WeatherTomorrow

How WeatherTomorrow compares

Our aim is to beat the best forecasts there are. Every forecast on this page, ours and the others, is scored the same way: against what each airport measured.

A year, held out: against the models and the guidance

To see where we stand against current practice, we held back a full year that our model never trained on, 1 November 2025 to 24 October 2026, and scored our published forecast beside:

Everything is scored at 319 airports on 358 days, all issued 18:00 local, the evening before from what was public by then, against what each airport measured. Our high was off by 0.92° on average. The next best, ECMWF AIFS (AI model), corrected per airport, was off by 1.00°.

WeatherTomorrow0.92°CECMWF AIFS (AI model), corrected per airport1.00°CECMWF IFS, corrected per airport1.09°CNOAA GFS, corrected per airport1.18°CWT-1 alone, our neural network1.29°CECMWF IFS, raw1.47°CNOAA GFS, raw1.58°CECMWF AIFS (AI model), raw1.68°CNormal for the date2.84°CSame as today2.98°C
Average error of the next-day high, 1 November 2025 to 24 October 2026. Lower is better.
All airports, held-out year
ForecastHigh, average errorHigh within 2°Low, average error
WeatherTomorrow0.92°90%0.95°
ECMWF AIFS (AI model), corrected per airport1.00°88%1.08°
ECMWF IFS, corrected per airport1.09°85%1.13°
NOAA GFS, corrected per airport1.18°83%1.39°
WT-1 alone, our neural network1.29°79%1.10°
ECMWF IFS, raw1.47°73%1.35°
NOAA GFS, raw1.58°71%1.72°
ECMWF AIFS (AI model), raw1.68°67%1.60°
Normal for the date2.84°49%2.44°
Same as today2.98°49%2.59°

On US airports, against the official US guidance

In the US, forecasters start from MOS: a physics model corrected against each station's history. On 97 US airports, the same days and the same issue time:

US airports, held-out year
ForecastHigh, average errorHigh within 2°Low, average error
WeatherTomorrow0.98°88%0.95°
ECMWF AIFS (AI model), corrected per airport1.06°86%1.10°
GFS MOS (US guidance), corrected per airport1.25°81%1.17°
ECMWF IFS, corrected per airport1.26°81%1.21°
NOAA GFS, corrected per airport1.33°78%1.50°
GFS MOS (US guidance)1.35°76%1.31°
WT-1 alone, our neural network1.39°76%1.15°
NAM MOS (US guidance), corrected per airport1.42°76%1.25°
ECMWF IFS, raw1.53°72%1.37°
NOAA GFS, raw1.62°70%1.81°
ECMWF AIFS (AI model), raw1.69°66%1.43°
NAM MOS (US guidance)1.79°64%1.31°
Normal for the date3.80°37%3.28°
Same as today3.93°40%3.37°

The US National Blend of Models, the official US guidance that blends several corrected models, could be checked from July to October 2026 on 105 US airports. Its next-day high was off by 1.22° (1.02° with its bias removed on the scored days, which favours it), ours by 0.87°.

ECMWF data: CC BY 4.0, www.ecmwf.int. NOAA data: public domain.

Every day, against DWD MOSMIX

MOSMIX is the station forecast of Germany's national weather service (DWD). Every day we score ours and MOSMIX's at the 224 airports where DWD forecasts for a station within 5 km: the same days, the same airport measurements and the same moment of issue. The count for our current forecast, WT-1 combined with ECMWF since 27 October 2026, starts as soon as its first days have been measured.

Before that, from 23 October 2026 to 27 October 2026, our forecast was WT-1 without ECMWF. On 553 airport-days its high was off by 1.31° and MOSMIX's by 0.99°; its low by 1.14° and MOSMIX's by 1.06°.

MOSMIX is the right yardstick because it chases the same goal by other means. It takes DWD's ICON model and ECMWF's IFS, which simulate the whole atmosphere, and corrects them with years of each station's own measurements. We start from ECMWF too, and improve it with WT-1, our neural network trained on GPUs on 26 years of reports from 6,047 airports, calibrated for each airport. MOSMIX never feeds our forecast.

How the comparison with MOSMIX works

MOSMIX figures: based on data from Deutscher Wetterdienst (opendata.dwd.de), own elements added: we reduce DWD's hourly forecasts to daily highs and lows. Licence: CC BY 4.0.