Forecast Scoreboard Forecast
Scoreboard

Days 1–5. Compared with the National Weather Service forecast from the same hour. No one pays for a rank.

Hurricane tracks

Tropical Storm Gonzalo Model Accuracy: DeepMind vs GFS vs WeatherNext 3

Final advisory

NHC issued its final advisory at 2:00 PM ET Sat, Sep 26.

Tropical Storm Gonzalo has 17 positions on the best track, which is where the storm actually went, from the operational NHC file. 4 official forecast tracks are drawn. At 12 hours, the average track miss is 21 miles across 6 forecasts. At 12 hours, the official wind forecast averaged 48 mph and where the storm actually went averaged 46 mph. Stored model tracks on these forecast tracks: GFS, GEFS mean, Canadian GEM, UKMET, HAFS-A, HAFS-B, HWRF, HMON, NAVGEM, Google DeepMind, WeatherNext 3.

AL072026 · 2026 · Sep 22-26, 2026. Score table. Damage reports.

How to read this. The solid line is where the storm went. A dashed line is where the official forecast said it would go. A smaller path miss is closer. Distances are statute miles. Wind speeds are miles per hour.

The technical details

Path miss on this page is the great-circle distance in statute miles, the same miles as the home card and the score table. The Earth radius is 3,958.7613 miles. The file also keeps that distance in nautical miles. One nautical mile is 1,852 meters, about 1.15 statute miles. A case counts when that forecast and the best track (BEST, lead 0) share the same valid time. Positions are not interpolated. A model track counts even when that cycle has no official forecast yet. Skill against the official forecast (OFCL) still requires the official forecast from the same issue time and lead.

Shown leads are 12, 24, 36, 48, 60, 72, 96, and 120 hours, once a paired fix exists. Sample size is the number of paired cases at that lead. Overall rank still uses 24, 48, 72, and 120 hours. The 96-hour lead is drawn when the deck has a paired fix, and it is not in that rank.

Wind on this page is miles per hour. The file stores maximum wind in knots. One knot is about 1.15 miles per hour. An advisory wind is rounded to the nearest 5 mph. A mean on this page is rounded to the nearest mile per hour. Wind miss is the absolute difference on the paired cases. There is no confidence interval on this map. The daily board’s interval is a 95% percentile bootstrap.

Overall rank is the average of the path rank and the wind rank on this storm. Each rank uses the graded leads at 24, 48, 72, and 120 hours, and each of those leads counts once, however many forecasts it holds. A lower miss is the better rank. A tie shares the average of the places those forecasts occupy. A source is ranked only with at least 3 graded forecasts for path and 3 for wind. Fewer than that says Not enough forecasts yet. A source with no graded path, or no graded wind, is left out of both ranks, and overall shows —.

The best track is the operational NHC b-deck. It is preliminary and revised after the season. HURDAT2 is not loaded. Model lines come from the public a-deck for the same forecast tracks, and only when that file stores them. Google DeepMind is the Weather Lab operational ensemble mean. WeatherNext 3 is that model’s ensemble mean from the same download. ECMWF AIFS, ECMWF HRES, and the ECMWF ENS mean are tropical-cyclone tracks from ECMWF open data. The ECMWF ENS mean is the average of the member centers in the IFS ensemble track file. AI GFS is NOAA’s AIGFS tracker when that file is still posted. The methodology page names the aids that are scored.

The methodology page is the full reference. How we grade says the same rules in plain English.

The best track is the operational NHC b-deck. It is preliminary and is revised after the season. The post-season HURDAT2 track is not loaded.

ECMWF AIFS, ECMWF HRES, ECMWF ENS mean, AI GFS: No graded forecasts yet.

Overall rank

Overall averages each forecast's rank on path and on wind strength. See the separate scores below.

