Raw model output on the native 0.25° grid — no MOS, no bias correction, no post-processing. Scores understate operational forecast quality. Read the fairness statement →

CastCheck methodology v0.2 · data through 2026-08-30

KMSY — New Orleans Intl

29.9928, -90.2508 · 1 m· standard offset UTC-6 h · truth product CLIMSY

These pages are always bilinear interpolation, the headline method. The nearest-node variant, and every other window/initialization/interpolation/variable combination, is published on each permanent link below — follow any number.

Daily maximum temperature — MAE °F

the last 90 days, 12Z, bilinear. MAE with the bias and n underneath; every cell links to its permanent page. The sparkline shows the same model across lead days 1–9 on a scale shared within this table.
Modeld0d1d2d3d4d5d6d7d8d9lead 1–9
ECMWF AIFS Singleaifs_single 4.84-4.67 · n=29 4.77-4.77 · n=28 4.81-4.81 · n=27 4.89-4.89 · n=26 4.80-4.80 · n=24 5.23-5.23 · n=24 5.17-5.17 · n=23 5.33-5.33 · n=22 5.58-5.58 · n=21 ECMWF AIFS Single MAE by lead day 1 to 9, tmax
Aurora (GFS init)aurora_gfs 7.46-7.46 · n=2 5.57-5.57 · n=1 Aurora (GFS init) MAE by lead day 1 to 9, tmax
Aurora (IFS init)aurora_ifs 7.03-7.03 · n=2 3.89-3.89 · n=1 Aurora (IFS init) MAE by lead day 1 to 9, tmax
FourCastNet v2 (GFS init)fourcastnet_gfs 3.56-3.56 · n=2 2.22-2.22 · n=1 FourCastNet v2 (GFS init) MAE by lead day 1 to 9, tmax
FourCastNet v2 (IFS init)fourcastnet_ifs 2.73-2.73 · n=2 1.49-1.49 · n=1 FourCastNet v2 (IFS init) MAE by lead day 1 to 9, tmax
NCEP GFSgfs 4.84-4.57 · n=29 4.48-4.48 · n=28 4.10-4.10 · n=27 4.47-4.16 · n=26 4.31-3.97 · n=25 4.90-4.65 · n=24 3.97-3.51 · n=23 4.48-4.36 · n=22 4.52-4.26 · n=21 NCEP GFS MAE by lead day 1 to 9, tmax
GraphCast (GFS init)graphcast_gfs 5.90-5.90 · n=2 4.62-4.62 · n=1 GraphCast (GFS init) MAE by lead day 1 to 9, tmax
GraphCast (IFS init)graphcast_ifs 5.57-5.46 · n=27 5.45-5.45 · n=26 5.41-5.41 · n=25 5.68-5.68 · n=25 5.80-5.80 · n=25 5.81-5.81 · n=24 5.52-5.52 · n=23 5.63-5.63 · n=22 5.65-5.29 · n=21 GraphCast (IFS init) MAE by lead day 1 to 9, tmax
ECMWF IFS HRESifs_hres 4.44-4.07 · n=24 4.71-4.71 · n=22 4.54-4.54 · n=22 4.21-4.21 · n=21 4.61-4.61 · n=20 5.05-5.05 · n=19 5.19-5.15 · n=17 4.15-4.01 · n=17 4.19-3.85 · n=15 ECMWF IFS HRES MAE by lead day 1 to 9, tmax
Pangu-Weather (GFS init)pangu_gfs 4.19-4.19 · n=2 3.69-3.69 · n=1 Pangu-Weather (GFS init) MAE by lead day 1 to 9, tmax
Pangu-Weather (IFS init)pangu_ifs 3.90-3.90 · n=2 3.40-3.40 · n=1 Pangu-Weather (IFS init) MAE by lead day 1 to 9, tmax
Persistence (baseline)persistence 1.96-0.04 · n=90 2.39-0.08 · n=90 2.61-0.12 · n=90 2.81-0.12 · n=90 2.89-0.20 · n=90 3.08-0.28 · n=90 3.17-0.39 · n=90 3.21-0.61 · n=90 3.22-0.80 · n=90 Persistence (baseline) MAE by lead day 1 to 9, tmax

Up to 1 of the scored days in this table carry a QC flag on the observation (a CLI value that disagreed with the hourly observations, or a fallback source). They are kept in the scores and counted here rather than dropped — see methodology.

