Sapian Metrics · AI barometer

What the AIs say about the 2027 French presidential election

Millions of voters now ask an AI their political questions. Every day we ask the main assistants the same questions, the way a pollster surveys its panel, and we measure what they answer.

Week of October 12, 2026 to October 18, 2026 · 803 answers from 6 AIs to 22 questions asked every day.

This week

The figures of the week

44%

Marine Le Pen is the first name the AIs give in 44% of their answers about the presidential election.

5/6

Asked who the favourite is, 5 AIs out of 6 name Marine Le Pen.

22%

22% of the sources the AIs cite are sites that republish polls, against 4% for the polling institutes themselves.

18%

Gemini dodges or refuses to answer 18% of the time, against 1% for Copilot.

-6

Olivier Faure loses 6 points in a week: named in 4% of the answers.

The method in brief

How the barometer works

Like a poll, the barometer relies on a fixed questionnaire asked under the same conditions every day. Here, the respondents are AIs.

22

questions about the election, asked in French

6

consumer AIs asked: ChatGPT, Perplexity, Gemini, Copilot, Google AI Mode, LeChat

Every day

since July 20, 2026, results aggregated each week

803

answers analysed this week

Forecast9 questions · 327 answers

Who leads, who will win, who inspires trust.

Themes8 questions · 292 answers

Which candidate is most credible on a given issue.

Second rounds2 questions · 71 answers

Who would win a given run-off.

Positioning3 questions · 113 answers

Who embodies the left, the right, the centre.

The full list of questions is in the dossier. Download the PDF dossier

This week

Who the AIs name, and on which questions

The same candidate is not named the same way depending on the question. Pick a family of questions.

Share of answers naming themNamedFirst
  • Jean-Luc Mélenchon75 %16 %
  • Marine Le Pen71 %44 %
  • Édouard Philippe68 %10 %
  • Raphaël Glucksmann50 %6 %
  • Gabriel Attal45 %2 %
  • Bruno Retailleau34 %2 %
  • Jordan Bardella *24 %7 %
  • Marine Tondelier16 %4 %
  • Éric Zemmour13 %1 %
  • Emmanuel Macron *12 %3 %

Base: 803 answers to 22 questions, 6 consumer AIs, this week.

Each AI's verdict

For each question, the name each AI gives

For each question and each AI, the name the AI gave first most often this week, and how many times.

QuestionChatGPTPerplexityGeminiCopilotGoogle AI ModeLeChatOverall
Le favoriLe Pen7 times out of 7Le Pen5 times out of 5–Le Pen5 times out of 5Le Pen6 times out of 6Le Pen7 times out of 75 AIs out of 6: Le Pen
Qui va gagnerLe Pen5 times out of 7Le Pen5 times out of 5Le Pen7 times out of 7Le Pen2 times out of 4Le Pen7 times out of 7Le Pen7 times out of 76 AIs out of 6: Le Pen
Qui pourrait devenir présidentLe Pen7 times out of 7Le Pen4 times out of 5–Le Pen5 times out of 5Le Pen3 times out of 6Le Pen7 times out of 75 AIs out of 6: Le Pen
Les principaux candidatsLe Pen7 times out of 7Le Pen4 times out of 5Le Pen6 times out of 7Le Pen5 times out of 5Le Pen5 times out of 5Le Pen6 times out of 76 AIs out of 6: Le Pen
En tête des intentions de voteLe Pen7 times out of 7Le Pen5 times out of 5Mélenchon6 times out of 7Le Pen5 times out of 5Le Pen4 times out of 6Le Pen7 times out of 75 AIs out of 6: Le Pen
Qui progresseMélenchon4 times out of 7Glucksmann2 times out of 5Le Pen7 times out of 7Mélenchon3 times out of 4Glucksmann2 times out of 6Mélenchon4 times out of 73 AIs out of 6: Mélenchon
Ce que disent les sondagesLe Pen6 times out of 7Le Pen5 times out of 5Le Pen7 times out of 7Le Pen5 times out of 5Le Pen5 times out of 5Le Pen7 times out of 76 AIs out of 6: Le Pen
Le plus présidentiableLe Pen6 times out of 7Philippe3 times out of 4Le Pen6 times out of 7Le Pen4 times out of 4Le Pen5 times out of 5Le Pen7 times out of 75 AIs out of 6: Le Pen
Inspire le plus confianceLe Pen6 times out of 7Le Pen4 times out of 5Le Pen4 times out of 7Le Pen4 times out of 5Le Pen4 times out of 6Le Pen7 times out of 76 AIs out of 6: Le Pen

Consumer AIs only (6). Models queried through an API are shown apart, below.

In one week

Risers and fallers

Change in the share of answers naming the candidate, compared with week 41.

  • Marine Tondelier+4 pts
  • Raphaël Glucksmann+4 pts
  • Emmanuel Macron+3 pts
  • Éric Zemmour+3 pts
  • Gérald Darmanin-1 pts
  • Édouard Philippe-1 pts
  • Jordan Bardella-2 pts
  • David Lisnard-2 pts
  • Gabriel Attal-5 pts
  • Olivier Faure-6 pts

The AIs, one by one

How each AI answers

The AIs do not answer the same way: some dodge, others quote polls as facts.

