Which weather model is most accurate in Philadelphia?
Philadelphia, Pennsylvania · daily high temperature in °C · trailing 30 days · refreshed at most every 6 hours
Every day, The Spread archives what each major weather model predicted for Philadelphia at 1-, 3-, and 7-day leads, then scores those forecasts against the PHL observations once the day has happened. This page covers the trailing 30 days (2026-07-26 to 2026-08-24), for daily high temperature.
One day out, too close to call; at three days, too close to call; at seven days, ECMWF AIFS (AI) (1.41°C).
The largest standing bias belongs to GEM (Canada), which has run cool by about 2.27°C at 3-day lead over this window.
The Spread's own bias-corrected blend scored a 0.62°C typical miss at one day. Its corrections come from the same window it is scored on (in-sample), so read it as a ceiling, not a promise.
The scoreboard
Typical miss (MAE) in °C with the signed bias in parentheses — positive bias means the model ran warm. Days = scored days behind the 1-day number.
| Model | 1-day | 3-day | 7-day | Days |
|---|---|---|---|---|
| UKMO (UK) | 0.8° (-0.3°) | 1.3° (-0.8°) | — | 30 |
| ECMWF AIFS (AI) | 0.9° (-0.9°) | 1.4° (-0.9°) | 1.4° (-0.7°) | 30 |
| NOAA GFS | 1.0° (+0.3°) | 1.5° (-0.2°) | 2.0° (+1.2°) | 30 |
| DWD ICON | 1.3° (-1.1°) | 1.4° (-0.8°) | — | 30 |
| ECMWF IFS | 1.4° (-1.1°) | 1.9° (-1.2°) | 2.7° (-2.0°) | 30 |
| NOAA AIGFS (AI) | 1.5° (-1.4°) | 2.1° (-1.8°) | 2.3° (-1.7°) | 30 |
| GEM (Canada) | 1.5° (-1.0°) | 2.5° (-2.3°) | 2.7° (-2.2°) | 30 |
| NBM (US blend) | 1.8° (-1.7°) | 1.8° (-1.7°) | 1.9° (-1.5°) | 30 |
| Blended (bias-corrected) | 0.6° (+0.0°) | 0.9° (-0.0°) | 1.2° (+0.0°) | 30 |
Method, honestly
The Spread's Philadelphia point is the Philadelphia Intl station (PHL), 9.8 km from downtown, used for both forecasts and verifications. Forecasts come from each model's actual archived runs via Open-Meteo's Previous Runs API — what the model said at the time, not a reconstruction. Truth is PHL observations — the station's own daily highs, a thermometer rather than a grid, and no correction applies: the thermometer is the truth outright. Rankings cover the models themselves; the two consensus products at the bottom of the table — NBM, which is itself a blend of models, and The Spread's own bias-corrected blend — are shown for comparison, never ranked or named "most accurate" here. The blend's corrections come from the same trailing window it is scored on (in-sample), so treat its score as a ceiling. A rolling 30-day window means these numbers move — that is the point.
Other cities
Atlanta, Georgia Boston, Massachusetts Buffalo, New York Charlotte, North Carolina Chicago, Illinois Dallas, Texas Denver, Colorado Detroit, Michigan Houston, Texas London, England Los Angeles, California Miami, Florida Milan, Lombardy Minneapolis, Minnesota New Orleans, Louisiana New York, New York Oklahoma City, Oklahoma Orlando, Florida Phoenix, Arizona Salt Lake City, Utah San Antonio, Texas San Diego, California San Francisco, California Seattle, Washington St. Louis, Missouri Tampa, Florida Washington, District of Columbia
The Spread — the forecast spread — is in closed beta. These verification pages are public while the rest is gated.