Leaderboards
View team rankings and model performance for period-aggregated and weekly RPSS (see leaderboards guide). You can filter results by competitive period, week, forecast window, and variable(s), click a team name for details on participants and models, and click an RPSS to view corresponding forecasts in the ECMWF-hosted sub-seasonal AI forecasting portal (see portal guide).
Please note:
- Teams are ranked according to their best performing model.
- Models appear in the period-aggregated leaderboards only if they have submitted forecasts for the selected variable and forecast window for every week up to the chosen week.
- A score of 0.0 indicates a climatology-based forecast (i.e. a uniform 20% probability assigned to each quintile bin).
- Leaderboards and model scores evolution graphs also include dynamical model skill based on forecast data from the S2S Database. These entries are not associated with a registered team and thus appear without a rank (“N/A”). Details regarding forecast and reforecast configuration can be found on the following confluence page.
- Automated regional forecast evaluations is available on the following confluence page to provide model developers insights into geographical areas where forecasts may underperform.
