Google AI Model Ranks #1 in CDC FluSight Forecasting for 2025-26 Season

A flu forecasting model built with Google AI secured the top ranking in the CDC's FluSight competition for the 2025-26 season. The Centers for Disease Control announced this week that Google's best submission most accurately matched observed hospital admissions, outperforming 38 other eligible models from government, industry, and academic teams.

Forecasting Methodology

The FluSight initiative runs from October through May, combining weekly submissions to predict U.S. hospital admissions for the current week and three weeks into the future. The CDC uses these combined forecasts to communicate anticipated state-level demand for medical services.

Underlying Technology

Google's forecasts were developed using Empirical Research Assistance (ERA), an AI tool designed to generate optimization algorithms across various scientific fields. Research on ERA was recently published in the journal Nature, and the underlying technology is now available to trusted testers as part of Google's experimental science tools.