Was the forecast right for San Francisco on Thu Sep 17?
San Francisco, California · daily high temperature in °C · forecasts from each model's archived runs, verified against the SFOC1 observations
13 days out, 4 models put San Francisco's Thu Sep 17 high anywhere from 20° to 29°; by the final call the field had settled to a median of 20°. The day verified at 21° against the SFOC1 observations — drizzle.
GFS landed closest, off by 0.1°. GEM ran 2° cold.
What every model said, at every lead
Daily-high calls for Thu Sep 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 San Francisco scoreboard shows them, labelled.
| Lead | AIFS | AIGFS | ECMWF | GEM | GFS | ICON | UKMO | Range |
|---|---|---|---|---|---|---|---|---|
| 15d · 2026-09-02 | — | 31° | — | — | 27° | — | — | 27–31° |
| 14d · 2026-09-03 | 28° | 22° | — | — | 25° | — | — | 22–28° |
| 13d · 2026-09-04 | 20° | 29° | 21° | — | 25° | — | — | 20–29° |
| 12d · 2026-09-05 | 20° | 21° | 19° | — | 23° | — | — | 19–23° |
| 11d · 2026-09-06 | 22° | 20° | 17° | — | 20° | — | — | 17–22° |
| 10d · 2026-09-07 | 19° | 24° | 18° | — | 19° | — | — | 18–24° |
| 9d · 2026-09-08 | 18° | 20° | 17° | — | 20° | — | — | 17–20° |
| 8d · 2026-09-09 | 20° | 19° | 17° | 19° | 20° | — | — | 17–20° |
| 7d · 2026-09-10 | 20° | 19° | 19° | 19° | 22° | — | — | 19–22° |
| 6d · 2026-09-11 | 20° | 20° | 18° | 18° | 23° | 20° | — | 18–23° |
| 5d · 2026-09-12 | 20° | 20° | 19° | 19° | 23° | 19° | 17° | 17–23° |
| 4d · 2026-09-13 | 20° | 20° | 20° | 18° | 21° | 20° | 20° | 18–21° |
| 3d · 2026-09-14 | 20° | 21° | 20° | 19° | 20° | 20° | 20° | 19–21° |
| 2d · 2026-09-15 | 20° | 21° | 20° | 20° | 21° | 20° | 21° | 20–21° |
| 1d · 2026-09-16 | 20° | 20° | 20° | 19° | 21° | 20° | 20° | 19–21° |
| 0d · 2026-09-17 | 20° | 20° | 20° | 19° | 21° | 20° | 20° | 19–21° |
| actual | 21° |
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 the SFOC1 observations. Archive depth varies by city; receipts exist only for dates the archive watched arrive.