Abstract We evaluate the Google WeatherNext Cyclone (WN‐C) ensemble and ensemble mean TC intensity performance for all storms between June 2022 and May 2026 and compare Google’s model against select operational models, such as the Hurricane Analysis and Forecast System (HAFS), Statistical Hurricane Intensity Prediction Scheme Rapid Intensification Index (SHIPS‐RII), and Rapid Intensification Prediction Aid (RIPA). Results indicate WN‐C has comparable, if not better, performance metrics. WN‐C’s ensemble mean has a lower mean absolute error than the HAFS model at all forecast hours. The model is comparable to the SHIPS‐RII and better than RIPA in terms of reliability of probabilistic rapid intensification (RI) forecasts over the first 24‐hr forecast period. However, the WN‐C ensemble is generally underdispersive and shows a negative bias in intensity change forecasts, including an underprediction of RI, that increases in magnitude with forecast lead time.