Was the forecast right for Paris on Sat Sep 12?
Paris, Île-de-France Region · daily high temperature in °C · forecasts from each model's archived runs, verified against the LFPB observations
13 days out, 4 models put Paris's Sat Sep 12 high anywhere from 19° to 25°; by the final call the field had settled to a median of 24°. The day verified at 26° against the LFPB observations — cloudy.
GFS landed closest, off by 0.4°. AIGFS ran 2° cold.
What every model said, at every lead
Daily-high calls for Sat Sep 12 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 |
|---|---|---|---|---|---|---|---|---|
| 13d · 2026-08-30 | 25° | 24° | 19° | — | 24° | — | — | 19–25° |
| 12d · 2026-08-31 | 21° | 19° | 20° | — | 25° | — | — | 19–25° |
| 11d · 2026-09-01 | 20° | 23° | 18° | — | 25° | — | — | 18–25° |
| 10d · 2026-09-02 | 22° | 20° | 20° | — | 26° | — | — | 20–26° |
| 9d · 2026-09-03 | 21° | 17° | 21° | 20° | 25° | — | — | 17–25° |
| 8d · 2026-09-04 | 20° | 20° | 16° | 21° | 23° | — | — | 16–23° |
| 7d · 2026-09-05 | 24° | 23° | 21° | 20° | 20° | — | — | 20–24° |
| 6d · 2026-09-06 | 24° | 23° | 20° | 21° | 28° | 23° | 22° | 20–28° |
| 5d · 2026-09-07 | 23° | 24° | 24° | 22° | 26° | 24° | 23° | 22–26° |
| 4d · 2026-09-08 | 23° | 23° | 23° | 24° | 25° | 24° | 22° | 22–25° |
| 3d · 2026-09-09 | 24° | 23° | 24° | 23° | 26° | 24° | 23° | 23–26° |
| 2d · 2026-09-10 | 23° | 24° | 24° | 24° | 27° | 25° | 25° | 23–27° |
| 1d · 2026-09-11 | 24° | 24° | 23° | 24° | 27° | 25° | 24° | 23–27° |
| 0d · 2026-09-12 | 24° | 24° | 24° | 25° | 26° | 24° | 25° | 24–26° |
| actual | 26° |
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.