Was the forecast right for San Francisco on Tue Aug 18?
San Francisco, California · daily high temperature in °F · 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 65° to 73°;by the final call, the day before, the field had settled to a median of 68°. The day verified at 64° against the ECMWF IFS analysis — cloudy.
GEM landed closest, off by 0.7°. AIGFS ran 9° 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 | — | 63° | — | — | 65° | — | — | 63–65° |
| 14d · 2026-08-04 | 65° | 73° | 66° | — | 66° | — | — | 65–73° |
| 13d · 2026-08-05 | 64° | 70° | 65° | — | 70° | — | — | 64–70° |
| 12d · 2026-08-06 | 66° | 71° | 68° | — | 71° | — | — | 66–71° |
| 11d · 2026-08-07 | 67° | 84° | 64° | — | 66° | — | — | 64–84° |
| 10d · 2026-08-08 | 69° | 92° | 71° | — | 69° | — | — | 69–92° |
| 9d · 2026-08-09 | 65° | 70° | 63° | 62° | 70° | — | — | 62–70° |
| 8d · 2026-08-10 | 71° | 76° | 64° | 64° | 71° | — | — | 64–76° |
| 7d · 2026-08-11 | 69° | 69° | 63° | 63° | 71° | — | — | 63–71° |
| 6d · 2026-08-12 | 68° | 68° | 63° | 63° | 71° | 62° | 65° | 62–71° |
| 5d · 2026-08-13 | 69° | 68° | 65° | 63° | 66° | 62° | 65° | 62–69° |
| 4d · 2026-08-14 | 73° | 70° | 67° | 64° | 71° | 63° | 65° | 63–73° |
| 3d · 2026-08-15 | 72° | 70° | 66° | 64° | 69° | 62° | 67° | 62–72° |
| 2d · 2026-08-16 | 73° | 74° | 67° | 64° | 70° | 62° | 66° | 62–74° |
| 1d · 2026-08-17 | 72° | 73° | 68° | 64° | 68° | 62° | 66° | 62–73° |
| actual | 64° |
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.