Place on this list. 1 was closest to the weather that happened. A tie shares this number, and the next place skips ahead. Early read until the longer day count, then proven. The forecast source this row scores. Path and wind ranksOverall averages each forecast's rank on path and on wind strength. See the separate scores below. Track rankPlace on path miss. 1 was closest. On one storm this is that place. Across storms it is the average of those places. Each graded lead counts once. A tie shares the average place. Intensity rankPlace on wind miss. 1 was closest. On one storm this is that place. Across storms it is the average of those places. Each graded lead counts once. A tie shares the average place.
1 WeatherNext 3 1 1 1
2 Google DeepMind 2 2 2
3 NHC official 3.5 3 4
4 GEFS mean 4 5 3
5 NAVGEM 5 4 6
6 GFS 7.5 10 5
6 HAFS-A 7.5 7 8
6 HAFS-B 7.5 8 7
9 HMON 8 6 10
10 HWRF 9 9 9
— Canadian GEM Not enough forecasts yet — —
— UKMET Not enough forecasts yet — —

How we grade

Track and intensity by model

Each row is one source at one lead that has already verified, including 12, 24, 36, and 48 hours. The count is how many forecasts shared a time with where the storm went. Path miss is statute miles. Wind miss is miles per hour. The rank number is that source's place in the table above, and it still uses 24, 48, 72, and 120 hours.

