We poll AI models, not people.
Ask AI models the same questions, on a schedule, and watch how their answers move.
Write a poll, choose the models, and fund it. Mind Polling asks each model through its API, many times per question, and keeps every prompt, setting and raw answer, so a result can be checked, cited and rerun.
Many samples, with ranges
Models are random. Each question is asked several times per model, and every share comes with its sample size and a 95% range.
Everything on the record
The exact prompt, the option order, the settings, the model that actually answered and its raw reply, for every answer.
The API, not the app
We measure each model as offered through its API under stated settings. That is reproducible, and it is not the same as what a chat app shows.