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.

Overview since July 20, 2026: 14 weeks, 915 answers in the latest week.

Download the full dossier (PDF)MethodPress kit

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.

ShareXLinkedInImage

5/6

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

ShareXLinkedInImage

21%

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

ShareXLinkedInImage

18%

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

ShareXLinkedInImage

+6

David Lisnard gains 6 points in a week: named in 14% of the answers.

ShareXLinkedInImage

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

Since July

The race, week after week

Share of the AIs' answers naming each candidate, each week. Switch to "named first" to see who the AIs put ahead.

Candidates:
0 %20 %40 %60 %80 %Jul 20Aug 3Aug 17Aug 31Sep 14Sep 28Oct 12Oct 1975 %Mélenchon70 %Le Pen66 %Philippe56 %Glucksmann46 %Attal

* not running.

Base: 14 weeks since July 20, 2026, consumer AIs only.

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

Each AI’s verdict

Who each AI names, week after week

One row per AI, one cell per week, in the colour of the candidate the AI named first most often. When the colour changes along a row, the AI changed its mind.

Le favori

ChatGPT
Perplexity
Gemini
Copilot
Google AI Mode
LeChat
Jul 20Aug 3Aug 17Aug 31Sep 14Sep 28Oct 12Oct 19
  • Marine Le Pen
  • Édouard Philippe
  • No clear name

Qui va gagner

ChatGPT
Perplexity
Gemini
Copilot
Google AI Mode
LeChat
Jul 20Aug 3Aug 17Aug 31Sep 14Sep 28Oct 12Oct 19
  • Marine Le Pen
  • No clear name

Qui pourrait devenir président

ChatGPT
Perplexity
Gemini
Copilot
Google AI Mode
LeChat
Jul 20Aug 3Aug 17Aug 31Sep 14Sep 28Oct 12Oct 19
  • Édouard Philippe
  • Gabriel Attal
  • Marine Le Pen
  • No clear name

Les principaux candidats

ChatGPT
Perplexity
Gemini
Copilot
Google AI Mode
LeChat
Jul 20Aug 3Aug 17Aug 31Sep 14Sep 28Oct 12Oct 19
  • Édouard Philippe
  • Marine Le Pen
  • Gabriel Attal
  • No clear name

En tête des intentions de vote

ChatGPT
Perplexity
Gemini
Copilot
Google AI Mode
LeChat
Jul 20Aug 3Aug 17Aug 31Sep 14Sep 28Oct 12Oct 19
  • Marine Le Pen
  • Jean-Luc Mélenchon
  • No clear name

Qui progresse

ChatGPT
Perplexity
Gemini
Copilot
Google AI Mode
LeChat
Jul 20Aug 3Aug 17Aug 31Sep 14Sep 28Oct 12Oct 19
  • Marine Le Pen
  • Jean-Luc Mélenchon
  • Édouard Philippe
  • Gabriel Attal
  • Raphaël Glucksmann
  • No clear name

Ce que disent les sondages

ChatGPT
Perplexity
Gemini
Copilot
Google AI Mode
LeChat
Jul 20Aug 3Aug 17Aug 31Sep 14Sep 28Oct 12Oct 19
  • Marine Le Pen
  • No clear name

Le plus présidentiable

ChatGPT
Perplexity
Gemini
Copilot
Google AI Mode
LeChat
Jul 20Aug 3Aug 17Aug 31Sep 14Sep 28Oct 12Oct 19
  • Marine Le Pen
  • Édouard Philippe
  • Gabriel Attal
  • No clear name

Inspire le plus confiance

ChatGPT
Perplexity
Gemini
Copilot
Google AI Mode
LeChat
Jul 20Aug 3Aug 17Aug 31Sep 14Sep 28Oct 12Oct 19
  • Édouard Philippe
  • Marine Le Pen
  • No clear name

Consumer AIs only, 14 weeks.

The sources

Where the AIs get their facts, week after week

The links the AIs cite in support of their answers, by type of site, as a share of each week’s total.

Jul 20Aug 3Aug 17Aug 31Sep 14Sep 28Oct 12Oct 19
  • Media
  • Poll aggregators
  • Polling institutes
  • Wikipedia
  • Institutions
  • Other sites

Only links cited in the answer count; pages consulted during the search are excluded.

Week by week

Every edition in detail

Each week has its edition: the verdicts question by question, the bars by question family, the sources and the PDF dossier.

No. 14 · wk 43Week of October 19, 2026915 answersOpen the edition ›No. 13 · wk 42Week of October 12, 2026803 answersOpen the edition ›No. 12 · wk 41Week of October 5, 2026624 answersOpen the edition ›No. 11 · wk 40Week of September 28, 2026615 answersOpen the edition ›No. 10 · wk 39Week of September 21, 2026610 answersOpen the edition ›No. 9 · wk 38Week of September 14, 2026617 answersOpen the edition ›No. 8 · wk 37Week of September 7, 2026623 answersOpen the edition ›No. 7 · wk 36Week of August 31, 2026620 answersOpen the edition ›No. 6 · wk 35Week of August 24, 2026683 answersOpen the edition ›No. 5 · wk 34Week of August 17, 2026770 answersOpen the edition ›No. 4 · wk 33Week of August 10, 2026770 answersOpen the edition ›No. 3 · wk 32Week of August 3, 2026330 answersOpen the edition ›No. 2 · wk 31Week of July 27, 2026627 answersOpen the edition ›No. 1 · wk 30Week of July 20, 2026550 answersOpen the edition ›

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

Who the AIs nameWho the AIs nameHow each AI answersHow each AI answersWhere the sources come fromWhere the sources come fromFigure of the weekFigure of the week

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.

AI election barometer: France 2027 | Sapian Metrics