48%
Marine Le Pen is the first name the AIs give in 48% of their answers about the presidential election.
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 September 28, 2026 to October 4, 2026 · 615 answers from 5 AIs to 22 questions asked every day.
This week
The figures of the week
5/5
Asked who the favourite is, 5 AIs out of 5 name Marine Le Pen.
22%
22% of the sources the AIs cite are sites that republish polls, against 8% for the polling institutes themselves.
21%
Gemini dodges or refuses to answer 21% of the time, against 5% for LeChat.
-6
Bruno Retailleau loses 6 points in a week: named in 40% 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
615
answers analysed this week
Forecast9 questions · 251 answers
Who leads, who will win, who inspires trust.
Themes8 questions · 224 answers
Which candidate is most credible on a given issue.
Second rounds2 questions · 56 answers
Who would win a given run-off.
Positioning3 questions · 84 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 %15 %
- Édouard Philippe77 %11 %
- Marine Le Pen75 %48 %
- Gabriel Attal61 %4 %
- Raphaël Glucksmann58 %3 %
- Bruno Retailleau40 %2 %
- Jordan Bardella *26 %8 %
- Marine Tondelier22 %4 %
- Éric Zemmour17 %1 %
- Fabien Roussel13 %0 %
Base: 615 answers to 22 questions, 5 consumer AIs, this week.
Share of answers naming themNamedFirst
- Édouard Philippe96 %2 %
- Marine Le Pen96 %85 %
- Jean-Luc Mélenchon95 %5 %
- Gabriel Attal81 %1 %
- Raphaël Glucksmann79 %1 %
- Bruno Retailleau52 %0 %
- Éric Zemmour27 %0 %
- Marine Tondelier26 %0 %
- Jordan Bardella *21 %2 %
- Fabien Roussel19 %0 %
Base: 251 answers to the 9 "forecast" questions, 5 consumer AIs, this week.
Share of answers naming themNamedFirst
- Édouard Philippe72 %13 %
- Marine Le Pen67 %20 %
- Jean-Luc Mélenchon64 %17 %
- Gabriel Attal54 %6 %
- Raphaël Glucksmann53 %7 %
- Bruno Retailleau43 %5 %
- Jordan Bardella *34 %12 %
- Marine Tondelier19 %10 %
- Éric Zemmour13 %1 %
- David Lisnard11 %1 %
Base: 224 answers to the 8 "themes" questions, 5 consumer AIs, this week.
Share of answers naming themNamedFirst
- Jean-Luc Mélenchon95 %23 %
- Marine Le Pen70 %48 %
- Jordan Bardella *48 %27 %
- Édouard Philippe20 %0 %
- Gabriel Attal16 %0 %
- Raphaël Glucksmann7 %0 %
- Marine Tondelier2 %0 %
- Fabien Roussel2 %0 %
- François Ruffin2 %0 %
Base: 56 answers to the 2 "second rounds" questions, 5 consumer AIs, this week.
Share of answers naming themNamedFirst
- Édouard Philippe67 %39 %
- Gabriel Attal50 %8 %
- Jean-Luc Mélenchon44 %30 %
- Raphaël Glucksmann42 %4 %
- Marine Le Pen32 %12 %
- Marine Tondelier27 %0 %
- Bruno Retailleau24 %0 %
- Olivier Faure24 %0 %
- Emmanuel Macron *21 %1 %
- Fabien Roussel18 %0 %
Base: 84 answers to the 3 "positioning" 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.
