The Spread

Was the forecast right for Atlanta on Mon Aug 17?

Atlanta, Georgia · daily high temperature in °C · forecasts from each model's archived runs, verified against the ECMWF IFS analysis

13 days out, 4 models put Atlanta's Mon Aug 17 high anywhere from 27° to 34°; by the final call the field had settled to a median of 37°. The ECMWF IFS analysis says the day verified at 37° with 1.8 mm of precipitation — drizzle.

ICON landed closest, off by 0.1°. GEM ran 2° cold.

13 days out the models said 27–34; it hit 37. ICON led (off 0.1°C); GEM ran 2°C cold.
The shareable card for this receipt — what this page looks like pasted into a thread.

What every model said, at every lead

Daily-high calls for Mon Aug 17 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 AIFSAIGFSECMWFGEMGFSICONUKMO Range
15d · 2026-08-02 29° 33° 29–33°
14d · 2026-08-03 34° 24° 36° 24–36°
13d · 2026-08-04 27° 34° 31° 29° 27–34°
12d · 2026-08-05 30° 32° 33° 25° 25–33°
11d · 2026-08-06 32° 36° 31° 37° 31–37°
10d · 2026-08-07 33° 36° 32° 34° 32–36°
9d · 2026-08-08 34° 35° 37° 30° 30–37°
8d · 2026-08-09 34° 34° 38° 35° 40° 34–40°
7d · 2026-08-10 35° 35° 38° 33° 38° 33–38°
6d · 2026-08-11 35° 36° 40° 34° 40° 40° 34–40°
5d · 2026-08-12 35° 35° 39° 35° 40° 40° 37° 35–40°
4d · 2026-08-13 35° 35° 37° 35° 39° 39° 36° 35–39°
3d · 2026-08-14 35° 36° 37° 35° 39° 38° 37° 35–39°
2d · 2026-08-15 35° 36° 37° 35° 39° 38° 38° 35–39°
1d · 2026-08-16 35° 36° 37° 36° 37° 37° 37° 35–37°
0d · 2026-08-17 35° 38° 37° 35° 37° 37° 37° 35–38°
actual 37°

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 the ECMWF IFS analysis (temperature_2m_max). Archive depth varies by city; receipts exist only for dates the archive watched arrive.