The Spread

Was the forecast right for Atlanta on Sun Aug 16?

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

13 days out, 4 models put Atlanta's Sun Aug 16 high anywhere from 75° to 92°; by the final call the field had settled to a median of 96°. The ECMWF IFS analysis says the day verified at 97° with 0.01 in of precipitation — drizzle.

AIGFS landed closest, off by 0.0°. GEM ran 4° cold.

13 days out the models said 75–92; it hit 97. AIGFS led (off 0.0°F); GEM ran 4°F 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 Sun Aug 16 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 · 2026-08-01 92° 96° 92–96°
14d · 2026-08-02 87° 83° 96° 83–96°
13d · 2026-08-03 92° 75° 90° 85° 75–92°
12d · 2026-08-04 85° 92° 86° 89° 85–92°
11d · 2026-08-05 89° 89° 94° 88° 88–94°
10d · 2026-08-06 88° 94° 86° 100° 86–100°
9d · 2026-08-07 91° 95° 92° 96° 91–96°
8d · 2026-08-08 93° 94° 97° 90° 90° 90–97°
7d · 2026-08-09 93° 94° 99° 95° 101° 93–101°
6d · 2026-08-10 93° 95° 97° 93° 105° 101° 93–105°
5d · 2026-08-11 92° 95° 101° 88° 98° 101° 99° 88–101°
4d · 2026-08-12 94° 95° 100° 93° 100° 98° 97° 93–100°
3d · 2026-08-13 94° 95° 97° 92° 100° 100° 97° 92–100°
2d · 2026-08-14 94° 95° 95° 90° 102° 94° 97° 90–102°
1d · 2026-08-15 94° 95° 98° 94° 98° 96° 96° 94–98°
0d · 2026-08-16 93° 97° 96° 93° 96° 93° 96° 93–97°
actual 97°

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.