This page provides an overview of regional forecast skill for the SON 2025 period. Forecast scores are updated automatically every week throughout the competitive period. The current data includes forecasts initialized between Thursday 14th August 2025 and Thursday 14th August 2025 (inclusive). For a detailed description of the outputs, please refer to the section's overview.
Regional skill score files
All regional RPSSs are available to download via the following link:
SON 2025 Regional RPSSs (Excel format)
Regional scores for the top 10 teams of global, period-aggregated, variable-averaged RPSSs
| Team name | Team rank | Model name | Model rank | Global | Tropics | NHem. ExTro. | SHem. ExTro. | NHem. Polar | SHem. Polar | Europe | N. Amer. | S. Amer. | Africa | Asia | Oceania |
|---|
| AIFS | 1 | AIFShera | 1 | 0.087 | 0.108 | 0.083 | -0.059 | 0.044 | 0.024 | 0.092 | -0.028 | 0.055 | 0.057 | 0.147 | 0.061 | | AIFS | 1 | AIFSgaia | 3 | 0.081 | 0.133 | 0.05 | -0.08 | 0.034 | -0.024 | 0.091 | -0.074 | -0.03 | 0.139 | 0.156 | 0.035 | | AIFS | 1 | AIFSthalassa | 6 | 0.075 | 0.129 | 0.037 | -0.127 | 0.029 | -0.05 | 0.039 | -0.046 | -0.113 | 0.128 | 0.129 | 0.061 | | CMAandFDU | 2 | FengshunAdjust | 2 | 0.085 | 0.171 | 0.015 | -0.073 | 0.005 | -0.022 | 0.063 | -0.024 | 0.095 | 0.054 | 0.113 | 0.053 | | CMAandFDU | 2 | FengshunHybrid | 7 | 0.064 | 0.125 | 0.002 | -0.047 | 0.046 | -0.021 | 0.037 | -0.026 | -0.064 | 0.107 | 0.122 | -0.023 | | CMAandFDU | 2 | Fengshun | 10 | 0.035 | 0.086 | -0.006 | -0.082 | 0.048 | -0.041 | 0.066 | -0.041 | -0.008 | 0.03 | 0.083 | 0.104 | | MicroEnsemble | 3 | MicroDuet | 4 | 0.077 | 0.108 | 0.049 | -0.022 | 0.032 | 0.065 | 0.105 | -0.002 | -0.019 | 0.063 | 0.109 | 0.092 | | MicroEnsemble | 3 | StillLearning | 5 | 0.077 | 0.102 | 0.058 | -0.009 | 0.04 | 0.064 | 0.119 | -0.004 | -0.002 | 0.056 | 0.113 | 0.082 | | MicroEnsemble | 3 | Huracan | 9 | 0.047 | 0.044 | 0.06 | -0.045 | 0.02 | 0.069 | 0.104 | -0.005 | -0.09 | -0.015 | 0.099 | 0.04 | | LP | 4 | LPM | 8 | 0.062 | 0.083 | 0.061 | -0.014 | 0.024 | 0.017 | 0.087 | 0.019 | 0.032 | 0.021 | 0.092 | -0.021 | | KITKangu | 5 | KanguPlusPlus | 11 | 0.0 | -0.0 | -0.0 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0 | -0.0 | 0.0 | -0.0 | | KITKangu | 5 | KanguParametricPrediction | 11 | 0.0 | -0.0 | -0.0 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0 | -0.0 | 0.0 | -0.0 | | scienceAI | 5 | findforecast | 11 | 0.0 | -0.0 | -0.0 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0 | -0.0 | 0.0 | -0.0 | | scienceAI | 5 | zephyr | 11 | 0.0 | -0.0 | -0.0 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0 | -0.0 | 0.0 | -0.0 | | scienceAI | 5 | ngcm | 11 | 0.0 | -0.0 | -0.0 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0 | -0.0 | 0.0 | -0.0 | | KITKangu | 5 | KanguS2SEasyUQ | 39 | -1.235 | -1.34 | -1.045 | -1.357 | -1.094 | -1.265 | -1.194 | -0.876 | -1.493 | -1.446 | -1.178 | -1.673 | | CliMA | 7 | CliMAWeather | 16 | -0.04 | -0.039 | -0.052 | -0.24 | -0.037 | 0.063 | 0.011 | -0.087 | -0.151 | -0.024 | -0.019 | -0.137 | | CliMA | 7 | CliMAWeather2 | 17 | -0.04 | -0.041 | -0.049 | -0.238 | -0.039 | 0.068 | 0.008 | -0.086 | -0.159 | -0.025 | -0.017 | -0.129 | | WindBorne | 8 | WeatherMesh | 18 | -0.125 | -0.082 | -0.206 | -0.259 | -0.153 | -0.132 | -0.202 | -0.187 | -0.14 | -0.184 | -0.141 | -0.358 | | FengWuW2S | 9 | FengWu2 | 19 | -0.26 | -0.135 | -0.434 | -0.255 | -0.471 | -0.25 | -0.732 | -0.042 | -0.124 | -0.452 | -0.491 | -0.126 | | FengWuW2S | 9 | FengWu | 22 | -0.33 | -0.385 | -0.331 | -0.388 | -0.27 | -0.177 | -0.462 | -0.162 | -0.524 | -0.629 | -0.393 | -0.269 | | Sibyl | 10 | ClimSDE | 20 | -0.298 | -0.344 | -0.306 | -0.515 | -0.19 | -0.364 | -0.277 | -0.186 | -0.28 | -0.519 | -0.315 | -0.572 |