Place on this list. 1 was closest to the weather that happened. A tie shares this number, and the next place skips ahead. Early read until the longer day count, then proven. The forecast source this row scores. LeadHow many hours ahead this forecast was made. Scored leads are 24, 48, 72, and 120. The technical name is lead. CasesHow many past forecasts went into this average. A forecast counts only when the best track has a fix at that exact time. The technical name is cases. Track errorAverage how far the predicted storm path was from where it actually went, in miles. Lower is better. The technical name is track error. Track skillHow that path miss compares with the official hurricane forecast. Positive means better than the official forecast. Negative means worse. The technical name is track skill. Intensity errorAverage how far off the predicted wind speed was, in miles per hour. The file stores knots. Lower is better. The technical name is intensity error. Intensity skillHow that wind miss compares with the official hurricane forecast. Positive means better. Negative means worse. The technical name is intensity skill.
1 WeatherNext 3 12 h 6 17 mi Beats the official forecast by 19% 2 mph Behind the official forecast by 20%
1 WeatherNext 3 24 h 4 23 mi Beats the official forecast by 36% 1 mph Beats the official forecast by 73%
1 WeatherNext 3 36 h 2 22 mi Beats the official forecast by 68% 2 mph Beats the official forecast by 40%
2 Google DeepMind 12 h 6 17 mi Beats the official forecast by 23% 3 mph Behind the official forecast by 40%
2 Google DeepMind 24 h 4 30 mi Beats the official forecast by 15% 1 mph Beats the official forecast by 67%
2 Google DeepMind 36 h 2 53 mi Beats the official forecast by 21% 1 mph Beats the official forecast by 80%
3 NHC official 12 h 6 21 mi — 2 mph —
3 NHC official 24 h 4 36 mi — 4 mph —
3 NHC official 36 h 2 67 mi — 3 mph —
4 GEFS mean 12 h 12 89 mi Behind the official forecast by 304% 4 mph Behind the official forecast by 150%
4 GEFS mean 24 h 10 113 mi Behind the official forecast by 218% 6 mph Beats the official forecast by 7%
4 GEFS mean 36 h 8 118 mi Behind the official forecast by 84% 7 mph Beats the official forecast by 80%
4 GEFS mean 48 h 6 89 mi — 9 mph —
4 GEFS mean 60 h 4 39 mi — 8 mph —
4 GEFS mean 72 h 2 37 mi — 8 mph —
5 NAVGEM 12 h 11 69 mi Behind the official forecast by 250% 8 mph Behind the official forecast by 470%
5 NAVGEM 24 h 9 76 mi Behind the official forecast by 141% 10 mph Behind the official forecast by 100%
5 NAVGEM 36 h 7 65 mi Behind the official forecast by 21% 11 mph Behind the official forecast by 40%
5 NAVGEM 48 h 5 78 mi — 10 mph —
5 NAVGEM 60 h 4 84 mi — 5 mph —
5 NAVGEM 72 h 2 95 mi — 3 mph —
6 GFS 12 h 12 127 mi Behind the official forecast by 476% 4 mph Behind the official forecast by 100%
6 GFS 24 h 10 167 mi Behind the official forecast by 357% 6 mph Behind the official forecast by 67%
6 GFS 36 h 8 201 mi Behind the official forecast by 212% 6 mph Behind the official forecast by 40%
6 GFS 48 h 6 182 mi — 7 mph —
6 GFS 60 h 4 157 mi — 5 mph —
6 GFS 72 h 2 105 mi — 7 mph —
6 HAFS-A 12 h 12 122 mi Behind the official forecast by 367% 14 mph Behind the official forecast by 820%
6 HAFS-A 24 h 10 156 mi Behind the official forecast by 290% 9 mph Behind the official forecast by 153%
6 HAFS-A 36 h 8 151 mi Behind the official forecast by 133% 7 mph Behind the official forecast by 180%
6 HAFS-A 48 h 6 86 mi — 3 mph —
6 HAFS-A 60 h 4 109 mi — 13 mph —
6 HAFS-A 72 h 2 83 mi — 14 mph —
6 HAFS-B 12 h 12 131 mi Behind the official forecast by 438% 14 mph Behind the official forecast by 860%
6 HAFS-B 24 h 10 170 mi Behind the official forecast by 327% 9 mph Behind the official forecast by 140%
6 HAFS-B 36 h 8 141 mi Behind the official forecast by 143% 4 mph Beats the official forecast by 20%
6 HAFS-B 48 h 6 96 mi — 5 mph —
6 HAFS-B 60 h 4 106 mi — 15 mph —
6 HAFS-B 72 h 2 105 mi — 7 mph —
9 HMON 12 h 6 87 mi Behind the official forecast by 303% 10 mph Behind the official forecast by 420%
9 HMON 24 h 4 125 mi Behind the official forecast by 248% 14 mph Behind the official forecast by 233%
9 HMON 36 h 2 192 mi Behind the official forecast by 188% 10 mph Behind the official forecast by 260%
10 HWRF 12 h 6 56 mi Behind the official forecast by 162% 4 mph Behind the official forecast by 120%
10 HWRF 24 h 4 157 mi Behind the official forecast by 335% 12 mph Behind the official forecast by 180%
10 HWRF 36 h 2 228 mi Behind the official forecast by 243% 13 mph Behind the official forecast by 360%
— UKMET 12 h 6 66 mi Behind the official forecast by 258% 5 mph Behind the official forecast by 160%
— UKMET 24 h 5 82 mi Behind the official forecast by 116% 8 mph Ties the official forecast
— UKMET 36 h 4 94 mi Behind the official forecast by 51% 9 mph Beats the official forecast by 20%
— UKMET 48 h 3 143 mi — 7 mph —
— UKMET 60 h 2 195 mi — 9 mph —
— UKMET 72 h 1 254 mi — 5 mph —
— Canadian GEM 12 h 6 77 mi Behind the official forecast by 168% 9 mph Behind the official forecast by 180%
— Canadian GEM 24 h 5 82 mi Behind the official forecast by 47% 4 mph Beats the official forecast by 80%
— Canadian GEM 36 h 4 80 mi Beats the official forecast by 7% 2 mph Beats the official forecast by 60%
— Canadian GEM 48 h 3 104 mi — 4 mph —
— Canadian GEM 60 h 2 100 mi — 5 mph —
— Canadian GEM 72 h 1 106 mi — 1 mph —

How we grade

ECMWF AIFS, ECMWF HRES, ECMWF ENS mean, AI GFS: No graded forecasts yet.

