Parse
IndexPricing
Sign inCheck your brand
  1. Research
Research
Cited sources fell after a ChatGPT model update

Cited sources fell after a ChatGPT model update

Published Jun 25, 2026Updated Oct 12, 2026

On this page
  • The finding
  • How we measured
  • Sources
  • More like this
  • The finding
  • How we measured
  • Sources
  • More like this

Dimitry ApollonskyFounder, Parse

DataWhat reviewed means

A sudden loss of AI citations could reflect a change to a website or a change to the engine itself. We wanted to see whether a ChatGPT model upgrade changed the number of source domains behind its answers.

We compared 423,341 answers from steady windows before and after the flagship upgrade, including 16,161 questions observed under both versions. We also tracked an unchanged control model to help distinguish the upgrade pattern from broader changes.

Across 16,161 matched questions around ChatGPT's early March 2026 flagship upgrade, average cited source domains per answer fell from 23.4 to 12.1. An unchanged control model held steady, pointing to a platform change rather than a site-specific loss.

A model upgrade halved the sources behind each answer

A model upgrade on the vendor's side is a real cause of AI-visibility change, and it can move more than anything a brand does to its own pages. When ChatGPT's flagship version upgraded in early March 2026, the evidence behind each answer thinned out across the changeover.

Sources cited per answer fell from a mean of 23.4 to 12.1, a 48% cut. The drop was not gradual. It lined up with the model change, not with anything on the sites being cited.

Sources cited per answer

  • Before the upgrade23.4
  • After the upgrade12.1
  • 0102030
Mean sources cited per answer across the matched prompt set, meaning the same prompts run under both versions, before and after the upgrade.

23.4 → 12.1
mean sources cited per answer, before and after
a 48% cut

Takeaway

Before you read a citation drop as a content problem, check whether it lines up with a model change. The cause may be upstream of your site.

On a matched prompt set, 99.7% of answers cited fewer sources

Window averages can hide a shifting mix of questions. To rule that out we held the questions fixed and compared 16,161 prompts that ran under both versions of the flagship.

Of those matched prompts, 16,116 cited fewer sources after the upgrade and only 45 rose. That is 99.7% moving the same direction, with a mean drop of about 11 sources per prompt. This was not noise.

Prompts run under both versions
16,161
Cited fewer sources after
99.7%
Mean drop per matched prompt
−11.3

An unchanged control model held steady, isolating the cause

If the drop were a quirk of measurement, a model that did not change should have fallen alongside the flagship. A smaller, unchanged model ran throughout the same weeks as a control.

The upgraded flagship fell 48% while the control held steady, even ticking up 4% over the same window. The gap between the two is about 12 sources per answer. The drop tracks the model upgrade, not how we measured it.

  • Upgraded flagship−48.1%
  • Unchanged control+4.4%
  • 0%20%40%60%
Change in sources cited per answer over the same window, upgraded flagship versus unchanged control.

Takeaway

When a number changes, look for a control. The control held while the flagship fell, which is how we know the model moved it.

The control sat where the flagship used to, then the flagship dropped under it

Before the upgrade the two models cited almost the same number of sources, 23.4 for the flagship and 23.6 for the control. After, the control still cited 24.6 while the flagship had fallen to 12.1. Same weeks, same measurement, two very different paths.

Upgraded flagship, before to after
23.4 → 12.1
Unchanged control, before to after
23.6 → 24.6
Sources apart after the upgrade
~12

Every industry category fell

The cut was not concentrated in one kind of question. Every industry group in the sample fell, and answers after the upgrade landed at roughly 11 to 13 sources regardless of topic.

The biggest losers were the categories that had been citing the most. Software and artificial intelligence answers, which led before, fell the hardest. The model pulled the top categories down toward the rest.

Sources before · 6 results

  • Software25.4
  • Artificial intelligence25.4
  • Financial services23.5
  • Health care22.2
  • Commerce and shopping22
  • Community and lifestyle20.4
  • 0102030
Explore the data (6 rows)
Software25.412.5-12.9
Artificial intelligence25.412.7-12.7
Financial services23.512.8-10.7
Commerce and shopping2211.4-10.7
Health care22.211.8-10.4
Community and lifestyle20.411.6-8.8
Mean sources cited per answer by industry group, before and after. Click a column to sort.

After the upgrade, answers landed in a narrow range, whatever the topic

Across all 31 industry segments in the sample, the averages after the upgrade landed in a tight 11 to 13 source range. Where a question came from used to shape how much evidence it drew. After the upgrade it barely did.

