Verified forecast accuracy
Which weather model predicts snow best?
Across SnowSure's verification window, Météo-France is the most accurate snowfall-forecast model in the Alps (accuracy 71.8/100).
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
7,425,869 verified rows · 556 resorts
2024-01-01 → 2026-09-04 · Ground truth: SNOTEL, resort-reported totals, ERA5
As of 2026-09-04 · n = 7,425,869
Most accurate model by region
Per-model accuracy (overall)
| Region | Model | Accuracy | MAE (cm) | Samples |
|---|---|---|---|---|
| the Rockies | Météo-France | 81.2/100 | 3.75 | 3,759 |
| the Rockies | ECMWF | 78.8/100 | 4.24 | 15,092 |
| the Rockies | ICON | 78.5/100 | 4.3 | 7,252 |
| the Rockies | JMA | 77.8/100 | 4.44 | 12,065 |
| the Rockies | GEM | 77.5/100 | 4.51 | 10,847 |
| the Rockies | GFS | 77.1/100 | 4.57 | 15,524 |
| Cascades | ICON | 77/100 | 4.6 | 951 |
| Cascades | Météo-France | 75.3/100 | 4.95 | 491 |
| Cascades | ECMWF | 74.1/100 | 5.18 | 1,967 |
| Cascades | JMA | 72.6/100 | 5.48 | 1,567 |
| Cascades | GEM | 72.1/100 | 5.59 | 1,411 |
| the Alps | Météo-France | 71.3/100 | 5.74 | 760 |
| Cascades | GFS | 71.1/100 | 5.78 | 2,000 |
| the Alps | ICON | 68.4/100 | 6.32 | 1,320 |
| Sierra | Météo-France | 67.7/100 | 6.45 | 159 |
| the Alps | ECMWF | 66.2/100 | 6.76 | 2,541 |
| the Alps | GEM | 65.3/100 | 6.95 | 1,692 |
| the Alps | GFS | 64.9/100 | 7.01 | 2,560 |
| the Alps | JMA | 62.3/100 | 7.54 | 2,039 |
| Sierra | ICON | 56.5/100 | 8.69 | 318 |
| Sierra | GEM | 54.8/100 | 9.04 | 468 |
| Sierra | GFS | 54.2/100 | 9.15 | 683 |
| Sierra | ECMWF | 54/100 | 9.2 | 683 |
| Sierra | JMA | 53.3/100 | 9.34 | 527 |
| the Andes | Météo-France | 48.5/100 | 10.3 | 560 |
| the Andes | JMA | 47.8/100 | 10.44 | 1,820 |
| the Andes | ICON | 47.3/100 | 10.53 | 1,092 |
| the Andes | GEM | 45.8/100 | 10.85 | 1,632 |
| the Andes | ECMWF | 44.7/100 | 11.07 | 2,306 |
| the Andes | GFS | 42.7/100 | 11.46 | 2,366 |
| Southern Alps | Météo-France | 33.2/100 | 13.36 | 679 |
| Southern Alps | ICON | 32.9/100 | 13.42 | 1,190 |
| Southern Alps | ECMWF | 32.4/100 | 13.52 | 2,325 |
| Southern Alps | GFS | 31.7/100 | 13.66 | 2,373 |
| Southern Alps | GEM | 29.9/100 | 14.02 | 1,530 |
| Southern Alps | JMA | 29.8/100 | 14.03 | 1,867 |
Lower MAE = closer to observed snowfall. Accuracy is the inverse-error score (0–100). Source: SnowSure forecast verification, updated 2026-09-04.
See also: does blending models beat the best single one? · Forecast Trust
