Was the forecast right for San Francisco on Sun Aug 9?
San Francisco, California · daily high temperature in °F · forecasts from each model's archived runs, verified against ERA5
13 days out, 4 models put San Francisco's Sun Aug 9 high anywhere from 62° to 75°; by the final call the field had settled to a median of 74°. ERA5 says the day verified at 66° — partly cloudy.
ICON landed closest, off by 2.5°. AIGFS ran 16° hot.
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 San Francisco scoreboard shows them, labelled.
| Lead | AIFS | AIGFS | ECMWF | GEM | GFS | ICON | UKMO | Range |
|---|---|---|---|---|---|---|---|---|
| 13d · 2026-07-27 | 68° | 75° | 62° | — | 72° | — | — | 62–75° |
| 12d · 2026-07-28 | 70° | 66° | 66° | — | 72° | — | — | 66–72° |
| 11d · 2026-07-29 | 70° | 69° | 64° | — | 69° | — | — | 64–70° |
| 10d · 2026-07-30 | 70° | 71° | 64° | — | 68° | — | — | 64–71° |
| 9d · 2026-07-31 | 69° | 72° | 63° | — | 69° | — | — | 63–72° |
| 8d · 2026-08-01 | 68° | 75° | 67° | 68° | 74° | — | — | 67–75° |
| 7d · 2026-08-02 | 70° | 74° | 65° | 69° | 70° | — | — | 65–74° |
| 6d · 2026-08-03 | 70° | 75° | 64° | 67° | 71° | 62° | — | 62–75° |
| 5d · 2026-08-04 | 73° | 78° | 71° | 71° | 73° | 62° | 67° | 62–78° |
| 4d · 2026-08-05 | 73° | 81° | 68° | 72° | 73° | 63° | 66° | 63–81° |
| 3d · 2026-08-06 | 73° | 80° | 71° | 68° | 73° | 62° | 68° | 62–80° |
| 2d · 2026-08-07 | 76° | 80° | 75° | 73° | 75° | 63° | 73° | 63–80° |
| 1d · 2026-08-08 | 74° | 82° | 74° | 74° | 78° | 63° | 72° | 63–82° |
| 0d · 2026-08-09 | 74° | 82° | 74° | 73° | 75° | 63° | 74° | 63–82° |
| actual | 66° |
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 San Francisco — 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.