MeteoSignal

Europe, against ERA5.

AIFS 2 against IFS and GFS: lower error in 4 of 8 tested comparisonsSample, sources and status
Scored against
ERA5 reanalysis on a 0.25° grid, 35 to 72°N and 12.5°W to 40°E
Sample
AIFS 2: 171 days, 23 May 2026 to 9 November 2026. Other AI models: 108 days
Result so far, AIFS 2
Against IFS and GFS: AIFS's error lower in 4 of 8 tested comparisons, higher in 0, not separated in 4
Status
Provisional: no full year yet. ERA5 is a model product and AIFS was trained mostly on it, so this is a second view, not a measurement.

Last reviewed 16 November 2026ERA5 to 9 November 2026How verdicts are reachedData access

Every grid point inside the dashed frame is scored, sea included.

Results against ERA5

Show
Version
Models
Reference
500 hPa geopotential height: skill against climatology
0255075100▲ violet: lower error than climatologyDay 1Day 3Day 5Day 7Day 10Skill, %AIFSIFSGFS

171 days, 23 May 2026 to 9 November 2026, with no winter or spring. About 41 independent days. Provisional.

500 hPa geopotential height, AIFS 2: how AIFS's error compared, over 171 days
Compared withDay 1Day 3Day 5Day 7Day 10
IFS−2%not judged, no verdict−8%, AIFS lower error, tested−14%, AIFS lower error, tested−7%, not separated0%, not separated
GFS−34%not judged, no verdict−32%, AIFS lower error, tested−29%, not separated−19%, AIFS lower error, tested−11%, not separated

Each number is AIFS's RMSE against ERA5 minus the other model's, as a percentage of the other model's: minus is lower (better), plus is higher (worse). Over this sample only.

Day 1 is not judged: at day 1 the models start from different analyses, and ERA5 is an ECMWF product.

  • AIFS lower error, tested (better)
  • AIFS higher error, tested (worse)
  • Not separated: no clear difference, too few days, or the verdict depends on how the station is read or on the height correction (hover says which)
  • Dashed outline: not judged, sign only
Bias and activity: 500 hpa geopotential heightWhether a model runs high or low, and how much it varies
500 hPa geopotential height: anomaly correlation, uncentredHow well the forecast pattern matches ERA5, as departures from the 1990 to 2019 climatology. The first value is the uncentred form, as WeatherBench 2 computes it. The smaller value under it is the centred form, with the area-mean anomaly of each field removed first. 1 is perfect and higher is better. For 500 hPa height only, a value below 0.6 is commonly read as a forecast of little use; here that reading is applied to the uncentred form.
ModelDay 1Day 3Day 5Day 7Day 10
AIFS0.9990.9990.9900.9890.9480.9380.8410.8040.5790.505
IFS0.9990.9990.9880.9860.9300.9150.8070.7610.5630.470
GFS0.9980.9980.9800.9750.9060.8840.7550.6970.4440.347
500 hPa geopotential height: bias, in gpmForecast minus ERA5, on average. Plus: too high. Minus: too low. Zero is best.
ModelDay 1Day 3Day 5Day 7Day 10
AIFS+0.95+1.39+1.14−0.18−0.76
IFS+1.69+2.81+1.68+3.05+1.67
GFS−2.27+0.16+1.02+1.32−6.10
500 hPa geopotential height: activityVariability of the forecast divided by that of the ERA5 field, both as departures from climatology, with each grid cell centred on its own mean at each valid hour over the sample first. 1.00 is best. Below 1 the forecast is too smooth, which flatters RMSE.
ModelDay 1Day 3Day 5Day 7Day 10
AIFS1.001.000.991.001.03
IFS1.000.980.970.990.99
GFS1.000.980.980.991.02

Forecasts scored against ERA5 from 35 to 72°N and 12.5°W to 40°E, weighted by latitude. ERA5 is a model product and many AI models were trained on it. Treat this as a second view beside the station measurements. Its numbers cannot be compared with the station scores.

Where the error sat

Lead

Each square averages a 1.5° cell over the days scored. These show patterns only, with no verdict for any square: on the second map the colour gives the sign of the difference and is not a test. They follow the variable and version selected above.

500 hPa geopotential height

AIFS's error (RMSE)

AIFS against IFS: who had the lower error

Sign of the difference, not a test