How we ran this study

We wanted to know what ChatGPT, Gemini, Google AI Mode and Google AI Overviews say when a voter asks them about the 2026 New Zealand general election: how they explain the election, which parties they bring up, how they compare policies, where their information comes from, and whether what they say is right.

This is the third edition. The questions, voters, assistants and settings are the same as on 5 and 12 October, so differences between editions are differences in the answers, not in what we asked.

The study is neutral. No party is the focus, every registered party is treated the same way, and we take no view on any party or policy. We report what the assistants said.

Each question is written as a particular person would ask it. We described 23 households by their circumstances: their housing, work, income, caring responsibilities and access to services. We added nine people in particular locations, from a West Auckland renter to a Queenstown hospitality worker.

Each voter's priorities are our design assumptions for that situation. They are not findings about everyone in that group.

Every question was asked as a standalone conversation, so we captured the first answer a voter would get. The four assistants received identical wording.

The 31 local questions were asked twice: once with no location, and once from the voter's own location. That gives 205 question-and-location combinations and 820 planned answers per edition.

NZBrands.ai runs its studies on Onsomble, the platform that asks AI assistants questions at scale and records what they say. The study is set up as a topic with no focal entity, so no party is singled out, with every party on the Electoral Commission's register tracked. For this edition Onsomble re-ran the same saved setup: each question through the assistants' ordinary consumer apps, every answer saved in full, and for each answer the claims it made, which parties each claim was about, and the websites the assistant drew on.

We downloaded the complete record after the run and built every figure on this site from it. The script that does so is in the site's code, so the tables can be rebuilt from the saved files without running the study again.

Every ChatGPT, Gemini and AI Mode answer was saved. For 27 question-and-location combinations Google produced no AI Overview: 26 asked nationally and one asked from Dunedin. The record does not say why. A missing Overview is left missing; it never counts as an answer that named no party.

123 of the 124 national-and-location pairs came back complete. Following the 20 October identity corrections, 61 pairs named different parties; the location comparison uses those 123 pairs.

Every change compares the same question, assistant and location on 12 and 16 October. There are 792 matched answers. The headline covers all 17 tracked parties: 531 answers changed their party line-up. Charts display seven parties, the six parliamentary parties plus Opportunity; that narrower set changes in 528 answers. The seven-party scope is labelled beside the charts.

Assistants are compared on the 177 question-and-location combinations where all four answered in every edition, 708 answers per edition. A missing Overview never changes which questions are compared. Whole-edition counts, such as how many answers were saved, use all 793.

Locations are compared only within the 123 pairs where the question was identical. We never rank locations against each other on different questions.

The eight voting-guidance questions were read in full for all 31 answers and coded by hand for what each answer did. The definitions of two codes, asking the voter about their priorities and giving a shortlist, were tightened in this edition, so those two rows are not compared with Edition 2 as change rates. For each of the 32 voters we read the answer to their main question on both dates and wrote up what changed.

We selected 18 propositions worth checking: recurring consequential claims and new issues found while reading. Twelve of them appear as statements in this edition's answers, and those twelve are in the ledger: six are supported by the source, two are contradicted by it, two could not be resolved, and two leave out a qualification the source makes. The other six propositions are not stated in this edition's answers and are not shown as checks.

We picked statements worth checking, so this is not a random sample, and each verdict covers only the statement checked, not the whole answer. A statement that is right today may still be out of date in an older answer.

Each question was asked once per edition. AI assistants vary their answers, so part of any change between editions is that variation rather than a lasting shift. Three editions show what changed; they do not show why. News events, what the assistants retrieved and changes to the assistants themselves all remain possible explanations.

The voters are designed situations, not a sample of New Zealanders. The study shows what the assistants said and lets anyone check it. It does not show whether anyone changed their vote.

We read all 31 voting-guidance answers and each voter's main question in full, and checked 12 statements. We have not read all 793 answers in full or checked every policy claim.

On 20 October, an identity review removed ten false party matches: five in Edition 2 and five in Edition 3. The corrections exclude a Taranaki Alliance business initiative and generic uses of National for government levels, policy instruments and nationwide manifestos. Current comparisons restate both editions consistently. Historical pages and raw captures remain unchanged.

The archive holds all 793 answers, the 174 questions with their tags, the claims and sources Onsomble recorded, the guidance coding, the checks, the location pairs and the edition-to-edition comparisons, with file fingerprints so anyone can check the evidence has not changed since collection. Editions 1 and 2 keep their own archives and pages.