Was the forecast right for San Francisco on Mon Aug 17?
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 Mon Aug 17 high anywhere from 64° to 69°;by the final call, the day before, the field had settled to a median of 66°. The day verified at 66° against the ECMWF IFS analysis — cloudy.
ECMWF landed closest, off by 0.2°. AIGFS ran 8° warm.
What every model said, at every lead
Daily-high calls for Mon Aug 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 · 2026-08-02 | — | 74° | — | — | 77° | — | — | 74–77° |
| 14d · 2026-08-03 | 65° | 69° | 64° | — | 68° | — | — | 64–69° |
| 13d · 2026-08-04 | 65° | 72° | 65° | — | 68° | — | — | 65–72° |
| 12d · 2026-08-05 | 66° | 68° | 65° | — | 67° | — | — | 65–68° |
| 11d · 2026-08-06 | 67° | 68° | 67° | — | 78° | — | — | 67–78° |
| 10d · 2026-08-07 | 66° | 72° | 66° | — | 71° | — | — | 66–72° |
| 9d · 2026-08-08 | 67° | 78° | 64° | 63° | 71° | — | — | 63–78° |
| 8d · 2026-08-09 | 65° | 68° | 65° | 66° | 69° | — | — | 65–69° |
| 7d · 2026-08-10 | 66° | 68° | 65° | 63° | 73° | — | — | 63–73° |
| 6d · 2026-08-11 | 70° | 66° | 61° | 64° | 70° | 64° | 65° | 61–70° |
| 5d · 2026-08-12 | 69° | 67° | 65° | 63° | 70° | 63° | 65° | 63–70° |
| 4d · 2026-08-13 | 66° | 66° | 66° | 64° | 66° | 61° | 64° | 61–66° |
| 3d · 2026-08-14 | 67° | 68° | 64° | 64° | 69° | 61° | 63° | 61–69° |
| 2d · 2026-08-15 | 68° | 70° | 66° | 64° | 72° | 62° | 64° | 62–72° |
| 1d · 2026-08-16 | 69° | 73° | 66° | 65° | 65° | 63° | 67° | 63–73° |
| 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 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.