The browser is the ballot.

Two surfaces, one model

What we measure

We measure on the official model APIs: the same question, the same settings, the same week, for every brand. Web search is on, so the models can draw on what is live on the web. Nothing is personalized to a user, which is what makes the columns comparable.

What we don’t

The consumer apps are a different surface. What a person sees inside a chat app can carry memory, personalization, and live experiments on top of the same model, so its answers can differ from the API’s. We do not measure that surface yet. True browser listings, recorded from the consumer apps, arrive with WDIR Ranked, the Pro product. WDIR Ranked · Coming soon

What Ranked adds.

• True browser listings

  Ranked will record rankings from the consumer chat apps themselves: what a person actually sees, with memory, personalization, and live experiments on top of the same model.

• API and browser, side by side

  The API column that runs the public index today, set next to the browser column, so any drift between the comparable record and the lived answer is visible in one view.

• Alerts when they disagree

  When the two columns crown a different brand, Ranked will tell you. Disagreement between the surfaces is the signal worth watching.