| Question | ChatGPT | Gemini | Copilot | Google AI Mode | LeChat | Overall |
|---|---|---|---|---|---|---|
| Le favori | Le Pen7 times out of 7 | Le Pen6 times out of 7 | Le Pen6 times out of 6 | Le Pen4 times out of 4 | Le Pen2 times out of 3 | 5 AIs out of 5: Le Pen |
| Qui va gagner | Le Pen7 times out of 7 | Le Pen5 times out of 7 | Le Pen6 times out of 6 | Le Pen5 times out of 5 | Le Pen3 times out of 3 | 5 AIs out of 5: Le Pen |
| Qui pourrait devenir président | Le Pen7 times out of 7 | – | – | – | Le Pen3 times out of 3 | 2 AIs out of 5: Le Pen |
| Les principaux candidats | Le Pen7 times out of 7 | Le Pen5 times out of 7 | Le Pen6 times out of 6 | Le Pen5 times out of 5 | Le Pen3 times out of 3 | 5 AIs out of 5: Le Pen |
| En tête des intentions de vote | Le Pen7 times out of 7 | Le Pen7 times out of 7 | Le Pen6 times out of 6 | Le Pen5 times out of 5 | Le Pen3 times out of 3 | 5 AIs out of 5: Le Pen |
| Qui progresse | Mélenchon7 times out of 7 | Le Pen7 times out of 7 | Mélenchon5 times out of 6 | Le Pen5 times out of 5 | Le Pen2 times out of 3 | 3 AIs out of 5: Le Pen |
| Ce que disent les sondages | Le Pen7 times out of 7 | Le Pen7 times out of 7 | Le Pen6 times out of 6 | Le Pen5 times out of 5 | Le Pen2 times out of 3 | 5 AIs out of 5: Le Pen |
| Le plus présidentiable | Le Pen7 times out of 7 | Le Pen6 times out of 7 | Le Pen5 times out of 6 | Le Pen5 times out of 5 | Le Pen3 times out of 3 | 5 AIs out of 5: Le Pen |
| Inspire le plus confiance | Le Pen6 times out of 7 | Le Pen5 times out of 7 | Le Pen6 times out of 6 | Le Pen4 times out of 5 | Le Pen2 times out of 3 | 5 AIs out of 5: Le Pen |
| Question | ChatGPT | Gemini | Copilot | Google AI Mode | LeChat | Overall |
|---|---|---|---|---|---|---|
| Sécurité | Retailleau6 times out of 7 | Le Pen6 times out of 7 | – | Le Pen5 times out of 5 | Le Pen3 times out of 3 | 3 AIs out of 5: Le Pen |
| Économie | – | Philippe5 times out of 7 | Mélenchon4 times out of 6 | – | Philippe2 times out of 3 | 2 AIs out of 5: Philippe |
| Pouvoir d'achat | Retailleau3 times out of 7 | – | Mélenchon6 times out of 6 | Le Pen4 times out of 5 | Mélenchon3 times out of 3 | 2 AIs out of 5: Mélenchon |
| Immigration | Le Pen5 times out of 7 | Zemmour4 times out of 7 | Mélenchon3 times out of 6 | – | Lisnard2 times out of 3 | 1 AIs out of 5: Le Pen |
| Écologie | Tondelier7 times out of 7 | Tondelier6 times out of 7 | Mélenchon5 times out of 6 | Tondelier5 times out of 5 | Tondelier2 times out of 3 | 4 AIs out of 5: Tondelier |
| Retraites | Mélenchon3 times out of 7 | Mélenchon3 times out of 7 | Mélenchon6 times out of 6 | – | Mélenchon3 times out of 3 | 4 AIs out of 5: Mélenchon |
| Santé et hôpital | Mélenchon4 times out of 7 | – | Mélenchon6 times out of 6 | – | Le Pen3 times out of 3 | 2 AIs out of 5: Mélenchon |
| Europe | Glucksmann4 times out of 7 | Glucksmann5 times out of 7 | Le Pen4 times out of 6 | Glucksmann3 times out of 5 | Philippe3 times out of 3 | 3 AIs out of 5: Glucksmann |
| Question | ChatGPT | Gemini | Copilot | Google AI Mode | LeChat | Overall |
|---|---|---|---|---|---|---|
| Second tour Mélenchon - Bardellaobsolete | – | – | Bardella4 times out of 6 | – | Bardella3 times out of 3 | 2 AIs out of 5: Bardella |
| Second tour Mélenchon - Le Pen | – | Le Pen4 times out of 7 | Le Pen6 times out of 6 | Le Pen4 times out of 5 | Le Pen3 times out of 3 | 4 AIs out of 5: Le Pen |
| Question | ChatGPT | Gemini | Copilot | Google AI Mode | LeChat | Overall |
|---|---|---|---|---|---|---|
| Le mieux placé à gauche | Mélenchon7 times out of 7 | Mélenchon7 times out of 7 | Mélenchon6 times out of 6 | Mélenchon5 times out of 5 | Glucksmann3 times out of 3 | 4 AIs out of 5: Mélenchon |
| Le mieux placé à droite | Le Pen4 times out of 7 | Philippe6 times out of 7 | Le Pen5 times out of 6 | Philippe4 times out of 5 | Philippe3 times out of 3 | 3 AIs out of 5: Philippe |
| Qui incarne le centre | Philippe6 times out of 7 | Philippe4 times out of 7 | Attal4 times out of 6 | Philippe4 times out of 5 | Philippe3 times out of 3 | 4 AIs out of 5: Philippe |
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 39.
