A European nonprofit research project based in Berlin

AI Disinformation Benchmark

Data updated on 13 October 2026

How often popular AI assistants cite Kremlin propaganda sources

World

GermanyUnited States soon
June 2024 to October 2026 · combined ranking from 15 datasets

AssistantResponses to test questions that repeated a pro-Kremlin false claim or showed a Kremlin-linked source4,309 responses: 2,306 of Dosimeter and 2,003 of other organisations1 square is 1% of responses

  1. DeepSeek28.0%
  2. Perplexity21.4%
  3. Grok19.1%
  4. Meta AI18.3%
  5. Microsoft Copilot14.2%
  6. Mistral Vibe13.5%
  7. Claude12.5%
  8. Gemini6.2%
  9. Google AI Overviews3.3%
  10. ChatGPT2.5%
  11. All assistants16.8%
Sources
dosimeteraudit.org/benchmarkHollow square: a share that a later measurement no longer shows
World

Germany

United States soon
20 September 2026 · questions in German

AssistantResponses to our test questions citing at least one listed source632 responses of Dosimeter1 square is 1% of responses

  1. PerplexityWeb version, default model20.0%20 September · Cited Russia Today, Anti-Spiegel, NachDenkSeiten0.0%7 October, after Perplexity stated on 28 September that it had blocked the cited sites
  2. Meta AIWeb version, default model10.0%Cited Apolut, NachDenkSeiten
  3. Microsoft CopilotWeb version, default model3.0%Cited Compact
  4. ChatGPTWeb version with search, default model1.0%Cited Sputnik
  5. GeminiWeb version, default model0.0%
  6. Google AI OverviewsGoogle Search0.0%
  7. Google AI ModeGoogle Search, AI Mode0.0%
dosimeteraudit.org/benchmarkListed source: EU sanctions list, Pravda network lists, outlets with documented links to Russia Today

Cases found by journalists and researchers

These are public responses with Kremlin propaganda that journalists and researchers found

DeepSeek2 cases
Perplexity1 case
Grok5 cases
  • October 2026Wrote in a public post on X that Ukraine, backed by NATO, is the aggressor · Grok on X
  • August 2026Summarised the news of sanctioned state outlets on request, with no refusal · Reporters Without Borders
  • October 2025Carried Kremlin state-attributed sources in 40% of responses about military recruitment in Ukraine · Institute for Strategic Dialogue
  • October 2025Used the Kremlin's term for the invasion in a public reply on X and blamed Kyiv for the war in Donbas · Grok on X
  • September 2025Gave 25 propaganda sources, among them Pravda, Sputnik and Baltnews · Re:Baltica
Meta AI1 case
  • July 2026Repeated the fake report about Ukrainian soldiers in France and credited it to Le Point · NPR and NewsGuard
Microsoft Copilot3 cases
  • June 2026Repeated a false claim about a Dane killed in Kryvyi Rih in Finnish, Danish and Slovenian · France 24 Observers
  • April 2025Answered yes to the same false claim in Danish, with the Danish Pravda site as its only source · NORDIS
  • March 2025Gave Pravda network content with no warning about the network · DFRLab and CheckFirst
Mistral Vibe4 cases
  • August 2026Found Sputnik and Russia Today content through other platforms when asked for sanctioned outlets · Reporters Without Borders
  • July 2026A Mistral model backed a false claim about Zelensky and cited the sanctioned site R-FBI · Euronews
  • June 2026At least 12 responses of Mistral models referred to sanctioned sources such as Russia Today and Sputnik · Euronews
  • April 2026Repeated false claims about the Iran war in 50% of tests in English and 57% in French, and cited a Pravda network page for one of them · NewsGuard
Claude5 cases
  • August 2026Summarised a Russia Today article on request · Reporters Without Borders
  • May 2026Used Pravda network domains seven times in news searches, in a study of Agora Digitale Transformation · Der Spiegel
  • April 2026Repeated the fake report about 20,000 deserters and cited a Pravda network page · NewsGuard
  • April 2026Confirmed a false figure of deaths on the Tisza river and cited a Pravda network page and a Russia Today article · NewsGuard
  • September 2025Cited Pravda, Russia Today, RIA Novosti, Sputnik and Izvestia in responses about the Baltic states · Re:Baltica
Gemini3 cases
  • August 2026Gave a summary of sanctioned outlets with links to Russia Today posts · Reporters Without Borders
  • April 2025Quoted Pravda network headlines in four Nordic languages with no warning · NORDIS
  • March 2025Gave Pravda network content with no warning about the network · DFRLab and CheckFirst
Google AI Overviews1 case
  • April 2026Declared the fake Le Point story about 20,000 deserters to be true and cited the fake report · NewsGuard

Colleagues' work

The board also rests on the published measurements of colleagues who counter disinformation

These are 2,003 responses from 9 published reports

Method

We ask test questions, not everyday ones: debunked false claims, claims that the Pravda network published on the same day, and topics with little reliable coverage, which researchers call data voids

We count a response if it shows at least one Kremlin-linked source

Kremlin-linked sources are:

The Germany board counts only the two lists and the outlets with documented links to Russia Today

ChatGPT folds part of its sources into groups: the sources shown in the response text are counted
Overall dataset: 2,446 responses collected · 18,525 cited sources checked

Data and scripts of the Germany measurement

  • EU Funding & Tenders PortalParticipant Register, Participant ID (PIC) 862736819

    Portal managed byEuropean Commission

  • Research dataResponses, cited sources and scripts

    Persistent identifierDOI 10.5281/zenodo.22925952

    LicenceData: CC BY 4.0 · Scripts: EUPL-1.2, the open-source licence of the European Union

  • Sources classified by official listsEU Council Regulation 833/2014, Annex XV

    Network listsVIGINUM · CheckFirst

  • Cryptographic sealQuestions and source lists are fixed before the first response

    GitHubgithub.com/gurovdigital

  • GDPR complianceNo cookies, no visitor profiles, anonymous visit statistics

    RegulationGeneral Data Protection Regulation (EU) 2016/679

  • EU AI Act complianceData handled by humans

    FrameworksRegulation (EU) 2024/1689 · Ethics Guidelines for Trustworthy AI