45%
Marine Le Pen is the first name the AIs give in 45% of their answers about the presidential election.
Sapian Metrics · AI barometer
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 21, 2026 to September 27, 2026 · 610 answers from 4 AIs to 22 questions asked every day.
This week
45%
Marine Le Pen is the first name the AIs give in 45% of their answers about the presidential election.
4/4
Asked who the favourite is, 4 AIs out of 4 name Marine Le Pen.
21%
21% of the sources the AIs cite are sites that republish polls, against 12% for the polling institutes themselves.
20%
Google AI Mode dodges or refuses to answer 20% of the time, against 4% for Copilot.
+7
Raphaël Glucksmann gains 7 points in a week: named in 62% of the answers.
The method in brief
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
4
consumer AIs asked: ChatGPT, Gemini, Copilot, Google AI Mode
Every day
since July 20, 2026, results aggregated each week
610
answers analysed this week
Forecast9 questions · 248 answers
Who leads, who will win, who inspires trust.
Themes8 questions · 223 answers
Which candidate is most credible on a given issue.
Second rounds2 questions · 56 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
The same candidate is not named the same way depending on the question. Pick a family of questions.
Base: 610 answers to 22 questions, 4 consumer AIs, this week.
Base: 248 answers to the 9 "forecast" questions, 4 consumer AIs, this week.
Base: 223 answers to the 8 "themes" questions, 4 consumer AIs, this week.
Base: 56 answers to the 2 "second rounds" questions, 4 consumer AIs, this week.
Base: 83 answers to the 3 "positioning" questions, 4 consumer AIs, this week.
Each AI's verdict
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 | Overall |
|---|---|---|---|---|---|
| Le favori | Le Pen7 times out of 7 | Le Pen7 times out of 7 | Le Pen7 times out of 7 | Le Pen7 times out of 7 | 4 AIs out of 4: Le Pen |
| Qui va gagner | Le Pen7 times out of 7 | Le Pen7 times out of 7 | Le Pen6 times out of 7 | Le Pen5 times out of 6 | 4 AIs out of 4: Le Pen |
| Qui pourrait devenir président | Le Pen7 times out of 7 | – | Le Pen5 times out of 7 | Le Pen4 times out of 6 | 3 AIs out of 4: Le Pen |
| Les principaux candidats | Le Pen6 times out of 7 | Le Pen6 times out of 7 | Le Pen5 times out of 7 | Le Pen3 times out of 7 | 4 AIs out of 4: Le Pen |
| En tête des intentions de vote | Le Pen7 times out of 7 | Le Pen7 times out of 7 | Le Pen7 times out of 7 | Le Pen5 times out of 7 | 4 AIs out of 4: Le Pen |
| Qui progresse | Mélenchon7 times out of 7 | Le Pen7 times out of 7 | Mélenchon5 times out of 7 | Le Pen4 times out of 6 | 2 AIs out of 4: Le Pen |
| Ce que disent les sondages | Le Pen7 times out of 7 | Le Pen7 times out of 7 | Le Pen7 times out of 7 | Le Pen6 times out of 6 | 4 AIs out of 4: Le Pen |
| Le plus présidentiable | Le Pen7 times out of 7 | Le Pen6 times out of 7 | Le Pen6 times out of 7 | Le Pen7 times out of 7 | 4 AIs out of 4: Le Pen |
| Inspire le plus confiance | Le Pen7 times out of 7 | Le Pen6 times out of 7 | Le Pen7 times out of 7 | Le Pen4 times out of 7 | 4 AIs out of 4: Le Pen |
| Question | ChatGPT | Gemini | Copilot | Google AI Mode | Overall |
|---|---|---|---|---|---|
| Sécurité | Retailleau5 times out of 7 | Le Pen6 times out of 7 | Le Pen6 times out of 7 | Le Pen5 times out of 7 | 3 AIs out of 4: Le Pen |
| Économie | – | Attal3 times out of 7 | Le Pen3 times out of 7 | – | No dominant name |
| Pouvoir d'achat | Mélenchon3 times out of 7 | Le Pen5 times out of 7 | Mélenchon6 times out of 7 | – | 2 AIs out of 4: Mélenchon |
| Immigration | Le Pen6 times out of 7 | Le Pen4 times out of 7 | Le Pen4 times out of 7 | Zemmour6 times out of 7 | 3 AIs out of 4: Le Pen |
| Écologie | Tondelier7 times out of 7 | Tondelier7 times out of 7 | Mélenchon6 times out of 7 | Tondelier6 times out of 6 | 3 AIs out of 4: Tondelier |
