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

Hurricane Nolo Model Accuracy: DeepMind vs GFS vs WeatherNext 3

Final advisory

NHC issued its final advisory at 2:00 PM ET Sun, Oct 4.

Hurricane Nolo has 98 positions on the best track, which is where the storm actually went, from the operational NHC file. 4 official forecast tracks are drawn. At 48 hours, the average track miss is 49 miles across 47 forecasts. At 48 hours, the official wind forecast averaged 88 mph and where the storm actually went averaged 86 mph. Stored model tracks on these forecast tracks: GFS, GEFS mean, HAFS-A, HAFS-B, HWRF, HMON, NAVGEM, Google DeepMind, WeatherNext 3.

EP152026 · 2026 · Sep 10–Oct 4, 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 2.5 3 2
2 NHC official 2.5 2 3
4 HAFS-A 6 7 5
4 HAFS-B 6 8 4
4 HWRF 6 6 6
7 GFS 6.5 5 8
8 GEFS mean 7 4 10
9 HMON 9 11 7
10 UKMET 10 9 11
11 NAVGEM 10.5 12 9
12 Canadian GEM 11 10 12

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 57 14 mi Beats the official forecast by 35% 8 mph Behind the official forecast by 30%
1 WeatherNext 3 24 h 55 21 mi Beats the official forecast by 36% 8 mph Beats the official forecast by 22%
1 WeatherNext 3 36 h 51 25 mi Beats the official forecast by 39% 9 mph Beats the official forecast by 34%
1 WeatherNext 3 48 h 48 30 mi Beats the official forecast by 40% 10 mph Beats the official forecast by 26%
1 WeatherNext 3 60 h 44 38 mi Beats the official forecast by 33% 11 mph Beats the official forecast by 3%
1 WeatherNext 3 72 h 40 46 mi Beats the official forecast by 22% 13 mph Behind the official forecast by 10%
1 WeatherNext 3 96 h 33 59 mi Beats the official forecast by 31% 16 mph Behind the official forecast by 5%
1 WeatherNext 3 120 h 29 78 mi Beats the official forecast by 39% 17 mph Beats the official forecast by 19%
2 Google DeepMind 12 h 57 17 mi Beats the official forecast by 23% 8 mph Behind the official forecast by 26%
2 Google DeepMind 24 h 55 26 mi Beats the official forecast by 23% 8 mph Beats the official forecast by 21%
2 Google DeepMind 36 h 50 33 mi Beats the official forecast by 18% 9 mph Beats the official forecast by 37%
2 Google DeepMind 48 h 46 45 mi Beats the official forecast by 5% 10 mph Beats the official forecast by 27%
2 Google DeepMind 60 h 44 57 mi Behind the official forecast by 2% 12 mph Beats the official forecast by 1%
2 Google DeepMind 72 h 40 68 mi Behind the official forecast by 18% 14 mph Behind the official forecast by 12%
2 Google DeepMind 96 h 33 87 mi Behind the official forecast by 7% 19 mph Behind the official forecast by 23%
2 Google DeepMind 120 h 29 123 mi Behind the official forecast by 5% 20 mph Behind the official forecast by 2%
2 NHC official 12 h 55 21 mi — 6 mph —
2 NHC official 24 h 52 32 mi — 11 mph —
2 NHC official 36 h 49 41 mi — 14 mph —
2 NHC official 48 h 47 49 mi — 13 mph —
2 NHC official 60 h 45 54 mi — 12 mph —
2 NHC official 72 h 43 60 mi — 12 mph —
2 NHC official 96 h 38 80 mi — 13 mph —
2 NHC official 120 h 27 114 mi — 20 mph —
4 HAFS-A 12 h 82 39 mi Behind the official forecast by 20% 10 mph Behind the official forecast by 64%
4 HAFS-A 24 h 79 58 mi Behind the official forecast by 41% 11 mph Behind the official forecast by 22%
4 HAFS-A 36 h 77 62 mi Behind the official forecast by 31% 11 mph Beats the official forecast by 1%
4 HAFS-A 48 h 75 76 mi Behind the official forecast by 37% 13 mph Behind the official forecast by 10%
4 HAFS-A 60 h 73 93 mi Behind the official forecast by 44% 13 mph Behind the official forecast by 18%
4 HAFS-A 72 h 71 108 mi Behind the official forecast by 47% 12 mph Beats the official forecast by 5%
4 HAFS-A 96 h 67 142 mi Behind the official forecast by 54% 18 mph Behind the official forecast by 25%
4 HAFS-A 120 h 63 205 mi Behind the official forecast by 63% 20 mph Behind the official forecast by 18%
4 HAFS-B 12 h 82 39 mi Behind the official forecast by 21% 10 mph Behind the official forecast by 68%
4 HAFS-B 24 h 80 54 mi Behind the official forecast by 32% 10 mph Behind the official forecast by 8%
4 HAFS-B 36 h 78 63 mi Behind the official forecast by 35% 11 mph Beats the official forecast by 5%
4 HAFS-B 48 h 76 72 mi Behind the official forecast by 33% 10 mph Beats the official forecast by 7%
4 HAFS-B 60 h 74 83 mi Behind the official forecast by 32% 11 mph Behind the official forecast by 7%
4 HAFS-B 72 h 72 96 mi Behind the official forecast by 39% 12 mph Behind the official forecast by 12%
4 HAFS-B 96 h 67 142 mi Behind the official forecast by 73% 14 mph Behind the official forecast by 16%
4 HAFS-B 120 h 61 210 mi Behind the official forecast by 110% 17 mph Behind the official forecast by 21%
4 HWRF 12 h 74 36 mi Behind the official forecast by 8% 12 mph Behind the official forecast by 115%
4 HWRF 24 h 72 53 mi Behind the official forecast by 25% 13 mph Behind the official forecast by 35%
4 HWRF 36 h 70 67 mi Behind the official forecast by 28% 13 mph Behind the official forecast by 14%
4 HWRF 48 h 68 77 mi Behind the official forecast by 34% 14 mph Behind the official forecast by 25%
4 HWRF 60 h 66 88 mi Behind the official forecast by 44% 15 mph Behind the official forecast by 54%
4 HWRF 72 h 64 106 mi Behind the official forecast by 58% 15 mph Behind the official forecast by 38%
