Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.getcited.in/llms.txt

Use this file to discover all available pages before exploring further.

Citation rate is the percentage of AI responses that include a direct hyperlink to a brand’s domain as a cited source. It is a stricter test than mention rate — a brand can be named in an AI response without being linked, but a citation requires the AI to surface a clickable source URL pointing to the brand’s website.

​
Why it matters

Citations drive traffic. When an AI response includes a link to your domain, some fraction of readers will click through. Mentions without citations are brand awareness; citations are brand awareness plus a direct pathway to conversion. A 30% mention rate with 5% citation rate delivers materially more value than a 30% mention rate with 0% citation rate. Citations also signal authority. When an AI platform chooses to cite your domain rather than a review aggregator or a news article, it is making an editorial judgment that your content is a high-quality source for the query. Sustained citation presence on a specific topic is one of the strongest signals of GEO success — it means the AI has chosen you as a primary authority rather than a downstream mention.

​
Formula

citation_rate = (responses_with_citation / total_responses) × 100
Inputs:
  • responses_with_citation — number of AI responses that include a link to your domain as a source
  • total_responses — total AI responses across the tracked query set
Citation rate is calculated per platform. It is lowest when averaged across platforms because not all platforms provide citations in a consistent format.

​
Example calculation

A B2B SaaS brand tracks 60 queries on Perplexity. In one week, Perplexity returns 60 responses. 9 of those responses include a link to the brand’s domain among the cited sources. 
citation_rate = (9 / 60) × 100 = 15%
Perplexity cites the brand’s domain on 15% of relevant queries — a moderate but actionable citation presence.

​
Citation rate vs. mention rate

Citation rate is a subset of mention rate. A brand can be mentioned without being cited, but a citation always implies a mention. The gap between the two metrics is diagnostic:
  • High mention rate, low citation rate — the AI knows about your brand from training data or third-party sources but does not treat your own website as a quality source. Focus: improve on-site content quality, schema markup, and technical AI readability.
  • Similar mention rate and citation rate — the AI both knows you exist and considers your own content authoritative. Maintain freshness and expand coverage of new topics.
  • Zero citation rate across all platforms — either your content is not discoverable to AI crawlers, or your domain is filtered out by the platform’s source selection. Check your robots.txt and llms.txt files and review the Fix your llms.txt and robots.txt playbook.

​
Empirical benchmarks not yet available

Cited does not currently publish percentile benchmarks for citation rate across the Cited Index. This is driven by data availability, not classifier issues. The problem. Structured citation URLs are reliably provided by only one platform — Perplexity. ChatGPT’s search feature provides citations inconsistently, Claude rarely provides explicit source URLs, and Gemini’s AI Overviews use a different citation structure that is harder to extract. Cross-platform citation rate benchmarks would be dominated by Perplexity data with sparse contributions from other platforms, making the numbers misleading. What is available today. Cited tracks citation rate for Perplexity on all dashboard brands and for brands that opt into extended citation tracking. These numbers are visible in the customer dashboard but are not aggregated into published benchmarks because the sample is currently too small to produce stable percentiles. When benchmarks will be added. Citation rate benchmarks will be published once either (a) citation extraction across ChatGPT, Claude, and Gemini reaches parity with Perplexity, or (b) the Cited Index sample grows large enough that Perplexity-only percentiles are statistically stable at the category level. Target: Q3 2026. See the benchmarks methodology for the full list of metrics with and without current benchmarks.

​
What changes this metric

  • AI-readable content structure — pages with clear headings, structured data, and clean HTML are more likely to be cited than pages hidden behind JavaScript rendering or heavy marketing copy
  • Robots.txt and llms.txt configuration — blocking AI crawlers prevents citation regardless of content quality; allowing them is a prerequisite, not a guarantee
  • Source authority — citation rate is influenced by the same signals that drive SEO authority: inbound links, domain age, content depth, and topical focus
  • Content freshness — platforms favor recently-updated pages over stale ones, especially for queries about evolving topics (pricing, features, comparisons)
  • Schema markup — structured data helps AI platforms parse your content into citation-ready summaries

​
How Cited measures it

Cited parses each AI response for outbound URLs in the cited sources list (where available). When a response contains a URL on your configured domain, the response is counted as a citation. The citation rate is the number of citing responses divided by the total responses for a given query set and time window. For Perplexity, citations are extracted from the explicit “Sources” section of each response, which Perplexity provides in a structured format. For other platforms, citation extraction is best-effort and less reliable — the Cited dashboard distinguishes Perplexity citation rate from cross-platform citation rate to prevent misleading comparisons.

​
Frequently asked questions

Perplexity is the only platform that consistently provides structured citation URLs in its responses. ChatGPT’s search feature provides citations inconsistently, Claude rarely exposes source URLs, and Gemini uses a different citation structure that is harder to extract programmatically. Cited tracks citation rate on all platforms but only Perplexity citation data is reliable enough for reporting today.
Three common causes: (1) your robots.txt or llms.txt is blocking AI crawlers, (2) your website’s content is not structured in a way AI platforms can parse into citations (e.g., everything behind a JavaScript-rendered app), or (3) the AI is citing third-party sources about your brand (review sites, press coverage) rather than your own domain. Start by verifying crawler access, then audit content structure.
They overlap but are not the same. Traditional SEO authority is measured by link equity, keyword rankings, and traffic — it predicts how your domain performs in Google search results. Citation rate is measured by how often AI platforms choose to cite your domain in generated answers — it predicts how your domain performs in AI-mediated discovery. A high-authority domain in SEO terms may have low citation rate if its content is not structured for AI parsing.
Mostly no. Citations require mentions — the AI cannot cite your domain without first referencing your brand. That said, the gap between mention rate and citation rate can be narrowed by improving content quality and technical AI readability. If your mention rate is 30% and citation rate is 5%, the work is to move that 5% closer to 30% by making your own domain the preferred source rather than third-party articles.
Target is Q3 2026, dependent on either citation extraction improving across ChatGPT, Claude, and Gemini or the Cited Index sample growing large enough that Perplexity-only percentiles are stable at the category level. Until then, citation rate is tracked in customer dashboards but not aggregated into public benchmarks.