| Retraites | Mélenchon4 times out of 7 | – | Mélenchon7 times out of 7 | – | 2 AIs out of 4: Mélenchon |
| Santé et hôpital | Mélenchon5 times out of 7 | – | Mélenchon7 times out of 7 | – | 2 AIs out of 4: Mélenchon |
| Europe | Glucksmann5 times out of 7 | Attal5 times out of 7 | Attal3 times out of 7 | – | 2 AIs out of 4: Attal |
| Question | ChatGPT | Gemini | Copilot | Google AI Mode | Overall |
|---|---|---|---|---|---|
| Second tour Mélenchon - Bardellaobsolete | – | – | Bardella6 times out of 7 | Bardella6 times out of 7 | 2 AIs out of 4: Bardella |
| Second tour Mélenchon - Le Pen | – | Le Pen4 times out of 7 | Le Pen7 times out of 7 | Le Pen7 times out of 7 | 3 AIs out of 4: Le Pen |
| Question | ChatGPT | Gemini | Copilot | Google AI Mode | Overall |
|---|---|---|---|---|---|
| Le mieux placé à gauche | Mélenchon6 times out of 7 | Mélenchon7 times out of 7 | Mélenchon5 times out of 7 | Mélenchon7 times out of 7 | 4 AIs out of 4: Mélenchon |
| Le mieux placé à droite | Le Pen4 times out of 7 | Philippe7 times out of 7 | Le Pen7 times out of 7 | Philippe6 times out of 7 | 2 AIs out of 4: Philippe |
| Qui incarne le centre | Philippe7 times out of 7 | Philippe6 times out of 7 | Attal5 times out of 7 | Philippe6 times out of 6 | 3 AIs out of 4: Philippe |
Consumer AIs only (4). Models queried through an API are shown apart, below.
In one week
Change in the share of answers naming the candidate, compared with week 38.
The AIs, one by one
The AIs do not answer the same way: some dodge, others quote polls as facts.
Sources
The links the AIs cite to support their answers, classified by type of site.
Most cited sites
Base: 1,785 citations this week (405 pages consulted but not cited, excluded).
In their words
Excerpts of the week's answers, one per behaviour and per AI, picked automatically.
« Il n'existe pas de consensus objectif ou de réponse définitive pour déterminer quel candidat possède le programme économique le plus « solide » pour l'élection présidentielle de 2027, la notion de « solidité » économique dépendant des orientations politiques, des priorités et des grilles de… »
« Les principaux favoris dans les sondages Marine Le Pen (Rassemblement national) : Elle est actuellement placée en tête des intentions de vote pour le premier tour dans la plupart des sondages nationaux, recueillant traditionnellement le score le plus élevé (autour de 34 % à 36 %). »
« Voici les principaux forces et candidats qui marquent les débats et les sondages : 1\. »
« Il n’existe pas, à ce stade, de façon objectivement démontrable de dire qu’un candidat a « le programme économique le plus solide » : cela dépend des critères retenus — réduction de la dette, croissance, pouvoir d’achat, emploi, fiscalité, réindustrialisation, soutenabilité budgétaire, etc. »
« Selon les derniers sondages de septembre 2026, Marine Le Pen est largement en tête des intentions de vote pour la présidentielle française de 2027, avec environ 33 à 35 % des suffrages. »
« À l'approche de l'élection présidentielle française de 2027, plusieurs personnalités politiques majeures se sont déjà déclarées candidates ou s'imposent comme des prétendants incontournables dans les sondages et le débat public . »
For journalists
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-W39, https://barometre.sapianmetrics.com/en/france-2027?week=2026-W39
Press contact: contact@sapianmetrics.com
Method and limits
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.
Consumer AIs: ChatGPT, 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.
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.
"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.
Each cited site is classified as media, polling institute, poll aggregator, Wikipedia, institution or other, from a fixed list published in the dossier.
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: 610 answers over 7 days.