Was the forecast right for San Francisco on Tue Aug 18?
San Francisco, California · daily high temperature in °C · forecasts from each model's archived runs, verified against the ECMWF IFS analysis
14 days out, 4 models put San Francisco's Tue Aug 18 high anywhere from 18° to 23°;by the final call, the day before, the field had settled to a median of 20°. The day verified at 18° against the ECMWF IFS analysis — cloudy.
GEM landed closest, off by 0.4°. AIGFS ran 5° warm.
What every model said, at every lead
Daily-high calls for Tue Aug 18 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 · 2026-08-03 | — | 17° | — | — | 18° | — | — | 17–18° |
| 14d · 2026-08-04 | 18° | 23° | 19° | — | 19° | — | — | 18–23° |
| 13d · 2026-08-05 | 18° | 21° | 18° | — | 21° | — | — | 18–21° |
| 12d · 2026-08-06 | 19° | 22° | 20° | — | 22° | — | — | 19–22° |
| 11d · 2026-08-07 | 19° | 29° | 18° | — | 19° | — | — | 18–29° |
| 10d · 2026-08-08 | 20° | 33° | 22° | — | 20° | — | — | 20–33° |
| 9d · 2026-08-09 | 18° | 21° | 17° | 17° | 21° | — | — | 17–21° |
| 8d · 2026-08-10 | 22° | 24° | 18° | 18° | 22° | — | — | 18–24° |
| 7d · 2026-08-11 | 20° | 21° | 17° | 17° | 22° | — | — | 17–22° |
| 6d · 2026-08-12 | 20° | 20° | 17° | 17° | 22° | 17° | 18° | 17–22° |
| 5d · 2026-08-13 | 21° | 20° | 18° | 17° | 19° | 17° | 19° | 17–21° |
| 4d · 2026-08-14 | 23° | 21° | 19° | 18° | 22° | 17° | 18° | 17–23° |
| 3d · 2026-08-15 | 22° | 21° | 19° | 18° | 21° | 16° | 20° | 16–22° |
| 2d · 2026-08-16 | 23° | 23° | 19° | 18° | 21° | 17° | 19° | 17–23° |
| 1d · 2026-08-17 | 22° | 23° | 20° | 18° | 20° | 17° | 19° | 17–23° |
| actual | 18° |
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 ECMWF IFS analysis (temperature_2m_max). 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.