Eight National Weather Models, One Korean AI: Darwin Has the Lowest Error in All 28 Categories
aiweatherforecastingbenchmark

TL;DR
VIDRAFT compared its AI weather engine, Darwin-Prediction-Weather, with eight forecast models run by the European Centre for Medium-Range Weather Forecasts (ECMWF), the US National Oceanic and Atmospheric Administration (NOAA) and the national weather services of Japan, Canada, Germany and Norway. The comparison covers 24 cities, about nine months of 2026 and 1.23 million published forecasts, each checked against what actually happened.
Darwin had the lowest error in all 28 categories: four weather elements (daily maximum temperature, daily minimum temperature, wind speed, precipitation) times seven lead times (1 to 7 days).
- 7-day maximum temperature error: 2.08 C, 14.0% lower than ECMWF AIFS (2.42 C), the second most accurate model.
- Darwin's 7-day forecast is more accurate than the 6-day forecast of ECMWF AIFS and the 5-day forecast of ECMWF IFS.
- The scores are public and update every day on the Global Weather Model Leaderboard.
The models compared
| Model | Operator | Type |
|---|---|---|
| Darwin-Prediction-Weather | VIDRAFT, Korea | AI |
| AIFS | ECMWF, Europe | AI |
| IFS | ECMWF, Europe | Physics |
| AIGFS | NOAA, United States | AI |
| GFS | NOAA, United States | Physics |
| ICON | German Weather Service | Physics |
| GSM | Japan Meteorological Agency | Physics |
| GEM | Environment and Climate Change Canada | Physics |
| MET Nordic | Norwegian Meteorological Institute | Physics |
A physics model solves the equations of the atmosphere on a supercomputer. An AI model learns to forecast from past weather data.
7-day maximum temperature: the full ranking
Root mean square error over 4,896 cases, the same cities and the same days for every model, February 1 to November 11, 2026. A lower error means a more accurate forecast.
| Rank | Model | Operator | Type | 7-day error | Error above first place |
|---|---|---|---|---|---|
| 1 | Darwin-Prediction-Weather | VIDRAFT | AI | 2.08 C | |
| 2 | ECMWF AIFS | ECMWF | AI | 2.42 C | +16.2% |
| 3 | NOAA AIGFS | NOAA | AI | 2.83 C | +36.1% |
| 4 | ECMWF IFS | ECMWF | Physics | 2.86 C | +37.2% |
| 5 | MET Nordic | Norway | Physics | 2.94 C | +41.2% |
| 6 | JMA GSM | Japan | Physics | 3.10 C | +49.0% |
| 7 | NOAA GFS | NOAA | Physics | 3.18 C | +52.6% |
| 8 | GEM | Canada | Physics | 3.20 C | +53.8% |
The German ICON model does not publish a 7-day forecast, so it is not in the 7-day ranking.
How many days ahead
The gap is clearer when lead times are compared.
| Comparison | Darwin | Other model |
|---|---|---|
| Next-day maximum temperature | 0.84 C | AIFS 1.36 C (Darwin 38.6% lower) |
| Maximum temperature | 7-day forecast 2.08 C | AIFS 6-day forecast 2.14 C |
| Maximum temperature | 7-day forecast 2.08 C | IFS 5-day forecast 2.21 C |
| Minimum temperature | 7-day forecast 1.81 C | AIFS 5-day forecast 1.86 C |
| Wind speed | 7-day forecast 4.36 km/h | AIFS 4-day forecast 4.50 km/h |
At the same accuracy, Darwin sees one day further than the European AI model and two days further than the most accurate supercomputer physics model.
The other elements
| Element, 7-day forecast | Darwin | ECMWF AIFS | Difference |
|---|---|---|---|
| Minimum temperature error | 1.81 C | 2.18 C | 16.7% lower |
| Wind speed error | 4.36 km/h | 5.64 km/h | 22.9% lower |
| Rain of 1 mm or more, correct calls, next day | 90.6% | 88.4% | |
| Rain of 1 mm or more, correct calls, day 7 | 79.6% | 77.2% |
Precipitation is the hardest element to forecast. Darwin was first at every lead time from 1 to 7 days there as well.
AI forecasts and supercomputer physics models
In the 7-day maximum temperature forecast, AIFS, the most accurate public AI model, had 15.3% less error than IFS, the most accurate physics model. Darwin had 27.1% less error than IFS. AI models were ahead of physics models in all four elements, and Darwin widened that lead the most.
City by city
- 7-day wind speed: Darwin was first in all 24 cities.
- 7-day minimum temperature: first in 20 cities.
- 7-day maximum temperature: first in 18 cities.
- Seoul, 7-day maximum temperature: 2.27 C against 2.62 C for AIFS, 13.5% lower.
- Busan: 1.76 C against 2.16 C for AIFS, 18.7% lower.
When the period is cut to the most recent 7, 14, 30 and 90 days, Darwin stays first for maximum temperature, minimum temperature and wind speed at the 1, 3, 5 and 7-day lead times in every window.
WeatherBench 2
VIDRAFT also submitted a full-year 2020 global forecast from the same engine to WeatherBench 2, the weather AI evaluation framework from Google Research. Scored with the same method as the public scoreboard, the forecast had a lower error than the previous best record on 39 of 45 metrics.
How the comparison is done
- Every model is scored on the forecast it actually published. Forecast records come from the public Open-Meteo archive.
- Models are compared only on the same cities and the same days.
- The reference is ERA5, the reanalysis dataset from ECMWF.
- Temperature and wind speed are scored on each city's local calendar day.
- Temperature and wind speed are verified through November 11, 2026, and precipitation through November 10.
- The leaderboard recalculates every day, and anyone can open it.
What the CEO said
Kim Minsik, CEO of VIDRAFT, said weather forecasting has long belonged to national weather services and supercomputers, and that a Korean AI came first in all 28 categories in an open daily contest against those models under the same conditions. He said the company will supply forecasts that see further and more accurately to industries where weather decides cost, such as energy trading, agriculture and logistics.
Links
- Leaderboard: https://huggingface.co/spaces/FINAL-Bench/Weather-Model-Leaderboard
- VIDRAFT: https://vidraft.net
FAQ
Which weather model is the most accurate in 2026?
On the Global Weather Model Leaderboard, which compares nine models across 24 cities, Darwin-Prediction-Weather has the lowest error in all 28 categories for February 1 to November 11, 2026. ECMWF AIFS is second for 7-day maximum temperature.
Are AI weather models more accurate than physics models?
In this comparison, yes. AI models had lower error than supercomputer physics models in all four elements at the 7-day lead time.
Where does the data come from?
Forecasts come from the Open-Meteo public archive and the reference values from the ERA5 reanalysis.