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 August 24, 2026 to August 30, 2026 · 683 answers from 5 AIs to 22 questions asked every day.

This week

The figures of the week

38%

Marine Le Pen is the first name the AIs give in 38% of their answers about the presidential election.

5/5

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

20%

20% 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 2% for Perplexity.

+12

Marine Le Pen gains 12 points in a week: named in 71% 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, Perplexity, Gemini, Copilot, Google AI Mode

Every day

since July 20, 2026, results aggregated each week

683

answers analysed this week

Forecast9 questions · 283 answers

Who leads, who will win, who inspires trust.

Themes8 questions · 244 answers

Which candidate is most credible on a given issue.

Second rounds2 questions · 62 answers

Who would win a given run-off.

Positioning3 questions · 94 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 Mélenchon77 %18 %
  • Édouard Philippe75 %9 %
  • Marine Le Pen71 %38 %
  • Gabriel Attal63 %6 %
  • Raphaël Glucksmann55 %4 %
  • Jordan Bardella *45 %11 %
  • Bruno Retailleau40 %3 %
  • Marine Tondelier20 %2 %
  • Emmanuel Macron *13 %2 %
  • Éric Zemmour10 %0 %

Base: 683 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.

QuestionChatGPTPerplexityGeminiCopilotGoogle AI ModeOverall
Le favoriLe Pen6 times out of 7Le Pen4 times out of 4Le Pen4 times out of 7Le Pen7 times out of 7Le Pen5 times out of 75 AIs out of 5: Le Pen
Qui va gagnerLe Pen7 times out of 7Le Pen2 times out of 2Le Pen6 times out of 7Le Pen7 times out of 7Le Pen6 times out of 75 AIs out of 5: Le Pen
Qui pourrait devenir présidentLe Pen7 times out of 7Le Pen2 times out of 3–Le Pen7 times out of 7–3 AIs out of 5: Le Pen
Les principaux candidatsLe Pen7 times out of 7Le Pen2 times out of 3Le Pen5 times out of 7Attal3 times out of 7Le Pen4 times out of 74 AIs out of 5: Le Pen
En tête des intentions de voteLe Pen7 times out of 7Le Pen2 times out of 4Le Pen5 times out of 7Le Pen7 times out of 7Le Pen6 times out of 75 AIs out of 5: Le Pen
Qui progresseMélenchon7 times out of 7Mélenchon1 times out of 2Le Pen6 times out of 7Mélenchon6 times out of 7–3 AIs out of 5: Mélenchon
Ce que disent les sondagesLe Pen7 times out of 7Le Pen4 times out of 4Le Pen5 times out of 7Le Pen7 times out of 7Le Pen7 times out of 75 AIs out of 5: Le Pen
Le plus présidentiableLe Pen6 times out of 7Le Pen4 times out of 5Le Pen5 times out of 7Le Pen4 times out of 7Le Pen5 times out of 75 AIs out of 5: Le Pen
Inspire le plus confianceLe Pen3 times out of 7Philippe3 times out of 4Le Pen5 times out of 7Le Pen7 times out of 7Le Pen4 times out of 74 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 34.

  • Marine Le Pen+12 pts
  • Raphaël Glucksmann+10 pts
  • Jean-Luc Mélenchon+10 pts
  • Gabriel Attal+8 pts
  • Édouard Philippe+7 pts
  • Marine Tondelier+2 pts
  • Yannick Jadot+2 pts
  • François Ruffin+2 pts
  • Gérald Darmanin-7 pts
  • Jordan Bardella-8 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 refuses2 %
  • Poll figures55 %
  • Mentions polls77 %
  • Outdated knowledge0 %
Dodging since July
Perplexity68 answers
  • Dodges or refuses2 %
  • Poll figures47 %
  • Mentions polls77 %
  • Outdated knowledge0 %
Dodging since July
Gemini154 answers
  • Dodges or refuses15 %
  • Poll figures16 %
  • Mentions polls66 %
  • Outdated knowledge0 %
Dodging since July
Copilot153 answers
  • Dodges or refuses2 %
  • Poll figures71 %
  • Mentions polls78 %
  • Outdated knowledge0 %
Dodging since July
Google AI Mode154 answers
  • Dodges or refuses18 %
  • Poll figures42 %
  • Mentions polls63 %
  • 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
  • 20 %Poll aggregators
  • 8 %Polling institutes
  • 5 %Wikipedia
  • 5 %Institutions
  • 19 %Other sites
Aggregators' share since July

Most cited sites

  • sondages-presidentielle2027.fr180
  • lemonde.fr149
  • elyseescope.com121
  • publicsenat.fr102
  • lcp.fr93
  • elabe.fr87
  • lefigaro.fr87
  • fr.wikipedia.org85
  • reuters.com82
  • votons-2027.fr72

Base: 2,318 citations this week (916 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.

« Pour suivre l'évolution des intentions de vote et les analyses concernant l'élection présidentielle française de 2027, vous pouvez consulter les publications d'instituts de sondage et d'information politique : Consultez les analyses et enquêtes d'opinion sur le site de Elabe . »
Gemini · August 24, 2026 · Dodges or refuses
« Juin 2026 ÉlyséeScope 2027 ÉlyséeScope Les principaux favoris selon les sondages Rassemblement national (RN) Marine Le Pen : créditée de 35 à 38 % des intentions de vote au premier tour selon RTL et Harris Interactive. »
Copilot · August 24, 2026 · Poll figures
« Les sondages le plaçaient très haut dans les hypothèses de premier tour. »
ChatGPT · August 24, 2026 · Mentions polls
« Il est impossible de désigner un candidat "le plus crédible" de manière objective, la crédibilité en politique dépendant des attentes des électeurs, de leur sensibilité et de l'importance qu'ils accordent à tel ou tel angle de réforme (moyens financiers, organisation territoriale, fin de la… »
Google AI Mode · August 24, 2026 · Dodges or refuses
« Marine Le Pen : autour de 34–35 % au premier tour dans les agrégations disponibles. »
ChatGPT · August 24, 2026 · Poll figures
« Le RN est favori des sondages : Le Pen et Bardella dominent les intentions de vote, mais la candidature définitive dépendra notamment de l’issue judiciaire concernant Le Présidentielle 2027 : tous les candidats déclarés — 👉 À noter : La liste des candidats peut évoluer d’ici au scrutin des 18… »
Copilot · August 24, 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-W35, https://barometre.sapianmetrics.com/en/france-2027?week=2026-W35

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, 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: 683 answers over 7 days.