Was the forecast right for Paris on Mon Oct 19?
Paris, Île-de-France Region · daily high temperature in °F · forecasts from each model's archived runs, verified against the LFPB observations
14 days out, 4 models put Paris's Mon Oct 19 high anywhere from 53° to 64°;by the final call, the day before, the field had settled to a median of 56°. The day verified at 56° against the LFPB observations — drizzle.
ICON landed closest, off by 0.0°. GEM ran 4° warm.
What every model said, at every lead
Daily-high calls for Mon Oct 19 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 |
|---|---|---|---|---|---|---|---|---|
| 14d · 2026-10-05 | 64° | 56° | 63° | — | 53° | — | — | 53–64° |
| 13d · 2026-10-06 | 58° | 51° | 59° | — | 61° | — | — | 51–61° |
| 12d · 2026-10-07 | 60° | 62° | 65° | — | 66° | — | — | 60–66° |
| 11d · 2026-10-08 | 61° | 59° | 62° | — | 60° | — | — | 59–62° |
| 10d · 2026-10-09 | 59° | 59° | 63° | — | 59° | — | — | 59–63° |
| 9d · 2026-10-10 | 50° | 56° | 57° | 62° | 56° | — | — | 50–62° |
| 8d · 2026-10-11 | 60° | 60° | 59° | 63° | 57° | — | — | 57–63° |
| 7d · 2026-10-12 | 53° | 61° | 63° | 69° | 60° | — | — | 53–69° |
| 6d · 2026-10-13 | — | 62° | 51° | 62° | 60° | 57° | 52° | 51–62° |
| 5d · 2026-10-14 | 58° | 62° | 59° | 67° | 63° | 56° | 55° | 55–67° |
| 4d · 2026-10-15 | 58° | 63° | 60° | 59° | 60° | 55° | 59° | 55–63° |
| 3d · 2026-10-16 | 53° | 58° | 58° | 58° | 56° | 52° | 55° | 52–58° |
| 2d · 2026-10-17 | 55° | 58° | 58° | 58° | 60° | 58° | 59° | 55–60° |
| 1d · 2026-10-18 | 54° | 56° | 59° | 60° | 58° | 56° | 54° | 54–60° |
| actual | 56° |
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. The actual values are the ones in hand when this receipt was settled, usually 2 days after the date; a correction published after that is not carried into it. Archive depth varies by city; receipts exist only for dates the archive watched arrive.