In a dataset of 15,000 prompts, we discovered that—on common—solely 12% of hyperlinks cited by ChatGPT, Gemini, and Copilot seem in Google’s high 10 outcomes for a similar immediate.
Perplexity is the outlier: almost 1 in 3 of its citations level to pages that rank within the high 10 for the goal question.
We analyzed 4 AI assistants—ChatGPT, Gemini, Copilot, and Perplexity—to measure how typically the URLs they cite or reference overlap with what Google or Bing ranks for a similar question.
On common, the quotation overlap between AI assistants and Google and Bing’s high 10 stands at 11%.
((Google AI overlap whole + Bing AI overlap whole) / 10) = 10.96%
Additional down, we take a look at this damaged down by particular person search engine.
Utilizing knowledge from Ahrefs Model Radar, our knowledge scientist, Xibeijia Guan, searched 15,000 long-tail queries in Google and Bing, then requested those self same inquiries to AI assistants.
Instance queries included:
- “How a lot does it price to put in a safety digital camera?”
- “Methods to get sufficient protein when you may’t eat dairy?”
- “What’s the most cost-effective full complete insurance coverage?”
- “¿Cuál es el mejor suplemento para la recuperación muscular?”
Xibeijia then extracted each seen quotation returned for every query throughout each search and AI indices.
Within the search dataset, she recorded the rating positions of the cited URLs—then categorized them based mostly on whether or not they appeared within the high 10, or high 100 outcomes.
The AI assistants examined embody ChatGPT (each in-text citations and bottom-of-response references), Gemini, Copilot, and Perplexity.
In line with analysis carried out by our knowledge scientist, Xibeijia Guan, simply 12% of citations in AI assistants additionally rank in Google’s high 10, on common.
((28.6 + 8 + 6.1 + 8.6 + 8.2) / 5) = 11.9%
80% of these citations don’t rank anyplace in Google for the unique question—80% is basically the typical of all of the “crimson” columns within the chart above.
The overlap between AI and search citations is smaller than we anticipated, however we’ve got a few theories as to why that may be.
We’ll get into them a little bit later on.
Perplexity aligns closest to Google
Perplexity is an AI assistant that was actually constructed to quote—its purpose is to assist almost each assertion with a supply.
Perplexity is the world’s first reply engine. It searches the web in actual time to ship quick, clear solutions to any query—with sources and citations included…Each reply comes with clickable citations, making it straightforward to confirm the knowledge and dig deeper in order for you.
Perplexity Workforce, Oct 2024
ChatGPT and Gemini, then again, don’t at all times hyperlink out.
Their quotation course of may be very a lot query-dependent, and their inner programs set off searches based mostly on completely different standards.
ChatGPT, for instance, appears to make use of one thing referred to as the sonic classifier—if the immediate “likelihood” exceeds a sure threshold (i.e. if the response is much less straightforward to “predict” based mostly on coaching knowledge), then ChatGPT will carry out an internet search.
Perplexity persistently favors content material that ranks properly in Google, with 28.6% of its cited URLs touchdown within the high 10.
For the opposite AI assistants, that quantity hovers round 8%—and greater than 80% of their citations come from pages that don’t rank in any respect for the goal question.
Since Perplexity focuses closely on citations, it appears logical that its outcomes would align intently with Google’s.
However, not like Gemini and different AI assistants, Perplexity doesn’t draw on Google or Bing’s index. Actually, it has its personal search index, based mostly on its crawler: perplexitybot.
AI assistants—even people who draw on Google and Bing—seem to question search indexes in a essentially completely different approach. This explains why we’re seeing minimal crossover.
When measuring towards Bing outcomes, overlap stays low within the high 10—hitting roughly 10% on common.
((16.6 + 14 + 8.1 + 8.1 + 3.3) / 5) = 10.02%
Copilot rises to the highest of the record, which is to be anticipated since it’s a Microsoft-owned product that attracts on Bing search outcomes when producing its responses.
