All four Mistral models evaluated by the Institute of the Estonian Language were deemed likely to use Russian propaganda in their answers.
Europe’s most prominent artificial intelligence (AI) model is among the most vulnerable to Russian propaganda, a new study showed.
ADVERTISEMENT
ADVERTISEMENT
Researchers at the Institute of the Estonian Language asked 60 models of popular AI chatbots, including four versions of Mistral AI, OpenAI’s ChatGPT and Anthropic’s Claude, a series of 75 questions in three language to gauge how likely the models are to promote Russian propaganda or how filter out Kremlin talking points.
The work covered 14 themes, such as oft-repeated incorrect claims that Russia was legitimately evacuating Ukrainian children from war zones and that NATO broke promises not to expand east after German reunification.
The answers were then scored on a scale of 1-5, with 5 indicating a balanced response and 1 indicating an amplification of misleading or false claims.
All four Mistral versions measured in the study scored less than 40% in their ability to detect Kremlin lines across all areas analysed. The study also found that at least 12 of Mistral’s answers referred to sanctioned sources widely considered to be purveyors of pro-Russian reporting, such as Russia Today or Sputnik News.
Mistral is often seen as Europe’s main competitor to US giants Anthropic and Claude, but this is not the first time that it has failed testing for Russian propaganda.
An April 2026 analysis by NewsGuard, a US rating system for news sites, found that Mistral’s Le Chat repeated Russian falsehoods 50% of the time in English and 56.6% of the time in French. They include falsehoods about Russia, Iran and China.
According to Newsguard, the Pravda network or Portal Kombat, a network of websites composed of 370 sites, including 286 active as of April 2026, “seems to be aimed at flooding search engines and responses of AI chatbots with Russian propaganda” and is the likely culprit behind Mistral’s pro-Russian slant.
Euronews Next reached out to Mistral for this story but did not receive an immediate reply.
Earlier this year the French government signed an agreement with Mistral to integrate its AI technologies into the armed forces, directorates, services and public entities.
The company has also signed deals with major defence manufacturer Airbus, car company BMW and the government of Luxembourg.
