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

KLAX — Los Angeles Intl

33.9381, -118.3889 · 38 m· standard offset UTC-8 h · truth product CLILAX

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 1.48+0.57 · n=29 1.43+0.53 · n=28 1.41+0.67 · n=27 1.39+0.61 · n=26 1.49+0.49 · n=24 1.76+0.23 · n=24 2.17-0.35 · n=23 2.01-0.32 · n=22 2.11-1.01 · n=21 ECMWF AIFS Single MAE by lead day 1 to 9, tmax
Aurora (GFS init)aurora_gfs 6.93-6.93 · n=2 6.28-6.28 · n=1 Aurora (GFS init) MAE by lead day 1 to 9, tmax
Aurora (IFS init)aurora_ifs 5.89-5.89 · n=2 6.03-6.03 · n=1 Aurora (IFS init) MAE by lead day 1 to 9, tmax
FourCastNet v2 (GFS init)fourcastnet_gfs 3.47-3.47 · n=2 2.76-2.76 · n=1 FourCastNet v2 (GFS init) MAE by lead day 1 to 9, tmax
FourCastNet v2 (IFS init)fourcastnet_ifs 3.51-3.51 · n=2 2.68-2.68 · n=1 FourCastNet v2 (IFS init) MAE by lead day 1 to 9, tmax
NCEP GFSgfs 1.90-0.88 · n=29 2.15-0.63 · n=28 2.02-0.59 · n=27 2.13-0.68 · n=26 1.80-0.65 · n=25 1.80-0.87 · n=24 2.18-0.69 · n=23 2.82-1.42 · n=22 2.80-1.88 · n=21 NCEP GFS MAE by lead day 1 to 9, tmax
GraphCast (GFS init)graphcast_gfs 5.84-5.84 · n=2 5.33-5.33 · n=1 GraphCast (GFS init) MAE by lead day 1 to 9, tmax
GraphCast (IFS init)graphcast_ifs 3.52-3.52 · n=27 3.62-3.62 · n=26 3.55-3.55 · n=25 3.72-3.72 · n=25 3.68-3.67 · n=25 3.75-3.73 · n=24 3.88-3.88 · n=23 4.24-4.24 · n=22 4.96-4.96 · n=21 GraphCast (IFS init) MAE by lead day 1 to 9, tmax
ECMWF IFS HRESifs_hres 2.42-2.18 · n=24 2.28-2.07 · n=22 2.20-1.90 · n=22 2.31-1.54 · n=21 2.29-1.34 · n=20 2.42-1.47 · n=19 2.35-1.67 · n=17 2.59-2.09 · n=17 4.78-3.05 · n=14 ECMWF IFS HRES MAE by lead day 1 to 9, tmax
Pangu-Weather (GFS init)pangu_gfs 1.87-1.87 · n=2 2.73-2.73 · n=1 Pangu-Weather (GFS init) MAE by lead day 1 to 9, tmax
Pangu-Weather (IFS init)pangu_ifs 2.74-2.74 · n=2 3.72-3.72 · n=1 Pangu-Weather (IFS init) MAE by lead day 1 to 9, tmax
Persistence (baseline)persistence 1.61-0.12 · n=90 1.91-0.29 · n=90 2.01-0.46 · n=90 2.21-0.70 · n=90 2.38-0.91 · n=90 2.48-1.12 · n=90 2.72-1.30 · n=90 2.77-1.48 · n=90 2.94-1.63 · n=90 Persistence (baseline) MAE by lead day 1 to 9, tmax

Up to 2 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 0.53-0.03 · n=29 0.56-0.23 · n=28 0.70-0.31 · n=27 0.81-0.25 · n=26 0.69-0.33 · n=24 0.73-0.43 · n=24 0.91-0.48 · n=23 1.35-0.64 · n=22 1.20-0.92 · n=21 ECMWF AIFS Single MAE by lead day 1 to 9, tmin
Aurora (GFS init)aurora_gfs 2.72-2.72 · n=2 2.93-2.93 · n=1 Aurora (GFS init) MAE by lead day 1 to 9, tmin
Aurora (IFS init)aurora_ifs 1.41-1.41 · n=2 2.65-2.65 · n=1 Aurora (IFS init) MAE by lead day 1 to 9, tmin
FourCastNet v2 (GFS init)fourcastnet_gfs 1.63+1.63 · n=2 1.98+1.98 · n=1 FourCastNet v2 (GFS init) MAE by lead day 1 to 9, tmin
FourCastNet v2 (IFS init)fourcastnet_ifs 1.88+1.88 · n=2 1.66+1.66 · n=1 FourCastNet v2 (IFS init) MAE by lead day 1 to 9, tmin
NCEP GFSgfs 2.98+2.86 · n=29 3.47+3.30 · n=28 3.58+3.44 · n=27 3.49+3.38 · n=26 3.53+3.42 · n=25 3.38+3.34 · n=24 3.30+3.30 · n=23 3.33+3.03 · n=22 2.98+2.24 · n=21 NCEP GFS MAE by lead day 1 to 9, tmin
GraphCast (GFS init)graphcast_gfs 1.78-1.78 · n=2 2.46-2.46 · n=1 GraphCast (GFS init) MAE by lead day 1 to 9, tmin
GraphCast (IFS init)graphcast_ifs 0.72-0.49 · n=27 0.97-0.73 · n=26 0.90-0.73 · n=25 0.87-0.72 · n=25 0.95-0.68 · n=25 0.97-0.54 · n=24 1.12-0.45 · n=23 1.35-0.50 · n=22 1.86-1.06 · n=21 GraphCast (IFS init) MAE by lead day 1 to 9, tmin
ECMWF IFS HRESifs_hres 0.76+0.55 · n=24 0.84+0.68 · n=22 1.03+0.71 · n=22 1.36+1.21 · n=21 1.30+1.05 · n=20 1.34+1.19 · n=19 1.78+1.56 · n=17 1.70+1.18 · n=17 2.19-0.09 · n=14 ECMWF IFS HRES MAE by lead day 1 to 9, tmin
Pangu-Weather (GFS init)pangu_gfs 1.18-0.04 · n=2 2.12-2.12 · n=1 Pangu-Weather (GFS init) MAE by lead day 1 to 9, tmin
Pangu-Weather (IFS init)pangu_ifs 0.77-0.05 · n=2 2.31-2.31 · n=1 Pangu-Weather (IFS init) MAE by lead day 1 to 9, tmin
Persistence (baseline)persistence 0.96-0.11 · n=90 1.40-0.27 · n=90 1.42-0.42 · n=90 1.42-0.60 · n=90 1.56-0.78 · n=90 1.81-0.92 · n=90 2.00-1.04 · n=90 2.07-1.18 · n=90 2.20-1.29 · n=90 Persistence (baseline) MAE by lead day 1 to 9, tmin

Up to 2 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