Was the forecast right for San Francisco on Thu Oct 22?
San Francisco, California · daily high temperature in °F · forecasts from each model's archived runs, verified against the SFOC1 observations
14 days out, 4 models put San Francisco's Thu Oct 22 high anywhere from 64° to 78°;by the final call, the day before, the field had settled to a median of 62°. The day verified at 62° against the SFOC1 observations, with 0.04 in of precipitation — showers.
GEM landed closest, off by 0.2°. GFS ran 3° warm.
What every model said, at every lead
Daily-high calls for Thu Oct 22 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 · 2026-10-07 | — | 69° | — | — | 72° | — | — | 69–72° |
| 14d · 2026-10-08 | 64° | 78° | 74° | — | 78° | — | — | 64–78° |
| 13d · 2026-10-09 | 78° | 81° | 71° | — | 67° | — | — | 67–81° |
| 12d · 2026-10-10 | 74° | 74° | 66° | — | 81° | — | — | 66–81° |
| 11d · 2026-10-11 | 69° | 72° | 63° | — | 77° | — | — | 63–77° |
| 10d · 2026-10-12 | — | 75° | 65° | — | 64° | — | — | 64–75° |
| 9d · 2026-10-13 | 69° | 73° | 63° | 65° | 66° | — | — | 63–73° |
| 8d · 2026-10-14 | 61° | 65° | 67° | 61° | 63° | — | — | 61–67° |
| 7d · 2026-10-15 | 62° | 64° | 65° | 63° | 61° | — | — | 61–65° |
| 6d · 2026-10-16 | 60° | 61° | 64° | 61° | 58° | 62° | 60° | 58–64° |
| 5d · 2026-10-17 | 62° | 63° | 66° | 64° | 64° | 63° | 68° | 62–68° |
| 4d · 2026-10-18 | 62° | 63° | 62° | 62° | 64° | 61° | 64° | 61–64° |
| 3d · 2026-10-19 | 62° | 64° | 63° | 59° | 61° | 61° | 64° | 59–64° |
| 2d · 2026-10-20 | 62° | 63° | 66° | 63° | 62° | 60° | 61° | 60–66° |
| 1d · 2026-10-21 | 62° | 64° | 61° | 62° | 65° | 62° | 64° | 61–65° |
| actual | 62° |
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. The actual values are the ones in hand when this receipt was settled, usually 2 days after the date; a correction published after that is not carried into it. Archive depth varies by city; receipts exist only for dates the archive watched arrive.