Was the forecast right for Atlanta on Sun Aug 9?
Atlanta, Georgia · daily high temperature in °C · forecasts from each model's archived runs, verified against ERA5
13 days out, 4 models put Atlanta's Sun Aug 9 high anywhere from 31° to 36°; by the final call the field had settled to a median of 32°. ERA5 says the day verified at 33° with 1.3 mm of precipitation — drizzle.
UKMO landed closest, off by 0.1°. GEM ran 2° cold.
What every model said, at every lead
Daily-high calls for Sun Aug 9 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 Atlanta scoreboard shows them, labelled.
| Lead | AIFS | AIGFS | ECMWF | GEM | GFS | ICON | UKMO | Range |
|---|---|---|---|---|---|---|---|---|
| 13d · 2026-07-27 | 32° | 31° | 32° | — | 36° | — | — | 31–36° |
| 12d · 2026-07-28 | 30° | 30° | 31° | — | 34° | — | — | 30–34° |
| 11d · 2026-07-29 | 30° | 33° | 32° | — | 38° | — | — | 30–38° |
| 10d · 2026-07-30 | 30° | 30° | 34° | — | 34° | — | — | 30–34° |
| 9d · 2026-07-31 | 30° | 27° | 35° | — | 35° | — | — | 27–35° |
| 8d · 2026-08-01 | 30° | 29° | 34° | 29° | 29° | — | — | 29–34° |
| 7d · 2026-08-02 | 29° | 29° | 28° | 28° | 35° | — | — | 28–35° |
| 6d · 2026-08-03 | 30° | 29° | 31° | 27° | 35° | 33° | — | 27–35° |
| 5d · 2026-08-04 | 30° | 30° | 32° | 29° | 34° | 31° | 35° | 29–35° |
| 4d · 2026-08-05 | 31° | 31° | 32° | 30° | 32° | 33° | 34° | 30–34° |
| 3d · 2026-08-06 | 31° | 32° | 32° | 31° | 35° | 33° | 34° | 31–35° |
| 2d · 2026-08-07 | 31° | 31° | 31° | 32° | 34° | 33° | 35° | 31–35° |
| 1d · 2026-08-08 | 32° | 32° | 32° | 32° | 34° | 33° | 33° | 32–34° |
| 0d · 2026-08-09 | 31° | 33° | 33° | 31° | 32° | 32° | 33° | 31–33° |
| 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 Atlanta — 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 ERA5 reanalysis (temperature_2m_max). Archive depth varies by city; receipts exist only for dates the archive watched arrive.