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

KNYC — New York Central Park

40.7833, -73.9667 · 47 m· standard offset UTC-5 h · truth product CLINYC

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, 00Z, 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 1.46-0.21 · n=30 1.26-0.31 · n=29 1.90-0.43 · n=28 1.89-0.34 · n=27 2.20-0.78 · n=26 2.31-0.63 · n=25 2.28-0.57 · n=24 2.19-1.22 · n=23 2.34-1.83 · n=22 4.44-2.57 · n=21 ECMWF AIFS Single MAE by lead day 1 to 9, tmax
Aurora (GFS init)aurora_gfs 0.95-0.95 · n=2 0.24-0.24 · n=1 Aurora (GFS init) MAE by lead day 1 to 9, tmax
Aurora (IFS init)aurora_ifs 2.18-1.39 · n=3 0.28-0.11 · n=2 1.64+1.64 · n=1 Aurora (IFS init) MAE by lead day 1 to 9, tmax
FourCastNet v2 (GFS init)fourcastnet_gfs 1.69+0.53 · n=2 0.60+0.60 · n=1 FourCastNet v2 (GFS init) MAE by lead day 1 to 9, tmax
FourCastNet v2 (IFS init)fourcastnet_ifs 2.89-1.75 · n=3 2.01+1.18 · n=2 0.52+0.52 · n=1 FourCastNet v2 (IFS init) MAE by lead day 1 to 9, tmax
NCEP GFSgfs 3.36+3.06 · n=30 3.80+3.18 · n=29 4.14+2.47 · n=28 3.80+3.00 · n=27 4.17+2.71 · n=26 4.40+2.52 · n=25 4.45+3.63 · n=24 4.16+3.00 · n=23 3.67+1.72 · n=22 5.21+2.84 · n=21 NCEP GFS MAE by lead day 1 to 9, tmax
GraphCast (GFS init)graphcast_gfs 0.97-0.97 · n=2 2.18-2.18 · n=1 GraphCast (GFS init) MAE by lead day 1 to 9, tmax
GraphCast (IFS init)graphcast_ifs 1.80-1.31 · n=28 2.07-1.69 · n=27 2.41-1.62 · n=26 2.35-1.63 · n=25 2.66-1.67 · n=25 2.79-1.07 · n=25 2.38-1.38 · n=24 2.37-1.26 · n=23 3.52-0.80 · n=22 4.36-0.53 · n=21 GraphCast (IFS init) MAE by lead day 1 to 9, tmax
ECMWF IFS HRESifs_hres 2.41+0.32 · n=24 2.96-0.57 · n=23 2.12+0.28 · n=22 3.34+0.36 · n=22 3.33+1.27 · n=20 2.72+0.94 · n=18 3.80+1.86 · n=19 2.48+1.04 · n=18 3.43+0.93 · n=17 4.29+2.57 · n=16 ECMWF IFS HRES MAE by lead day 1 to 9, tmax
Pangu-Weather (GFS init)pangu_gfs 3.81+3.81 · n=2 4.44+4.44 · n=1 Pangu-Weather (GFS init) MAE by lead day 1 to 9, tmax
Pangu-Weather (IFS init)pangu_ifs 3.20+2.06 · n=3 3.71+3.71 · n=2 3.83+3.83 · n=1 Pangu-Weather (IFS init) MAE by lead day 1 to 9, tmax
Persistence (baseline)persistence 3.94-0.08 · n=90 5.47-0.09 · n=90 6.43-0.26 · n=90 6.61-0.28 · n=90 6.43-0.34 · n=90 6.44-0.31 · n=90 6.07-0.31 · n=90 6.41-0.39 · n=90 6.76-0.62 · 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, 00Z, 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 2.28+1.99 · n=30 2.47+2.20 · n=29 2.87+2.67 · n=28 2.76+2.70 · n=27 2.76+2.46 · n=26 2.68+2.49 · n=25 3.13+2.55 · n=24 2.74+2.66 · n=23 2.62+2.24 · n=22 3.33+2.21 · n=21 ECMWF AIFS Single MAE by lead day 1 to 9, tmin
Aurora (GFS init)aurora_gfs 0.82+0.82 · n=2 0.51+0.51 · n=1 Aurora (GFS init) MAE by lead day 1 to 9, tmin
Aurora (IFS init)aurora_ifs 1.23+1.05 · n=3 0.93+0.37 · n=2 0.03+0.03 · n=1 Aurora (IFS init) MAE by lead day 1 to 9, tmin
FourCastNet v2 (GFS init)fourcastnet_gfs 1.55+1.01 · n=2 0.24-0.24 · n=1 FourCastNet v2 (GFS init) MAE by lead day 1 to 9, tmin
FourCastNet v2 (IFS init)fourcastnet_ifs 1.98+0.15 · n=3 1.84+1.11 · n=2 0.99+0.99 · n=1 FourCastNet v2 (IFS init) MAE by lead day 1 to 9, tmin
NCEP GFSgfs 4.57+4.57 · n=30 4.92+4.92 · n=29 4.46+4.46 · n=28 5.21+5.21 · n=27 5.25+5.25 · n=26 5.08+4.47 · n=25 5.58+5.05 · n=24 5.37+4.93 · n=23 5.12+4.73 · n=22 5.32+4.64 · n=21 NCEP GFS MAE by lead day 1 to 9, tmin
GraphCast (GFS init)graphcast_gfs 0.59+0.45 · n=2 0.26+0.26 · n=1 GraphCast (GFS init) MAE by lead day 1 to 9, tmin
GraphCast (IFS init)graphcast_ifs 1.82+1.34 · n=28 1.69+0.84 · n=27 1.79+1.09 · n=26 2.03+1.74 · n=25 2.12+1.54 · n=25 2.26+1.35 · n=25 2.38+1.44 · n=24 2.57+1.26 · n=23 3.47+0.79 · n=22 3.32+1.06 · n=21 GraphCast (IFS init) MAE by lead day 1 to 9, tmin
ECMWF IFS HRESifs_hres 2.02+1.93 · n=24 1.77+1.48 · n=23 2.46+2.16 · n=22 3.24+3.24 · n=22 3.37+3.28 · n=20 2.64+2.19 · n=18 3.03+2.75 · n=19 3.21+3.00 · n=18 4.12+2.68 · n=17 4.05+3.29 · n=16 ECMWF IFS HRES MAE by lead day 1 to 9, tmin
Pangu-Weather (GFS init)pangu_gfs 2.04+0.08 · n=2 1.98-1.98 · n=1 Pangu-Weather (GFS init) MAE by lead day 1 to 9, tmin
Pangu-Weather (IFS init)pangu_ifs 2.35+0.88 · n=3 3.23-0.98 · n=2 2.11-2.11 · n=1 Pangu-Weather (IFS init) MAE by lead day 1 to 9, tmin
Persistence (baseline)persistence 2.69-0.16 · n=90 4.07-0.31 · n=90 4.50-0.50 · n=90 4.51-0.62 · n=90 4.63-0.66 · n=90 4.80-0.60 · n=90 4.93-0.67 · n=90 4.97-0.81 · n=90 5.22-1.00 · 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

