale, language, signed-in state, and mode constant, then repeat the same prompt across several days. Save the exact prompt and timestamp alongside the cited URLs, not only the brand mention, since a citation to the page you’re evaluating is a different outcome from a mention or a homepage link. I’d compare citation frequency and source overlap over a rolling window; for technical queries, verify each cited claim against the primary documentation. This makes the five-query test much easier to reproduce when answers fluctuate.