Track map

The solid line is the best track. Dashed lines are official forecast tracks from a few advisories, from the issue position out through the leads stored in that advisory. Thinner lines are model tracks from NHC’s public a-deck for those same advisories, and only when that file actually contains them. Google DeepMind and WeatherNext 3 are ensemble-mean tracks from Weather Lab, drawn on those same advisories. ECMWF AIFS, ECMWF HRES, and the ECMWF ENS mean are open-data cyclone tracks, drawn the same way. AI GFS is NOAA’s AIGFS tracker, drawn when that file is still posted.

6°N 13°N 21°N 29°N 35°W 27°W 19°W 11°W
Map of Tropical Storm Gonzalo. The best track, where the storm actually went, has 17 positions. 4 official forecast tracks are drawn. Model lines: GFS, GEFS mean, Canadian GEM, UKMET, HAFS-A, HAFS-B, HWRF, HMON, NAVGEM, Google DeepMind, WeatherNext 3. Latitude and longitude, scaled by the cosine of the mid-latitude so a degree of longitude is not stretched.
  • Actual track (17 positions)
  • NHC official Sep 25, 00:00 UTC
  • NHC official Sep 25, 12:00 UTC
  • NHC official Sep 26, 06:00 UTC
  • NHC official Sep 26, 18:00 UTC
  • GFS
  • GEFS mean
  • Canadian GEM
  • UKMET
  • HAFS-A
  • HAFS-B
  • HWRF
  • HMON
  • NAVGEM
  • Google DeepMind
  • WeatherNext 3

The chart measures how far the track was off in statute miles, the same miles as the home card. It includes 12, 24, 36, 48, 60, 72, 96, and 120 hours when a paired fix exists. The overall rank uses 24, 48, 72, and 120 hours. Positions are not interpolated.

How far the track was off

21 mi 12 h 36 mi 24 h 67 mi 36 h
Average official track miss in miles by how far ahead. 12 hours 21 miles over 6 forecasts. 24 hours 36 miles over 4 forecasts. 36 hours 67 miles over 2 forecasts.
LeadHow many hours ahead this forecast was made. This map shows 12, 24, 36, 48, 60, 72, 96, and 120 when a paired fix exists. Overall rank uses 24, 48, 72, and 120. The technical name is lead. CasesHow many past forecasts went into this average. A forecast counts only when the best track has a fix at that exact time. The technical name is cases. Track errorAverage how far the predicted storm path was from where it actually went, in statute miles. Lower is better. The technical name is track error. Intensity errorAverage how far off the predicted wind speed was, in miles per hour, on this page. Lower is better. The file stores knots. The technical name is intensity error. Forecast max windAverage top wind in the official forecast, in miles per hour, on the paired cases. The file stores knots. The technical name is forecast maximum wind. Best-track windAverage top wind where the storm actually went, in miles per hour, at the same times. The file stores knots. The technical name is best-track wind.
12 h 6 21 mi 2 mph 48 mph 46 mph
24 h 4 36 mi 4 mph 47 mph 43 mph
36 h 2 67 mi 3 mph 43 mph 40 mph

Miles are statute miles. Wind is miles per hour. The National Hurricane Center file stores wind in knots. One knot is about 1.15 miles per hour. Nautical miles are in the technical details.

How we grade

Top wind

12 h 24 h 36 h
Top wind, official forecast versus where the storm went. At 12 hours the forecast averaged 48 mph and where the storm actually went averaged 46 mph. At 24 hours the forecast averaged 47 mph and where the storm actually went averaged 43 mph. At 36 hours the forecast averaged 43 mph and where the storm actually went averaged 40 mph.
  • Official forecast maximum wind
  • Best-track maximum wind

Source: National Hurricane Center / NOAA. The operational b-deck and the public a-deck are U.S. government works in the public domain. Google DeepMind and WeatherNext 3 ensemble means are experimental forecasts from Google DeepMind Weather Lab. Forecasts older than 48 hours are used under CC BY 4.0. ECMWF AIFS, ECMWF HRES, and ECMWF ENS tracks are ECMWF open data, used under CC BY 4.0. AI GFS tracks are a NOAA AIGFS product. Forecast Scoreboard is not affiliated with NHC, NOAA, Google, or ECMWF.