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 5, 2026 to October 11, 2026 · 624 answers from 5 AIs to 22 questions asked every day.

This week

The figures of the week

46%

Marine Le Pen is the first name the AIs give in 46% of their answers about the presidential election.

4/5

Asked who the favourite is, 4 AIs out of 5 name Marine Le Pen.

18%

18% of the sources the AIs cite are sites that republish polls, against 8% for the polling institutes themselves.

18%

Google AI Mode dodges or refuses to answer 18% of the time, against 3% for LeChat.

-11

Gabriel Attal loses 11 points in a week: named in 50% 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

5

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

Every day

since July 20, 2026, results aggregated each week

624

answers analysed this week

Forecast9 questions · 256 answers

Who leads, who will win, who inspires trust.

Themes8 questions · 228 answers

Which candidate is most credible on a given issue.

Second rounds2 questions · 57 answers

Who would win a given run-off.

Positioning3 questions · 83 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 Mélenchon73 %14 %
  • Marine Le Pen71 %46 %
  • Édouard Philippe69 %11 %
  • Gabriel Attal50 %2 %
  • Raphaël Glucksmann47 %6 %
  • Bruno Retailleau33 %1 %
  • Jordan Bardella *26 %5 %
  • Marine Tondelier13 %3 %
  • David Lisnard10 %1 %
  • Éric Zemmour10 %1 %

Base: 624 answers to 22 questions, 5 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.

QuestionChatGPTGeminiCopilotGoogle AI ModeLeChatOverall
Le favoriLe Pen7 times out of 7–Le Pen1 times out of 1Le Pen6 times out of 6Le Pen7 times out of 74 AIs out of 5: Le Pen
Qui va gagnerLe Pen7 times out of 7Le Pen7 times out of 7Le Pen1 times out of 1Le Pen7 times out of 7Le Pen7 times out of 75 AIs out of 5: Le Pen
Qui pourrait devenir présidentLe Pen7 times out of 7–––Le Pen7 times out of 72 AIs out of 5: Le Pen
Les principaux candidatsLe Pen7 times out of 7Attal4 times out of 7Le Pen1 times out of 1Le Pen5 times out of 7Le Pen7 times out of 74 AIs out of 5: Le Pen
En tête des intentions de voteLe Pen7 times out of 7Mélenchon3 times out of 7Le Pen1 times out of 1Le Pen5 times out of 7Le Pen7 times out of 74 AIs out of 5: Le Pen
Qui progresseMélenchon4 times out of 7Le Pen7 times out of 7Mélenchon1 times out of 1–Le Pen4 times out of 72 AIs out of 5: Le Pen
Ce que disent les sondagesLe Pen7 times out of 7Le Pen7 times out of 7Le Pen1 times out of 1Le Pen6 times out of 6Le Pen6 times out of 75 AIs out of 5: Le Pen
Le plus présidentiableLe Pen7 times out of 7Le Pen7 times out of 7Le Pen1 times out of 1Le Pen5 times out of 7Le Pen7 times out of 75 AIs out of 5: Le Pen
Inspire le plus confianceLe Pen6 times out of 7Le Pen7 times out of 7Le Pen1 times out of 1Le Pen4 times out of 6Le Pen5 times out of 75 AIs out of 5: Le Pen

Consumer AIs only (5). 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 40.

  • François Ruffin-2 pts
  • Jean-Luc Mélenchon-3 pts
  • Marine Le Pen-3 pts
  • Fabien Roussel-6 pts
  • Éric Zemmour-7 pts
  • Bruno Retailleau-7 pts
  • Édouard Philippe-7 pts
  • Marine Tondelier-9 pts
  • Raphaël Glucksmann-11 pts
  • Gabriel Attal-11 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 refuses3 %
  • Poll figures69 %
  • Mentions polls62 %
  • Outdated knowledge0 %
Dodging since July
Gemini154 answers
  • Dodges or refuses12 %
  • Poll figures23 %
  • Mentions polls55 %
  • Outdated knowledge0 %
Dodging since July
Copilot22 answers
  • Dodges or refuses5 %
  • Poll figures77 %
  • Mentions polls73 %
  • Outdated knowledge0 %
Dodging since July
Google AI Mode140 answers
  • Dodges or refuses18 %
  • Poll figures41 %
  • Mentions polls59 %
  • Outdated knowledge0 %
Dodging since July
LeChat154 answers
  • Dodges or refuses3 %
  • Poll figures58 %
  • Mentions polls58 %
  • 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.

  • 36 %Media
  • 18 %Poll aggregators
  • 8 %Polling institutes
  • 6 %Wikipedia
  • 9 %Institutions
  • 22 %Other sites
Aggregators' share since July

Most cited sites

  • elyseescope.com113
  • fr.wikipedia.org84
  • lemonde.fr79
  • publicsenat.fr72
  • ipsos.com70
  • tf1info.fr65
  • touteleurope.eu54
  • leparisien.fr46
  • linternaute.com45
  • sondage-presidentielle.fr42

Base: 1,664 citations this week (359 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 2027, plusieurs personnalités politiques françaises sont déjà officiellement candidates à la présidentielle, mais il est impossible de dire aujourd’hui qui deviendra président avant les résultats officiels. »
Copilot · October 5, 2026 · Dodges or refuses
« Il est déjà officiellement candidat et arrive actuellement deuxième dans plusieurs scénarios de sondage, autour de 16 % dans une enquête récente. »
ChatGPT · October 5, 2026 · Poll figures
« À ce stade précoce de la campagne pour 2027, aucun sondage spécifique récent ne désigne un gagnant incontesté sur la seule "crédibilité sécurité", celle-ci se confondant largement avec la notoriété globale des leaders de la droite et du Rassemblement national sur ces sujets régaliens. »
Google AI Mode · October 5, 2026 · Mentions polls
« Il est impossible de désigner objectivement un programme économique « le plus solide » pour l'élection présidentielle de 2027, dans la mesure où la notion de solidité dépend des orientations politiques, des priorités et des modèles économiques que l'on privilégie. »
Google AI Mode · October 5, 2026 · Dodges or refuses
« Public Sénat Voici un aperçu des dynamiques observées dans les enquêtes récentes (notamment à l'automne 2026) : YouTube En tête au premier tour : Marine Le Pen recueille généralement entre 30% et 34% des suffrages selon les instituts et les hypothèses de candidatures testées. »
Gemini · October 5, 2026 · Poll figures
« À la date du 4 octobre 2026 , les sondages disponibles placent Marine Le Pen (Rassemblement national) en tête des intentions de vote pour le premier tour de la présidentielle de 2027 . »
ChatGPT · October 5, 2026 · Mentions polls

For journalists

Press kit

Everything can be reused with the credit "Sapian Metrics, AI election barometer" (CC BY 4.0 licence). 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-W41, https://barometre.sapianmetrics.com/en/france-2027?week=2026-W41

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, 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: 624 answers over 7 days.