31 / 31
industry segments that fell, all landing at ~11–13 sources

Citation counts went from a wide spread to a near-fixed number

Before the upgrade, source counts spread widely. Answers ranged from the mid-teens to past 40, with a long tail of deep-citing answers above 35. The spread, measured as standard deviation, was 7.6.

After, the range collapsed. 88% of answers now cite between 10 and 15 sources, and the spread roughly halved to 3.0. Answers stopped occasionally reaching deep and settled into a fixed band.

Of answers now cite 10–15 sources
88%
Spread in source counts, before to after
7.6 → 3.0
Of old answers cited 20–25 sources
47%

The cut was broad and even, not a shift toward big domains

Citation counts fell, but the domain shares barely changed.

The share of citations held by the top 20 domains barely moved, 9.6% to 9.9%, and the top 100 share moved just as little. The drop landed roughly proportionally across the whole field rather than favoring the biggest sites.

  • Top 20 share, before9.6%
  • Top 20 share, after9.9%
  • 0%5%10%
Share of all citations held by the top 20 domains, before and after the upgrade.

Takeaway

Fewer citations, but the same order. Everyone lost roughly the same share.

A third fewer citations, and a fifth fewer distinct domains

Halving sources per answer shrinks the whole citation footprint. Total citations across the window fell 37% and the number of distinct domains cited fell 23%. The web that AI draws from got both shallower per answer and narrower overall.

Total citations
−37%
Distinct domains cited
−23%
Top 20 domain share (held flat)
9.6% → 9.9%

What this means for your AI visibility

A citation drop can be the model, not you. Before you treat a fall in citations as a content problem, check whether it lines up with a model change. The cause may be upstream of anything on your site.

Fewer citations raises the bar. When each answer cites fewer sources, the contest to be one of them is sharper. Breadth of presence matters more, not less.

Track across model releases. A single visibility number read in isolation will blame the wrong cause when a model shift happens. Watch the trend across releases, not just week to week.

How we measured this

We counted the number of distinct source domains behind each ChatGPT answer across a steady window before the flagship upgrade and a steady window after, then compared 16,161 prompts that ran under both versions. A smaller, unchanged model ran throughout as a control. The upgrade is anchored on the observed changeover in early March 2026.

This covers one engine and one upgrade event, so it does not predict the direction of future upgrades. Source count measures breadth, not influence per source, so fewer citations does not strictly mean less downstream effect. Figures describe a measured sample of AI answers, not Perplexity, Gemini, or Copilot.

  • Is the AI visibility drop real or just noise? A measurement guide

How we measured

We compared 423,341 ChatGPT answers from steady windows before and after a flagship model upgrade, with 16,161 prompts run under both versions and an unchanged control model.

Sources cited per answer
23 → 12

Mean, before and after

Drop on the upgraded flagship
−48%
Of matched prompts cited fewer sources
99.7%
Change on the unchanged control
+4%

Get the data

Dataset CSVHeadline metrics behind every figure in this report.

Sources

  1. OpenAI ships flagship model updates that change ChatGPT's default behavior, OpenAI (opens in a new tab) · accessed June 25, 2026
  2. AI answer engines cite a variable number of web sources per answer, Search Engine Land (opens in a new tab) · accessed June 25, 2026

More like this

How long an AI citation lasts
About half of a question’s cited websites disappeared on the next run, while a smaller set persisted for weeks.
How AI rankings changed over five months
Four in ten top-100 brands left that group over five months. A single ranking snapshot can miss substantial change.
How AI picks a winner in head-to-head comparisons
The winner often changed with the criterion being compared. A brand could win on one need and lose on another.
How old are the pages AI cites?
Too few cited pages had a measurable age to draw broad conclusions about whether AI favors fresh content.
Is AI naming fewer brands per answer over time?
Google AI Mode named more brands per answer over the months compared, among answers naming at least one brand.
Do ChatGPT model updates change brand recommendations?
Both ChatGPT model updates changed the top brand more often than repeat answers from the same model did.
How ChatGPT's writing style changed by model version
Stock AI wording became less common across the ChatGPT model versions we compared on the same prompts.
Does AI change its tone when cited sources turn negative?
AI's descriptions stayed largely positive even after its cited sources changed from positive to negative.

See the sources behind your brand in AI answers.

Parse

Index

  • Brands
  • Markets
  • Topics
  • How we measure

For agents

  • Docs
  • Connect
  • Workflows
  • llms.txt

Parse

  • Pricing
  • Research
  • Blog
  • Compare

Company

  • About
  • Contact
  • Corrections

© 2026 Parse, Inc. All rights reserved.

Privacy PolicyTerms of Service