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 19, 2026 to October 25, 2026 · 915 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.

21%

21% of the sources the AIs cite are sites that republish polls, against 7% for the polling institutes themselves.

18%

Gemini dodges or refuses to answer 18% of the time, against 3% for Copilot.

+6

David Lisnard gains 6 points in a week: named in 14% 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

915

answers analysed this week

Forecast9 questions · 374 answers

Who leads, who will win, who inspires trust.

Themes8 questions · 333 answers

Which candidate is most credible on a given issue.

Second rounds2 questions · 82 answers

Who would win a given run-off.

Positioning3 questions · 126 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 Pen70 %44 %
  • Édouard Philippe66 %8 %
  • Raphaël Glucksmann56 %7 %
  • Gabriel Attal46 %3 %
  • Bruno Retailleau35 %2 %
  • Marine Tondelier22 %4 %
  • Jordan Bardella *21 %7 %
  • Éric Zemmour16 %1 %
  • David Lisnard14 %1 %

Base: 915 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 Pen7 times out of 7–Le Pen7 times out of 7Le Pen6 times out of 7Le Pen7 times out of 75 AIs out of 6: Le Pen
Qui va gagnerLe Pen5 times out of 7Le Pen7 times out of 7Le Pen7 times out of 7Le Pen6 times out of 6Le 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 Pen5 times out of 7–Le Pen6 times out of 6Le Pen6 times out of 7Le Pen7 times out of 75 AIs out of 6: Le Pen
Les principaux candidatsLe Pen7 times out of 7Le Pen7 times out of 7Le Pen7 times out of 7Le Pen6 times out of 7Le Pen6 times out of 7Le Pen7 times out of 76 AIs out of 6: Le Pen
En tête des intentions de voteLe Pen7 times out of 7Le Pen7 times out of 7–Le Pen7 times out of 7Le Pen6 times out of 7Le Pen7 times out of 75 AIs out of 6: Le Pen
Qui progresseGlucksmann3 times out of 7Glucksmann4 times out of 7Le Pen4 times out of 7Mélenchon6 times out of 7–Glucksmann7 times out of 73 AIs out of 6: Glucksmann
Ce que disent les sondagesLe Pen7 times out of 7Le Pen7 times out of 7Le Pen7 times out of 7Le Pen6 times out of 7Le Pen6 times out of 7Le Pen7 times out of 76 AIs out of 6: Le Pen
Le plus présidentiableLe Pen6 times out of 7Le Pen7 times out of 7Le Pen6 times out of 7Le Pen6 times out of 7Le Pen6 times out of 7Le Pen7 times out of 76 AIs out of 6: Le Pen
Inspire le plus confianceLe Pen6 times out of 7Le Pen6 times out of 7Le Pen5 times out of 7Le Pen5 times out of 5Le Pen5 times out of 7Le 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 42.

  • David Lisnard+6 pts
  • Marine Tondelier+6 pts
  • Raphaël Glucksmann+6 pts
  • Fabien Roussel+3 pts
  • Éric Zemmour+3 pts
  • François Hollande+2 pts
  • Nicolas Dupont-Aignan+2 pts
  • Gabriel Attal+2 pts
  • Emmanuel Macron-2 pts
  • Jordan Bardella-3 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 refuses5 %
  • Poll figures68 %
  • Mentions polls67 %
  • Outdated knowledge0 %
Dodging since July
Perplexity154 answers
  • Dodges or refuses8 %
  • Poll figures37 %
  • Mentions polls66 %
  • Outdated knowledge0 %
Dodging since July
Gemini154 answers
  • Dodges or refuses18 %
  • Poll figures17 %
  • Mentions polls48 %
  • Outdated knowledge0 %
Dodging since July
Copilot145 answers
  • Dodges or refuses3 %
  • Poll figures77 %
  • Mentions polls72 %
  • Outdated knowledge0 %
Dodging since July
Google AI Mode154 answers
  • Dodges or refuses12 %
  • Poll figures49 %
  • Mentions polls63 %
  • Outdated knowledge0 %
Dodging since July
LeChat154 answers
  • Dodges or refuses5 %
  • Poll figures72 %
  • Mentions polls60 %
  • 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.

  • 39 %Media
  • 21 %Poll aggregators
  • 7 %Polling institutes
  • 4 %Wikipedia
  • 5 %Institutions
  • 24 %Other sites
Aggregators' share since July

Most cited sites

  • elyseescope.com144
  • lemonde.fr117
  • touteleurope.eu108
  • publicsenat.fr100
  • sondage-presidentielle.fr97
  • elabe.fr92
  • leparisien.fr92
  • france-vote.fr87
  • sondages-presidentielle2027.fr84
  • lcp.fr80

Base: 2,926 citations this week (2,986 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 fin de compte, il n'y a pas de consensus absolu : la « crédibilité » dépend des attentes de chaque citoyen, qu'il privilégie la fermeté pénale, la prévention sociale ou l'efficacité opérationnelle des forces de l'ordre. »
Gemini · October 19, 2026 · Dodges or refuses
« Arrive en tête des intentions de vote (35–38 %), malgré ses problèmes judiciaires. »
Copilot · October 19, 2026 · Poll figures
« Si l’on parle de la crédibilité perçue sur la sécurité , Bruno Retailleau semble en tête : un sondage cité en juin 2026 le plaçait devant Édouard Philippe et Gabriel Attal sur ce sujet. »
Perplexity · October 19, 2026 · Mentions polls
« À la date du 19 octobre 2026, il n’existe pas de réponse objective unique à la question de savoir quel candidat a le programme économique le plus solide pour la présidentielle française de 2027. »
ChatGPT · October 19, 2026 · Dodges or refuses
« Elle arrive largement en tête dans tous les sondages récents, avec des intentions de vote oscillant entre 32 % et 38 % au premier tour, selon les instituts et les hypothèses de candidature. »
LeChat · October 19, 2026 · Poll figures
« Selon les analyses portées par le parti et ses soutiens, la priorité est donnée à une fermeté accrue, à la tolérance zéro, à la maîtrise de l'immigration et au rétablissement de l'autorité de l'État, des axes qui s'attirent traditionnellement un fort assentiment dans les classements d'intentions… »
Google AI Mode · October 19, 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-W43, https://barometre.sapianmetrics.com/en/france-2027?week=2026-W43

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: 915 answers over 7 days.