MAE °F at lead day 1, 00Z, bilinear, daily maximum — the seasonal slice behind the window averages. A model that is excellent in one season and poor in another shows up here and nowhere else.

Monthaifs_singleaurora_gfsaurora_ifsfourcastnet_gfsfourcastnet_ifsgfsgraphcast_gfsgraphcast_ifsifs_hrespangu_gfspangu_ifs
2026-08 1.26-0.31 · n=290.24-0.24 · n=10.28-0.11 · n=20.60+0.60 · n=12.01+1.18 · n=23.80+3.18 · n=292.18-2.18 · n=12.07-1.69 · n=272.96-0.57 · n=234.44+4.44 · n=13.71+3.71 · n=2
2026-01 1.63-1.27 · n=6

Model availability at this station

ModelPeriod Scored daysCoverage
ECMWF AIFS Single 2026-08-02 → 2026-08-3029
Aurora (GFS init) 2026-08-30 → 2026-08-301
Aurora (IFS init) 2026-08-29 → 2026-08-302
FourCastNet v2 (GFS init) 2026-08-30 → 2026-08-301
FourCastNet v2 (IFS init) 2026-08-29 → 2026-08-302
NCEP GFS 2026-08-02 → 2026-08-3029
GraphCast (GFS init) 2026-08-30 → 2026-08-301
GraphCast (IFS init) 2026-01-02 → 2026-08-3033
ECMWF IFS HRES 2026-08-02 → 2026-08-3023
Pangu-Weather (GFS init) 2026-08-30 → 2026-08-301
Pangu-Weather (IFS init) 2026-08-29 → 2026-08-302
Persistence (baseline) 2024-01-02 → 2026-08-30972

Observed truth — last 30 days

Climatological dayTmax °F Tmin °FSourceFlag
2026-08-307867OBSobs_fallback
2026-08-297664CLI
2026-08-288468CLI
2026-08-277768CLI
2026-08-268164CLI
2026-08-257863CLI
2026-08-247965CLI
2026-08-238068CLI
2026-08-227767CLI
2026-08-217963CLI
2026-08-208463CLI
2026-08-198569CLI
2026-08-188672CLI
2026-08-178168CLI
2026-08-168067CLI
2026-08-158368CLI
2026-08-148471CLI
2026-08-138570CLI
2026-08-128471CLI
2026-08-118572CLI
2026-08-108572CLI
2026-08-098875CLI
2026-08-088771CLI
2026-08-079172CLI
2026-08-068875CLI
2026-08-058370CLI
2026-08-048466CLI
2026-08-038071CLI
2026-08-028375CLI
2026-08-018672CLI

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