|
| Team name | Team rank | Model name | Model rank | Global | Tropics | NHem. ExTro. | SHem. ExTro. | NHem. Polar | SHem. Polar | Europe | N. Amer. | S. Amer. | Africa | Asia | Oceania |
|---|
| CMAandFDU | 1 | FengshunAdjust | 1 | 0.061 | 0.117 | 0.029 | 0.002 | 0.033 | -0.014 | 0.003 | 0.058 | 0.133 | 0.11 | 0.072 | 0.129 | | CMAandFDU | 1 | FengshunHybrid | 2 | 0.053 | 0.08 | 0.032 | 0.028 | 0.025 | 0.02 | 0.01 | 0.027 | 0.06 | 0.065 | 0.077 | 0.047 | | CMAandFDU | 1 | Fengshun | 14 | -0.002 | 0.001 | 0.006 | 0.029 | 0.053 | -0.08 | 0.006 | -0.024 | 0.007 | -0.077 | 0.042 | 0.078 | | MicroEnsemble | 2 | StillLearning | 3 | 0.051 | 0.099 | 0.006 | 0.039 | 0.045 | -0.022 | -0.019 | 0.019 | 0.095 | 0.083 | 0.055 | 0.094 | | MicroEnsemble | 2 | MicroDuet | 4 | 0.045 | 0.087 | 0.0 | 0.047 | 0.042 | -0.013 | -0.026 | 0.046 | 0.114 | 0.017 | 0.044 | 0.103 | | MicroEnsemble | 2 | Huracan | 8 | 0.009 | 0.021 | -0.017 | 0.053 | 0.032 | -0.044 | -0.047 | 0.032 | 0.048 | -0.06 | 0.001 | 0.059 | | LP | 3 | LPM | 5 | 0.036 | 0.056 | 0.026 | 0.044 | 0.022 | -0.059 | -0.002 | 0.036 | 0.077 | 0.024 | 0.066 | 0.006 | | AIFS | 4 | AIFSgaia | 6 | 0.024 | 0.04 | -0.013 | 0.032 | 0.029 | 0.029 | -0.017 | -0.051 | 0.118 | 0.009 | 0.033 | 0.009 | | AIFS | 4 | AIFShera | 7 | 0.009 | 0.014 | -0.02 | 0.005 | 0.045 | -0.015 | 0.009 | -0.083 | 0.078 | 0.007 | 0.019 | 0.061 | | AIFS | 4 | AIFSthalassa | 15 | -0.005 | -0.028 | 0.0 | -0.007 | 0.021 | 0.026 | 0.013 | -0.046 | 0.04 | -0.08 | 0.03 | -0.117 | | KITKangu | 5 | KanguPlusPlus | 9 | 0.0 | -0.0 | -0.0 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0 | -0.0 | 0.0 | -0.0 | | KITKangu | 5 | KanguParametricPrediction | 9 | 0.0 | -0.0 | -0.0 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0 | -0.0 | 0.0 | -0.0 | | scienceAI | 5 | findforecast | 9 | 0.0 | -0.0 | -0.0 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0 | -0.0 | 0.0 | -0.0 | | scienceAI | 5 | zephyr | 9 | 0.0 | -0.0 | -0.0 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0 | -0.0 | 0.0 | -0.0 | | scienceAI | 5 | ngcm | 9 | 0.0 | -0.0 | -0.0 | -0.0 | 0.0 | 0.0 | 0.0 | 0.0 | -0.0 | -0.0 | 0.0 | -0.0 | | KITKangu | 5 | KanguS2SEasyUQ | 39 | -1.39 | -1.441 | -1.309 | -0.861 | -1.343 | -1.442 | -1.219 | -1.261 | -1.532 | -1.509 | -1.364 | -1.174 | | CliMA | 7 | CliMAWeather | 16 | -0.1 | -0.138 | -0.114 | -0.127 | -0.031 | 0.024 | -0.122 | -0.12 | -0.117 | -0.269 | -0.103 | 0.089 | | CliMA | 7 | CliMAWeather2 | 17 | -0.106 | -0.142 | -0.123 | -0.138 | -0.037 | 0.02 | -0.134 | -0.133 | -0.13 | -0.278 | -0.102 | 0.09 | | FengWuW2S | 8 | FengWu2 | 18 | -0.264 | -0.203 | -0.457 | 0.008 | -0.308 | -0.054 | -0.301 | -0.058 | -0.098 | -0.276 | -0.616 | -0.282 | | FengWuW2S | 8 | FengWu | 20 | -0.35 | -0.476 | -0.363 | -0.106 | -0.205 | 0.007 | -0.271 | -0.139 | -0.587 | -0.678 | -0.472 | -0.333 | | NordicS2S | 9 | NordicS2S1 | 19 | -0.315 | -0.342 | -0.24 | -0.25 | -0.161 | -0.439 | -0.153 | -0.165 | -0.283 | -0.584 | -0.259 | -0.272 | | NordicS2S | 9 | NordicS2S3 | 27 | -0.527 | -0.778 | -0.28 | -0.111 | -0.328 | -0.427 | -0.321 | -0.477 | -0.704 | -0.923 | -0.413 | -0.589 | | NordicS2S | 9 | NordicS2S2 | 29 | -0.606 | -0.731 | -0.654 | -0.764 | -0.222 | -0.092 | -0.37 | -0.669 | -0.78 | -0.854 | -0.503 | -0.553 | | Sibyl | 10 | ClimSDE | 21 | -0.386 | -0.392 | -0.319 | -0.779 | -0.261 | -0.506 | -0.276 | -0.345 | -0.634 | -0.409 | -0.22 | -0.299 |
|
Figures showing aggregated RPSSs for best-performing model from top 10 teams