Which weather model is most accurate in Orlando?

Outlook Model accuracy

Orlando, Florida · 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 Orlando at 1-, 3-, and 7-day leads, then scores those forecasts against the ORL observations once the day has happened. This page covers the trailing 30 days (2026-08-04 to 2026-09-02), for daily high temperature.

One day out, NOAA AIGFS (AI) has been most accurate (typical miss 0.61°C); at three days, NOAA AIGFS (AI) (0.71°C); at seven days, NOAA AIGFS (AI) (0.99°C).

The largest standing bias belongs to NOAA GFS, which has run warm by about 2.52°C at 3-day lead over this window.

The Spread's own bias-corrected blend scored a 0.63°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
NOAA AIGFS (AI)	0.6° (-0.0°)	0.7° (+0.1°)	1.0° (+0.6°)	30
UKMO (UK)	1.0° (-0.4°)	1.5° (-0.4°)	—	30
GEM (Canada)	1.0° (-0.3°)	1.2° (-0.3°)	1.4° (-0.4°)	30
DWD ICON	1.3° (-0.8°)	1.2° (-0.3°)	—	30
ECMWF AIFS (AI)	1.7° (-1.7°)	1.8° (-1.7°)	1.6° (-1.4°)	30
ECMWF IFS	2.1° (-2.1°)	2.2° (-2.1°)	1.9° (-1.6°)	30
NOAA GFS	2.3° (+2.3°)	2.5° (+2.5°)	2.8° (+2.8°)	30
NBM (US blend)	1.3° (-1.1°)	1.2° (-1.1°)	1.5° (-0.9°)	30
Blended (bias-corrected)	0.6° (+0.0°)	0.6° (+0.0°)	0.9° (+0.0°)	30

Method, honestly

The Spread's Orlando point is the Orlando Executive station (ORL), 4.6 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 ORL 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.

Receipts — was the forecast right?

One page per settled date: what every model said as the day approached, what happened, and who was closest.

Tue Sep 1 13 days out the models said 31–37; it hit 31. GFS led (off 0.3°C); AIFS ran 4°C cold.
Mon Aug 31 12 days out the models said 32–34; it hit 32. AIFS led (off 0.1°C); GFS ran 3°C hot.
Sun Aug 30 11 days out the models said 32–37; it hit 33. GEM led (off 0.2°C); UKMO ran 3°C cold.
Sat Aug 29 10 days out the models said 30–36; it hit 34. ICON led (off 0.1°C); AIFS ran 5°C cold.
Fri Aug 28 9 days out the models said 32–36; it hit 33. ICON led (off 0.2°C); GFS ran 3°C hot.
Thu Aug 27 8 days out the models said 32–36; it hit 33. UKMO led (off 0.3°C); AIFS ran 6°C cold.
Wed Aug 26 7 days out the models said 32–35; it hit 36. GFS led (off 0.8°C); ECMWF ran 5°C cold.
Tue Aug 25 6 days out the models said 31–35; it hit 35. UKMO led (off 0.1°C); AIFS ran 4°C cold.
Mon Aug 24 5 days out the models said 33–37; it hit 34. AIGFS led (off 0.2°C); AIFS ran 3°C cold.
Sun Aug 23 4 days out the models said 29–37; it hit 31. AIGFS led (off 0.3°C); AIFS ran 5°C cold.
Sat Aug 22 3 days out the models said 32–37; it hit 34. ICON led (off 0.5°C); ECMWF ran 3°C cold.
Mon Aug 17 14 days out the models said 32–37; it hit 37. AIGFS led (off 0.3°C); ECMWF ran 3°C cold.
Sun Aug 16 14 days out the models said 32–37; it hit 36. UKMO led (off 0.1°C); ECMWF ran 3°C cold.
Sat Aug 15 14 days out the models said 32–37; it hit 36. UKMO led (off 0.2°C); AIFS ran 3°C cold.
Fri Aug 14 14 days out the models said 30–38; it hit 32. ECMWF led (off 0.2°C); GFS ran 5°C hot.
Thu Aug 13 14 days out the models said 30–38; it hit 32. ECMWF led (off 0.1°C); GFS ran 5°C hot.
Wed Aug 12 14 days out the models said 28–36; it hit 33. ECMWF led (off 0.3°C); GFS ran 5°C hot.
Tue Aug 11 14 days out the models said 32–38; it hit 33. ECMWF led (off 0.1°C); UKMO ran 3°C hot.
Mon Aug 10 14 days out the models said 32–39; it hit 33. ECMWF led (off 0.1°C); GFS ran 5°C hot.
Sun Aug 9 14 days out the models said 29–35; it hit 31. ECMWF led (off 0.0°C); GFS ran 4°C hot.
Sat Aug 8 14 days out the models said 30–38; it hit 31. ECMWF led (off 0.3°C); AIGFS ran 4°C hot.
Fri Aug 7 14 days out the models said 29–39; it hit 30. ICON led (off 0.4°C); AIGFS ran 2°C hot.
Thu Aug 6 14 days out the models said 31–36; it hit 29. AIFS led (off 0.2°C); GFS ran 4°C hot.
Wed Aug 5 14 days out the models said 29–36; it hit 31. ICON led (off 0.2°C); AIFS ran 1°C cold.
Tue Aug 4 13 days out the models said 30–36; it hit 29. ECMWF led (off 0.2°C); GFS ran 5°C hot.
Mon Aug 3 14 days out the models said 30–37; it hit 29. AIFS led (off 0.2°C); ICON ran 4°C hot.
Sun Aug 2 14 days out the models said 28–31; it hit 30. ICON led (off 0.4°C); AIGFS ran 2°C cold.
Sat Aug 1 13 days out the models said 28–35; it hit 31. GEM led (off 1.3°C); GFS ran 5°C hot.
Fri Jul 31 14 days out the models said 28–37; it hit 31. UKMO led (off 0.1°C); GFS ran 3°C hot.
Thu Jul 30 13 days out the models said 27–38; it hit 29. UKMO led (off 0.3°C); GEM ran 4°C hot.
Wed Jul 29 12 days out the models said 29–38; it hit 32. AIFS led (off 0.1°C); GFS ran 4°C hot.
Tue Jul 28 11 days out the models said 28–36; it hit 32. AIFS led (off 0.6°C); AIGFS ran 3°C hot.
Mon Jul 27 10 days out the models said 28–34; it hit 32. ICON led (off 0.2°C); AIGFS ran 3°C hot.
Sun Jul 26 9 days out the models said 30–37; it hit 34. AIGFS led (off 0.2°C); GEM ran 3°C hot.
Sat Jul 25 8 days out the models said 33–36; it hit 34. AIFS led (off 0.4°C); GFS ran 3°C hot.
Fri Jul 24 7 days out the models said 29–35; it hit 33. ECMWF led (off 0.6°C); GFS ran 3°C hot.
Thu Jul 23 6 days out the models said 32–36; it hit 34. ECMWF led (off 0.8°C); GFS ran 3°C hot.
Wed Jul 22 5 days out the models said 32–36; it hit 34. AIFS led (off 0.2°C); GFS ran 3°C hot.
Tue Jul 21 4 days out the models said 31–36; it hit 33. AIFS led (off 0.4°C); GFS ran 4°C hot.
Mon Jul 20 3 days out the models said 30–36; it hit 31. ECMWF led (off 0.1°C); GFS ran 5°C hot.

Other cities

Atlanta, Georgia Berlin, State of Berlin 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 Paris, Île-de-France Region Philadelphia, Pennsylvania 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.