+ model too warm · − model too cold · bias interval includes zero · ★ lowest MAE · = not distinguishable from the leader · ▼ significantly worse · n < 30 greyed and unranked · CI is a 95 % moving-block bootstrap interval.

Daily minimum temperature — MAE °F

the last 90 days, 12Z, bilinear. MAE with the bias and n underneath; every cell links to its permanent page. The sparkline shows the same model across lead days 1–9 on a scale shared within this table.
Modeld0d1d2d3d4d5d6d7d8d9lead 1–9
ECMWF AIFS Singleaifs_single 2.51+2.30 · n=29 2.70+2.43 · n=28 2.84+2.55 · n=27 2.83+2.54 · n=26 3.19+2.90 · n=24 3.25+3.05 · n=24 3.26+2.99 · n=23 3.11+2.79 · n=22 2.93+2.21 · n=21 ECMWF AIFS Single MAE by lead day 1 to 9, tmin
Aurora (GFS init)aurora_gfs 2.59-0.56 · n=2 3.10-3.10 · n=1 Aurora (GFS init) MAE by lead day 1 to 9, tmin
Aurora (IFS init)aurora_ifs 2.57-0.96 · n=2 3.73-3.73 · n=1 Aurora (IFS init) MAE by lead day 1 to 9, tmin
FourCastNet v2 (GFS init)fourcastnet_gfs 1.77-0.47 · n=2 2.44-2.44 · n=1 FourCastNet v2 (GFS init) MAE by lead day 1 to 9, tmin
FourCastNet v2 (IFS init)fourcastnet_ifs 1.98-0.11 · n=2 2.14-2.14 · n=1 FourCastNet v2 (IFS init) MAE by lead day 1 to 9, tmin
NCEP GFSgfs 1.47+1.01 · n=29 1.73+1.25 · n=28 1.67+1.15 · n=27 1.91+1.25 · n=26 2.10+1.15 · n=25 2.19+1.18 · n=24 2.21+1.09 · n=23 1.94+1.01 · n=22 1.70+0.32 · n=21 NCEP GFS MAE by lead day 1 to 9, tmin
GraphCast (GFS init)graphcast_gfs 2.50-0.38 · n=2 2.72-2.72 · n=1 GraphCast (GFS init) MAE by lead day 1 to 9, tmin
GraphCast (IFS init)graphcast_ifs 2.81+2.54 · n=27 2.83+2.48 · n=26 2.73+2.65 · n=25 2.63+2.51 · n=25 2.78+2.36 · n=25 2.85+2.46 · n=24 2.89+2.43 · n=23 2.83+2.49 · n=22 2.93+2.36 · n=21 GraphCast (IFS init) MAE by lead day 1 to 9, tmin
ECMWF IFS HRESifs_hres 3.11+2.94 · n=24 3.22+2.85 · n=22 3.12+2.90 · n=22 3.61+3.34 · n=21 3.24+2.82 · n=20 3.30+3.11 · n=19 3.68+2.80 · n=17 3.59+2.79 · n=17 3.59+2.24 · n=15 ECMWF IFS HRES MAE by lead day 1 to 9, tmin
Pangu-Weather (GFS init)pangu_gfs 1.83-1.38 · n=2 4.71-4.71 · n=1 Pangu-Weather (GFS init) MAE by lead day 1 to 9, tmin
Pangu-Weather (IFS init)pangu_ifs 2.45-2.27 · n=2 5.34-5.34 · n=1 Pangu-Weather (IFS init) MAE by lead day 1 to 9, tmin
Persistence (baseline)persistence 1.44-0.07 · n=90 1.97-0.08 · n=90 2.11-0.11 · n=90 2.04-0.11 · n=90 1.99-0.12 · n=90 2.12-0.12 · n=90 2.06-0.21 · n=90 2.20-0.31 · n=90 2.30-0.37 · n=90 Persistence (baseline) MAE by lead day 1 to 9, tmin

Up to 1 of the scored days in this table carry a QC flag on the observation (a CLI value that disagreed with the hourly observations, or a fallback source). They are kept in the scores and counted here rather than dropped — see methodology.

Month-by-month slices, model availability and the observed-truth table live on the canonical page: they do not depend on the window, initialization or interpolation selected here.

All scores as JSON scores_latest.csv daily_errors.csv.gz data & licences