ChatGPT154 answers
  • Dodges or refuses4 %
  • Poll figures73 %
  • Mentions polls64 %
  • Outdated knowledge0 %
Dodging since July
Perplexity108 answers
  • Dodges or refuses7 %
  • Poll figures35 %
  • Mentions polls66 %
  • Outdated knowledge0 %
Dodging since July
Gemini154 answers
  • Dodges or refuses18 %
  • Poll figures18 %
  • Mentions polls53 %
  • Outdated knowledge0 %
Dodging since July
Copilot103 answers
  • Dodges or refuses1 %
  • Poll figures72 %
  • Mentions polls79 %
  • Outdated knowledge0 %
Dodging since July
Google AI Mode130 answers
  • Dodges or refuses16 %
  • Poll figures48 %
  • Mentions polls65 %
  • Outdated knowledge0 %
Dodging since July
LeChat154 answers
  • Dodges or refuses6 %
  • Poll figures70 %
  • Mentions polls62 %
  • Outdated knowledge0 %
Dodging since July

Sources

Where the AIs get their facts

The links the AIs cite to support their answers, classified by type of site.

  • 44 %Media
  • 22 %Poll aggregators
  • 4 %Polling institutes
  • 3 %Wikipedia
  • 5 %Institutions
  • 21 %Other sites
Aggregators' share since July

Most cited sites

  • lemonde.fr138
  • elyseescope.com128
  • publicsenat.fr108
  • leparisien.fr74
  • reuters.com73
  • sondage-presidentielle.fr71
  • fr.wikipedia.org68
  • lefigaro.fr66
  • lcp.fr63
  • civiqo.fr61

Base: 2,337 citations this week (2,123 pages consulted but not cited, excluded).

In their words

What the AIs write

Excerpts of the week's answers, one per behaviour and per AI, picked automatically.

« En résumé, il n'y a pas de consensus objectif : Les électeurs cherchant une rupture ferme et un accent mis sur l'autorité répressive se tournent plus volontiers vers les propositions de Marine Le Pen ou de la droite. »
Gemini · October 12, 2026 · Dodges or refuses
« Raphaël Glucksmann Place publique — gauche sociale-démocrate Il vient de remporter, le 11 octobre 2026, la primaire de la gauche sociale-démocrate avec 66 % des voix. »
ChatGPT · October 12, 2026 · Poll figures
« Les sondages la placent régulièrement en tête sur ces questions, devant les candidats de la droite traditionnelle et du bloc central . »
LeChat · October 12, 2026 · Mentions polls
« Déterminer quel candidat possède le programme économique le "plus solide" relève d'un choix subjectif et dépend des priorités accordées à la réduction de la dette, à la préservation des services publics ou à la relance par le pouvoir d'achat. »
Google AI Mode · October 12, 2026 · Dodges or refuses
« Au 12 octobre 2026, Marine Le Pen (Rassemblement national) est en tête des intentions de vote pour le premier tour de la présidentielle 2027, avec une moyenne d’environ 33,9 % selon les derniers sondages publiés début octobre 2026. »
LeChat · October 12, 2026 · Poll figures
« Cependant, plusieurs personnalités politiques sont régulièrement mentionnées dans le débat public, à travers les intentions de vote ou les déclarations de candidature : Public Sénat Marine Le Pen (Rassemblement national) : Souvent placée en tête des intentions de vote dans les sondages pour le… »
Gemini · October 12, 2026 · Mentions polls

For journalists

Press kit

Everything can be reused with the credit "Sapian Metrics, AI election barometer". Each edition has a permanent link.

PDF

The edition's full dossier

Detailed method, full list of questions, every chart, verdicts per AI, sources, glossary.

Download the PDF

How to cite

Sapian Metrics, AI election barometer, France 2027, edition 2026-W42, https://barometre.sapianmetrics.com/en/france-2027?week=2026-W42

Press contact: contact@sapianmetrics.com

Method and limits

How we measure, and what we do not measure

What is measured

The barometer measures the answers AIs give voters, not voters' opinions. It says who the AIs name, who they put first, when they refuse to answer and which sources they rely on.

The AIs asked

Consumer AIs: ChatGPT, Perplexity, Gemini, Copilot, Google AI Mode, LeChat, queried through their public interfaces, like a user, every day since July 20, 2026. Models queried directly through an API, without web search, are shown apart and never added to the others.

How we count

A candidate is "named" when their name appears in the answer, and "named first" when they are the first candidate named. An AI's verdict on a question is the name it gives at the start of its answer; for a run-off, the one a winning verb is attached to. The same rules apply to every name and every AI; nothing is judged by hand or by another AI.

Behaviours

"Dodges or refuses", "poll figures", "mentions polls" and "outdated knowledge" are detected by fixed lists of French expressions. They describe how an AI answers, not whether the answer is right.

Sources

Each cited site is classified as media, polling institute, poll aggregator, Wikipedia, institution or other, from a fixed list published in the dossier.

Limits

AI answers vary from day to day and with the wording: that is why the questions are fixed and results are aggregated over a week. Collection gaps exist (Perplexity paused from 16 September to 13 October 2026, occasional errors on Copilot); rates always cover the answers actually collected. Grok is not covered for now. The barometer does not score the candidates and endorses no one.

This edition: 803 answers over 7 days.