Was the forecast right for Milan on Thu Sep 3?
Milan, Lombardy · daily high temperature in °C · forecasts from each model's archived runs, verified against the LIML observations
12 days out, 4 models put Milan's Thu Sep 3 high anywhere from 22° to 27°; by the final call the field had settled to a median of 33°. The day verified at 32° against the LIML observations — partly cloudy.
AIGFS landed closest, off by 0.6°. ECMWF ran 1° hot.
What every model said, at every lead
Daily-high calls for Thu Sep 3 as each model's runs approached it — the last archived run per day. NBM and The Spread's own blend are consensus products and stay out of these ranges and rankings; the Milan scoreboard shows them, labelled.
| Lead | AIFS | AIGFS | ECMWF | GEM | GFS | ICON | UKMO | Range |
|---|---|---|---|---|---|---|---|---|
| 12d · 2026-08-22 | 27° | 27° | 22° | — | 26° | — | — | 22–27° |
| 11d · 2026-08-23 | 22° | 33° | 25° | — | 31° | — | — | 22–33° |
| 10d · 2026-08-24 | 29° | 29° | 23° | — | 24° | — | — | 23–29° |
| 9d · 2026-08-25 | 29° | 33° | 28° | 32° | 32° | — | — | 28–33° |
| 8d · 2026-08-26 | 28° | 34° | 28° | 32° | 30° | — | — | 28–34° |
| 7d · 2026-08-27 | 28° | 27° | 28° | 31° | 27° | — | — | 27–31° |
| 6d · 2026-08-28 | 28° | 30° | 27° | 26° | 28° | 30° | 28° | 26–30° |
| 5d · 2026-08-29 | 29° | 30° | 30° | 31° | 32° | 30° | 29° | 29–32° |
| 4d · 2026-08-30 | 29° | 32° | 33° | 32° | 32° | 31° | 31° | 29–33° |
| 3d · 2026-08-31 | 30° | 31° | 32° | 32° | 32° | 31° | 32° | 30–32° |
| 2d · 2026-09-01 | 30° | 32° | 33° | 32° | 33° | 32° | 32° | 30–33° |
| 1d · 2026-09-02 | 31° | 32° | 33° | 32° | 32° | 33° | 33° | 31–33° |
| 0d · 2026-09-03 | 31° | 33° | 33° | 33° | 33° | 33° | 33° | 31–33° |
| actual | 32° |
Read it honestly
This is one date, not a league table. A model can win a day it deserved to lose; rankings only mean something over a window. For that, see which model has been most accurate in Milan — or every city The Spread scores.
Forecasts are what each model's archived runs said at the time, captured at The Spread's sweep times — never reconstructed after the fact. Truth is the LIML observations. Archive depth varies by city; receipts exist only for dates the archive watched arrive.