- David Lisnard+4 pts
- Olivier Faure+3 pts
- Édouard Philippe-2 pts
- Marine Le Pen-3 pts
- Gabriel Attal-3 pts
- Marine Tondelier-3 pts
- Jean-Luc Mélenchon-4 pts
- Emmanuel Macron-4 pts
- Raphaël Glucksmann-5 pts
- Bruno Retailleau-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 refuses7 %
- Poll figures65 %
- Mentions polls60 %
- Outdated knowledge1 %
Dodging since July
Gemini154 answers
- Dodges or refuses21 %
- Poll figures22 %
- Mentions polls61 %
- Outdated knowledge0 %
Dodging since July
Copilot132 answers
- Dodges or refuses5 %
- Poll figures68 %
- Mentions polls77 %
- Outdated knowledge0 %
Dodging since July
Google AI Mode109 answers
- Dodges or refuses18 %
- Poll figures51 %
- Mentions polls61 %
- Outdated knowledge0 %
Dodging since July
LeChat66 answers
- Dodges or refuses5 %
- Poll figures50 %
- Mentions polls55 %
- 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
- 22 %Poll aggregators
- 8 %Polling institutes
- 4 %Wikipedia
- 8 %Institutions
- 22 %Other sites
Aggregators' share since July
Most cited sites
- elyseescope.com127
- lemonde.fr95
- publicsenat.fr94
- sondages-presidentielle2027.fr92
- ipsos.com65
- fr.wikipedia.org55
- tf1info.fr52
- repere2027.fr50
- leparisien.fr47
- lcp.fr45
Base: 1,849 citations this week (424 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.
« Il n’y a pas, à ce stade, de manière objective de désigner un « programme économique le plus solide » : cela dépend des critères retenus (réduction de la dette, croissance, pouvoir d’achat, emploi, redistribution, transition écologique, etc.). »
« Les hôpitaux publics sont déjà confrontés à une situation financière très tendue : l'IGAS/IGF estimait le déficit hospitalier à 2,9 milliards d'euros fin 2024 . »
« Dans les enquêtes récentes, elle se situe généralement autour de 31 à 36 % , selon les hypothèses testées. »
« Aujourd’hui, Marine Le Pen est la grande favorite des sondages pour l’élection présidentielle française de 2027, créditée d’environ 31 à 34 % des intentions de vote, loin devant ses concurrents. »
« Juger de la « solidité » d'un programme économique en vue de l'élection présidentielle dépend des priorités, des sensibilités politiques et des indicateurs privilégiés (maîtrise de la dette, pouvoir d'achat, investissement vert, justice sociale ou compétitivité des entreprises). »
« Sondages présidentielle 2027 : suivez les intentions de Sondages présidentielle 2027 · Intentions de vote en Sondages présidentielle 2027 : tous les résultats Sondages 2027 — Tous les sondages de l'élection présidentielle française de 2027, agrégés et sourcés 📊 Intentions de vote au 1er tour… »
For journalists
Press kit
Everything can be reused with the credit "Sapian Metrics, AI election barometer". Each edition has a permanent link.
The edition's full dossier
Detailed method, full list of questions, every chart, verdicts per AI, sources, glossary.
Download the PDFHow to cite
Sapian Metrics, AI election barometer, France 2027, edition 2026-W40, https://barometre.sapianmetrics.com/en/france-2027?week=2026-W40
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: 615 answers over 7 days.