4 HWRF 96 h 60 147 mi Behind the official forecast by 43% 14 mph Behind the official forecast by 9%
4 HWRF 120 h 56 201 mi Behind the official forecast by 47% 19 mph Behind the official forecast by 8%
7 GFS 12 h 83 35 mi Behind the official forecast by 18% 15 mph Behind the official forecast by 219%
7 GFS 24 h 81 48 mi Behind the official forecast by 20% 16 mph Behind the official forecast by 101%
7 GFS 36 h 79 56 mi Behind the official forecast by 12% 17 mph Behind the official forecast by 76%
7 GFS 48 h 77 77 mi Behind the official forecast by 18% 18 mph Behind the official forecast by 83%
7 GFS 60 h 75 94 mi Behind the official forecast by 29% 18 mph Behind the official forecast by 97%
7 GFS 72 h 73 111 mi Behind the official forecast by 33% 17 mph Behind the official forecast by 74%
7 GFS 96 h 69 154 mi Behind the official forecast by 46% 17 mph Behind the official forecast by 43%
7 GFS 120 h 65 196 mi Behind the official forecast by 62% 22 mph Behind the official forecast by 23%
8 GEFS mean 12 h 83 32 mi Behind the official forecast by 14% 19 mph Behind the official forecast by 328%
8 GEFS mean 24 h 81 44 mi Behind the official forecast by 13% 20 mph Behind the official forecast by 165%
8 GEFS mean 36 h 79 56 mi Behind the official forecast by 14% 21 mph Behind the official forecast by 124%
8 GEFS mean 48 h 77 70 mi Behind the official forecast by 19% 21 mph Behind the official forecast by 130%
8 GEFS mean 60 h 75 82 mi Behind the official forecast by 27% 21 mph Behind the official forecast by 159%
8 GEFS mean 72 h 73 94 mi Behind the official forecast by 32% 22 mph Behind the official forecast by 151%
8 GEFS mean 96 h 69 121 mi Behind the official forecast by 30% 23 mph Behind the official forecast by 130%
8 GEFS mean 120 h 62 152 mi Behind the official forecast by 46% 26 mph Behind the official forecast by 71%
9 HMON 12 h 75 38 mi Behind the official forecast by 50% 8 mph Behind the official forecast by 35%
9 HMON 24 h 73 51 mi Behind the official forecast by 41% 11 mph Behind the official forecast by 13%
9 HMON 36 h 71 71 mi Behind the official forecast by 58% 12 mph Behind the official forecast by 6%
9 HMON 48 h 69 94 mi Behind the official forecast by 71% 14 mph Behind the official forecast by 27%
9 HMON 60 h 67 118 mi Behind the official forecast by 99% 16 mph Behind the official forecast by 62%
9 HMON 72 h 63 145 mi Behind the official forecast by 126% 18 mph Behind the official forecast by 75%
9 HMON 96 h 59 175 mi Behind the official forecast by 97% 19 mph Behind the official forecast by 57%
9 HMON 120 h 54 234 mi Behind the official forecast by 134% 23 mph Behind the official forecast by 26%
10 UKMET 12 h 40 33 mi Behind the official forecast by 4% 21 mph Behind the official forecast by 454%
10 UKMET 24 h 39 43 mi Beats the official forecast by 8% 22 mph Behind the official forecast by 236%
10 UKMET 36 h 38 49 mi Beats the official forecast by 9% 23 mph Behind the official forecast by 167%
10 UKMET 48 h 37 56 mi Beats the official forecast by 4% 24 mph Behind the official forecast by 168%
10 UKMET 60 h 36 76 mi Behind the official forecast by 25% 25 mph Behind the official forecast by 213%
10 UKMET 72 h 35 102 mi Behind the official forecast by 65% 24 mph Behind the official forecast by 208%
10 UKMET 96 h 33 157 mi Behind the official forecast by 118% 23 mph Behind the official forecast by 225%
10 UKMET 120 h 31 205 mi Behind the official forecast by 147% 24 mph Behind the official forecast by 81%
11 NAVGEM 12 h 62 56 mi Behind the official forecast by 127% 32 mph Behind the official forecast by 461%
11 NAVGEM 24 h 60 80 mi Behind the official forecast by 131% 31 mph Behind the official forecast by 216%
11 NAVGEM 36 h 58 111 mi Behind the official forecast by 140% 30 mph Behind the official forecast by 155%
11 NAVGEM 48 h 56 136 mi Behind the official forecast by 145% 27 mph Behind the official forecast by 143%
11 NAVGEM 60 h 54 158 mi Behind the official forecast by 157% 25 mph Behind the official forecast by 149%
11 NAVGEM 72 h 52 177 mi Behind the official forecast by 163% 22 mph Behind the official forecast by 123%
11 NAVGEM 96 h 48 226 mi Behind the official forecast by 143% 16 mph Behind the official forecast by 38%
11 NAVGEM 120 h 44 297 mi Behind the official forecast by 79% 18 mph Behind the official forecast by 18%
12 Canadian GEM 12 h 42 31 mi Behind the official forecast by 16% 22 mph Behind the official forecast by 500%
12 Canadian GEM 24 h 41 44 mi Behind the official forecast by 17% 24 mph Behind the official forecast by 250%
12 Canadian GEM 36 h 40 57 mi Behind the official forecast by 31% 25 mph Behind the official forecast by 194%
12 Canadian GEM 48 h 39 70 mi Behind the official forecast by 48% 26 mph Behind the official forecast by 198%
12 Canadian GEM 60 h 38 86 mi Behind the official forecast by 74% 26 mph Behind the official forecast by 228%
12 Canadian GEM 72 h 37 115 mi Behind the official forecast by 126% 27 mph Behind the official forecast by 251%
12 Canadian GEM 96 h 35 164 mi Behind the official forecast by 144% 28 mph Behind the official forecast by 249%
12 Canadian GEM 120 h 33 204 mi Behind the official forecast by 132% 28 mph Behind the official forecast by 123%

