Was the forecast right for Paris on Fri Sep 25?
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 Fri Sep 25 high anywhere from 59° to 73°;by the final call, the day before, the field had settled to a median of 80°. The day verified at 84° against the LFPB observations — cloudy.
GEM landed closest, off by 1.6°. AIGFS ran 7° cool.
What every model said, at every lead
Daily-high calls for Fri Sep 25 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 · 2026-09-10 | — | 68° | — | — | 73° | — | — | 68–73° |
| 14d · 2026-09-11 | 73° | 73° | 59° | — | 73° | — | — | 59–73° |
| 13d · 2026-09-12 | 73° | 66° | 74° | — | 75° | — | — | 66–75° |
| 12d · 2026-09-13 | 74° | 60° | 67° | — | 70° | — | — | 60–74° |
| 11d · 2026-09-14 | 69° | 68° | 82° | — | 87° | — | — | 68–87° |
| 10d · 2026-09-15 | 83° | 66° | 72° | — | 69° | — | — | 66–83° |
| 9d · 2026-09-16 | 72° | 64° | 78° | 76° | 76° | — | — | 64–78° |
| 8d · 2026-09-17 | 72° | 70° | 82° | 78° | 76° | — | — | 70–82° |
| 7d · 2026-09-18 | 72° | 69° | 86° | 77° | 82° | — | — | 69–86° |
| 6d · 2026-09-19 | 71° | 69° | 77° | 78° | 76° | 71° | — | 69–78° |
| 5d · 2026-09-20 | 77° | 68° | 78° | 81° | 76° | 75° | 72° | 68–81° |
| 4d · 2026-09-21 | 81° | 69° | 78° | 79° | 76° | 79° | 70° | 69–81° |
| 3d · 2026-09-22 | 80° | 72° | 75° | 77° | 80° | 82° | 69° | 69–82° |
| 2d · 2026-09-23 | 77° | 75° | 78° | 79° | 81° | 82° | 77° | 75–82° |
| 1d · 2026-09-24 | 79° | 77° | 80° | 82° | 82° | 80° | 82° | 77–82° |
| actual | 84° |
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.