Was the forecast right for Paris on Tue Sep 15?
Paris, Île-de-France Region · daily high temperature in °C · forecasts from each model's archived runs, verified against the LFPB observations
14 days out, 4 models put Paris's Tue Sep 15 high anywhere from 17° to 32°; by the final call the field had settled to a median of 31°. The day verified at 33° against the LFPB observations — cloudy.
GFS landed closest, off by 0.6°. AIGFS ran 3° cold.
What every model said, at every lead
Daily-high calls for Tue Sep 15 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 Paris scoreboard shows them, labelled.
| Lead | AIFS | AIGFS | ECMWF | GEM | GFS | ICON | UKMO | Range |
|---|---|---|---|---|---|---|---|---|
| 15d · 2026-08-31 | — | 18° | — | — | 33° | — | — | 18–33° |
| 14d · 2026-09-01 | 19° | 17° | 18° | — | 32° | — | — | 17–32° |
| 13d · 2026-09-02 | 19° | 20° | 20° | — | 25° | — | — | 19–25° |
| 12d · 2026-09-03 | 24° | 17° | 21° | — | 29° | — | — | 17–29° |
| 11d · 2026-09-04 | 21° | 20° | 20° | — | 27° | — | — | 20–27° |
| 10d · 2026-09-05 | 18° | 24° | 20° | — | 25° | — | — | 18–25° |
| 9d · 2026-09-06 | 20° | 22° | 22° | 25° | 26° | — | — | 20–26° |
| 8d · 2026-09-07 | 23° | 21° | 23° | 20° | 27° | — | — | 20–27° |
| 7d · 2026-09-08 | 25° | 25° | 27° | 24° | 29° | — | — | 24–29° |
| 6d · 2026-09-09 | 25° | 25° | 26° | 25° | 29° | 28° | — | 25–29° |
| 5d · 2026-09-10 | 24° | 26° | 28° | 29° | 31° | 24° | 29° | 24–31° |
| 4d · 2026-09-11 | 27° | 26° | 29° | 30° | 30° | 28° | 25° | 25–30° |
| 3d · 2026-09-12 | 29° | 29° | 30° | 31° | 31° | 30° | 31° | 29–31° |
| 2d · 2026-09-13 | 30° | 29° | 31° | 31° | 32° | 30° | 31° | 29–32° |
| 1d · 2026-09-14 | 30° | 29° | 32° | 31° | 32° | 32° | 31° | 29–32° |
| 0d · 2026-09-15 | 31° | 30° | 32° | 31° | 32° | 32° | 31° | 30–32° |
| actual | 33° |
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 Paris — 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 LFPB observations. Archive depth varies by city; receipts exist only for dates the archive watched arrive.