Was the forecast right for Paris on Wed Sep 30?
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 Wed Sep 30 high anywhere from 58° to 75°;by the final call, the day before, the field had settled to a median of 76°. The day verified at 75° against the LFPB observations, with 0.31 in of precipitation — thunderstorms.
GFS landed closest, off by 0.5°. GEM ran 6° warm.
What every model said, at every lead
Daily-high calls for Wed Sep 30 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 · 2026-09-15 | — | 57° | — | — | 69° | — | — | 57–69° |
| 14d · 2026-09-16 | 72° | 58° | 69° | — | 75° | — | — | 58–75° |
| 13d · 2026-09-17 | 62° | 60° | 70° | — | 80° | — | — | 60–80° |
| 12d · 2026-09-18 | 69° | 70° | 71° | — | 58° | — | — | 58–71° |
| 11d · 2026-09-19 | 75° | 77° | 81° | — | 72° | — | — | 72–81° |
| 10d · 2026-09-20 | 81° | 77° | 83° | — | 82° | — | — | 77–83° |
| 9d · 2026-09-21 | 82° | 78° | 86° | 67° | 72° | — | — | 67–86° |
| 8d · 2026-09-22 | 82° | 63° | 76° | 69° | 71° | — | — | 63–82° |
| 7d · 2026-09-23 | 75° | 67° | 79° | 82° | 82° | — | — | 67–82° |
| 6d · 2026-09-24 | 80° | 77° | 83° | 75° | 73° | 84° | 83° | 73–84° |
| 5d · 2026-09-25 | 80° | 77° | 76° | 84° | 71° | 87° | 82° | 71–87° |
| 4d · 2026-09-26 | 74° | 72° | 78° | 80° | 73° | 73° | 77° | 72–80° |
| 3d · 2026-09-27 | 74° | 70° | 77° | 76° | 74° | 71° | 76° | 70–77° |
| 2d · 2026-09-28 | 72° | 70° | 72° | 82° | 74° | 73° | 75° | 70–82° |
| 1d · 2026-09-29 | 72° | 72° | 77° | 81° | 76° | 73° | 77° | 72–81° |
| actual | 75° |
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.