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 21°N 36°N 51°N 134°E 177°E 139°W 96°W
Map of Hurricane Nolo. The best track, where the storm actually went, has 98 positions. 4 official forecast tracks are drawn. Model lines: GFS, GEFS mean, 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 (98 positions)
  • NHC official Sep 13, 18:00 UTC
  • NHC official Sep 25, 18:00 UTC
  • NHC official Sep 30, 06:00 UTC
  • NHC official Oct 4, 18:00 UTC
  • GFS
  • GEFS mean
  • 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 32 mi 24 h 41 mi 36 h 49 mi 48 h 54 mi 60 h 60 mi 72 h 80 mi 96 h 114 mi 120 h
Average official track miss in miles by how far ahead. 12 hours 21 miles over 55 forecasts. 24 hours 32 miles over 52 forecasts. 36 hours 41 miles over 49 forecasts. 48 hours 49 miles over 47 forecasts. 60 hours 54 miles over 45 forecasts. 72 hours 60 miles over 43 forecasts. 96 hours 80 miles over 38 forecasts. 120 hours 114 miles over 27 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 55 21 mi 6 mph 83 mph 81 mph
24 h 52 32 mi 11 mph 86 mph 83 mph
36 h 49 41 mi 14 mph 89 mph 85 mph
48 h 47 49 mi 13 mph 88 mph 86 mph
60 h 45 54 mi 12 mph 88 mph 86 mph
72 h 43 60 mi 12 mph 88 mph 85 mph
96 h 38 80 mi 13 mph 83 mph 85 mph
120 h 27 114 mi 20 mph 89 mph 96 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 48 h 60 h 72 h 96 h 120 h
Top wind, official forecast versus where the storm went. At 12 hours the forecast averaged 83 mph and where the storm actually went averaged 81 mph. At 24 hours the forecast averaged 86 mph and where the storm actually went averaged 83 mph. At 36 hours the forecast averaged 89 mph and where the storm actually went averaged 85 mph. At 48 hours the forecast averaged 88 mph and where the storm actually went averaged 86 mph. At 60 hours the forecast averaged 88 mph and where the storm actually went averaged 86 mph. At 72 hours the forecast averaged 88 mph and where the storm actually went averaged 85 mph. At 96 hours the forecast averaged 83 mph and where the storm actually went averaged 85 mph. At 120 hours the forecast averaged 89 mph and where the storm actually went averaged 96 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.