Seven models. Same prompt. Same public data. Some calls that held up. One that needs an asterisk. And a surprise from the Governor's race that the framework got partly right — and partly wrong.
Ahead of California’s June 2 primary, seven AI models were given the same public election data and asked to interpret two of the state’s highest-profile races: the Los Angeles mayoral contest and the California governor’s race. The experiment used public signals only — search visibility, news framing, social momentum, visible proof, and polling context — not private campaign data or proprietary polling.
There's a pattern emerging in 2026 that's easy to dismiss as noise and that's exactly why most brands are missing it.
This will close in 0 seconds
This will close in 0 seconds
This will close in 0 seconds
This will close in 0 seconds
This will close in 0 seconds
This will close in 0 seconds
This will close in 0 seconds
This will close in 0 seconds
This will close in 0 seconds
This will close in 0 seconds
