Overview » Leaderboards

Leaderboards

View team rankings and model performance for period-aggregated and weekly RPSS.  The teams are ranked according to their best performing model. 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 forecasts in the ECMWF-hosted sub-seasonal AI forecasting portal.

Please note:

The leaderboards and model scores evolution graphs include dynamical model skill based on forecast data downloaded 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.
Teams 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 that the team submitted a climatology-based forecast (i.e. a uniform 20% probability assigned to each quintile bin).

Further resources:

Guide to the Leaderboards page.
Guide to the ECMWF-hosted sub-seasonal AI forecasting porta l.
Evaluation System (for RPSS calculation details).

Period-aggregated RPSSs

Team Rank	Model Rank	Team name Model name	Period-aggregated RPSSs
Team Rank	Model Rank	Team name Model name

Show Less

Select up to 10 teams.

Select up to 10 models. The choises are structured as follows:

Team nameModel name

Please note: A score of 0.0 corresponds to climatology (i.e. a uniform 20% forecast for each quintile bin). Values above 0 indicate better skill compared to climatology, while values below 0 indicate worse skill.

Weekly RPSSs