Perplexity nonetheless stays one of the vital Website positioning-aligned AI assistants, whereas ChatGPT and Gemini present the least overlap.
This research builds on our earlier analysis into how typically high-ranking pages get cited in Google’s AI Overviews.
Additional studying:
In these research, we discovered a average optimistic correlation between Google rankings and citations in AI Overviews, with 76% of cited URLs coming from pages within the high 10.
Based mostly on the info, it appears as if AI Overviews perform like an extension of conventional search—surfacing outcomes that principally replicate the SERP.
In different phrases, AI Overviews observe the SERPs—AI assistants don’t.
Even the assistants constructed by Google aren’t intently aligned with Google’s SERPs.
There are clearly different elements influencing what will get cited, past simply search rankings.
Our knowledge reveals that the URLs cited by AI assistants not often match what Google and Bing ranks.
Normally, they don’t seem within the high 10 for the goal immediate—typically, they aren’t within the high 100 at all.
It’s because AI assistants don’t rank ends in the identical approach engines like google do.
As an alternative of processing only one consumer question when deciding what to quote, they have a tendency to retrieve pages based mostly on a number of variations of that question—a way often called “question fan-out.”
These variations then get merged utilizing strategies like Reciprocal Rank Fusion (RRF), the place the pages that seem persistently are favored extra.
For instance, a web page that ranks round #6 for “the right way to descale a espresso machine,” “cleansing a Nespresso machine,” and “take away limescale from espresso maker” is perhaps cited over one which ranks #1 for under one in all these.
Actually, it’s potential that AI assistants might by no means seek for the precise immediate that the consumer inputs—as an alternative it simply acts as a catalyst for different fan-out queries.
Because of this eventual citations gained’t at all times rank for the unique immediate.
Personalization may play a task: the very same search question run by AI can result in wholly completely different citations, on account of elements just like the consumer’s immediate or dialog historical past.
All of this helps clarify why AI citations don’t at all times mirror the SERPs.
Tip
You may optimize for a number of, long-tail question variations utilizing Mother or father Subjects in Ahrefs Key phrase Explorer.
Simply search a key phrase, head to the Matching Phrases or Associated Phrases report, and take a look at the Mother or father Subjects on the left, or hit the Clusters by Mother or father Matter tab.
Then hit the Questions tab for long-tail queries to focus on in your content material…
And to see how a lot possession you will have over current long-tail question permutations, add a Goal filter in your area.
Current assessments by Aleksis Rylko means that SearchGPT citations intently resemble Google citations.
Rylko believes ChatGPT might now quietly pull from Google’s search index.
Aleyda Solís corroborated this—she found that ChatGPT makes use of Google as a fallback when Bing pages are inaccessible.
These findings got here as a shock to many, as a result of ChatGPT’s built-in supplier is Bing.
From our personal dataset, we aren’t seeing a lot differentiation in how ChatGPT surfaces each Google and Bing outcomes.
| Google (high 10) | Bing (high 10) | Google (high 100) | Bing (high 100) | |
|---|---|---|---|---|
| ChatGPT (in-text citations) | 8.00% | 8.10% | 8.80% | 5.00% |
| ChatGPT (references) | 6.10% | 8.10% | 9.20% | 5.20% |
That mentioned, we collected this knowledge in early July, so outcomes might have modified—particularly provided that OpenAI is planning to launch its AI-first net browser, and probably even construct its personal search index, going by the latest memo leak.
We’ll be doing additional analysis to review any quotation shifts.
Wrapping up
From our analysis, evidently rating properly undoubtedly does assist, however not essentially for the queries you may assume you’d have to rank properly for.
We’ll hold finding out quotation overlap in conventional search and AI to see if something modifications.
Within the meantime, optimizing for question variations, constructing matter clusters, and “proudly owning the entity” appears to be the way in which to go in case you are hoping to get cited in AI.
