Verified forecast accuracy
Which weather model predicts snow best?
Across SnowSure's verification window, Nbm is the most accurate snowfall-forecast model in the Alps (accuracy 87.4/100).
SnowSure scores every model against observed snowfall, by region and horizon — primary-source verification, recomputed weekly. Machine-readable: /api/v1/model-accuracy.
Forecast Trust — Verified, not guessed — corpus scale, blend vs best model, and the full record.
Verification corpus
10,140,390 verified rows · 592 resorts
2024-01-01 → 2026-10-18 · Ground truth: SNOTEL, resort-reported totals, ERA5
As of 2026-10-19 · n = 10,140,390
Most accurate model by region
Per-model accuracy (overall)
| Region | Model | Accuracy | MAE (cm) | Samples |
|---|---|---|---|---|
| Scandinavia | JMA | 89.9/100 | 2.03 | 41 |
| Scandinavia | GFS | 88.7/100 | 2.26 | 53 |
| the Alps | Nbm | 87.5/100 | 2.51 | 126 |
| Scandinavia | ECMWF | 87.1/100 | 2.58 | 53 |
| Scandinavia | GEM | 86.6/100 | 2.67 | 36 |
| the Rockies | Météo-France | 79.5/100 | 4.11 | 3,735 |
| the Rockies | Nbm | 77.2/100 | 4.56 | 7,875 |
| the Rockies | Nam | 76.8/100 | 4.64 | 892 |
| the Rockies | ECMWF | 76.4/100 | 4.73 | 15,041 |
| the Rockies | ICON | 76/100 | 4.8 | 7,217 |
| the Rockies | UKMO | 75.9/100 | 4.81 | 5,742 |
| the Rockies | JMA | 75.5/100 | 4.9 | 12,002 |
| the Rockies | GEM | 75.2/100 | 4.96 | 10,695 |
| the Alps | Météo-France | 74.6/100 | 5.08 | 2,144 |
| the Rockies | GFS | 74.3/100 | 5.15 | 15,448 |
| the Alps | UKMO | 73.7/100 | 5.26 | 3,605 |
| the Alps | Icon2i | 73.7/100 | 5.26 | 1,112 |
| Cascades | ICON | 73.6/100 | 5.28 | 681 |
| the Alps | ECMWF | 73.5/100 | 5.3 | 7,545 |
| the Alps | ICON | 73.5/100 | 5.3 | 3,814 |
| the Alps | Meteoswiss | 72.7/100 | 5.46 | 2,449 |
| the Alps | GEM | 72.7/100 | 5.46 | 5,037 |
| the Alps | JMA | 71.9/100 | 5.63 | 5,997 |
| the Alps | GFS | 71.5/100 | 5.71 | 7,585 |
| Cascades | Météo-France | 70.6/100 | 5.88 | 355 |
| Cascades | UKMO | 70/100 | 6.01 | 638 |
| Cascades | ECMWF | 69.2/100 | 6.17 | 1,393 |
| Cascades | GEM | 68.2/100 | 6.37 | 1,009 |
| Cascades | GFS | 66.1/100 | 6.78 | 1,419 |
| Cascades | JMA | 65.9/100 | 6.83 | 1,118 |
| Sierra | Météo-France | 65.4/100 | 6.91 | 153 |
| Cascades | Nbm | 60.8/100 | 7.83 | 847 |
| Cascades | Nam | 58.9/100 | 8.21 | 96 |
| Sierra | Nbm | 56.4/100 | 8.72 | 350 |
| Sierra | Nam | 55.4/100 | 8.92 | 42 |
| Sierra | ICON | 53.9/100 | 9.21 | 306 |
| Southern Alps | Météo-France | 53.3/100 | 9.35 | 1,227 |
| Sierra | UKMO | 53.2/100 | 9.36 | 204 |
| Sierra | GEM | 51.7/100 | 9.67 | 450 |
| Southern Alps | ICON | 51.1/100 | 9.78 | 2,162 |
| Sierra | GFS | 51/100 | 9.8 | 657 |
| Sierra | ECMWF | 50.9/100 | 9.81 | 657 |
| Southern Alps | ECMWF | 50.6/100 | 9.88 | 4,278 |
| Sierra | JMA | 50.3/100 | 9.94 | 507 |
| Southern Alps | JMA | 49.5/100 | 10.1 | 3,366 |
| Southern Alps | GEM | 49.3/100 | 10.14 | 2,782 |
| Southern Alps | GFS | 49.1/100 | 10.18 | 4,312 |
| the Andes | Météo-France | 48.8/100 | 10.24 | 945 |
| the Andes | ECMWF | 46.6/100 | 10.67 | 4,046 |
| the Andes | ICON | 41.5/100 | 11.7 | 1,883 |
| the Andes | GFS | 40.2/100 | 11.96 | 4,061 |
| the Andes | JMA | 35.7/100 | 12.85 | 3,131 |
| the Andes | GEM | 25.1/100 | 14.99 | 2,741 |
Lower MAE = closer to observed snowfall. Accuracy is the inverse-error score (0–100). Source: SnowSure forecast verification, updated 2026-10-19.
See also: does blending models beat the best single one? · Forecast Trust
