Was the forecast right for San Francisco on Mon Aug 10?
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 Mon Aug 10 high anywhere from 66° to 73°; by the final call the field had settled to a median of 68°. ERA5 says the day verified at 66° — cloudy.
GFS landed closest, off by 1.3°. AIGFS ran 9° hot.
What every model said, at every lead
Daily-high calls for Mon Aug 10 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 |
|---|---|---|---|---|---|---|---|---|
| 14d · 2026-07-27 | 67° | 73° | — | — | 72° | — | — | 67–73° |
| 13d · 2026-07-28 | 70° | 66° | 66° | — | 73° | — | — | 66–73° |
| 12d · 2026-07-29 | 69° | 71° | 63° | — | 67° | — | — | 63–71° |
| 11d · 2026-07-30 | 64° | 72° | 60° | — | 71° | — | — | 60–72° |
| 10d · 2026-07-31 | 67° | 68° | 66° | — | 68° | — | — | 66–68° |
| 9d · 2026-08-01 | 64° | 74° | 63° | — | 78° | — | — | 63–78° |
| 8d · 2026-08-02 | 67° | 71° | 64° | 66° | 72° | — | — | 64–72° |
| 7d · 2026-08-03 | 68° | 75° | 63° | 66° | 73° | — | — | 63–75° |
| 6d · 2026-08-04 | 70° | 73° | 66° | 66° | 68° | 62° | — | 62–73° |
| 5d · 2026-08-05 | 69° | 77° | 66° | 69° | 73° | 62° | 62° | 62–77° |
| 4d · 2026-08-06 | 70° | 74° | 67° | 69° | 72° | 62° | 64° | 62–74° |
| 3d · 2026-08-07 | 71° | 72° | 69° | 68° | 72° | 62° | 62° | 62–72° |
| 2d · 2026-08-08 | 70° | 74° | 68° | 71° | 72° | 62° | 65° | 62–74° |
| 1d · 2026-08-09 | 70° | 75° | 69° | 69° | 69° | 63° | 65° | 63–75° |
| 0d · 2026-08-10 | 70° | 75° | 69° | 68° | 68° | 63° | 68° | 63–75° |
| 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.