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 Disturbance Rachel Model Accuracy: DeepMind vs GFS vs WeatherNext 3

Final advisory

NHC issued its final advisory at 8:00 AM ET Sun, Oct 11.

Tropical Disturbance Rachel has 67 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 30 miles across 50 forecasts. At 48 hours, the official wind forecast averaged 81 mph and where the storm actually went averaged 80 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.

EP182026 · 2026 · Sep 25–Oct 11, 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 Google DeepMind 2 2 2
1 NHC official 2 3 1
3 GFS 3.5 4 3
3 WeatherNext 3 3.5 1 6
5 HAFS-A 5.5 6 5
6 GEFS mean 7 5 9
6 HWRF 7 7 7
8 NAVGEM 8 12 4
9 HAFS-B 8.5 9 8
10 HMON 9 8 10
11 UKMET 10.5 10 11
12 Canadian GEM 11.5 11 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 Google DeepMind 12 h 56 15 mi Beats the official forecast by 25% 8 mph Behind the official forecast by 37%
1 Google DeepMind 24 h 54 17 mi Beats the official forecast by 24% 9 mph Behind the official forecast by 32%
1 Google DeepMind 36 h 51 19 mi Beats the official forecast by 26% 11 mph Behind the official forecast by 43%
1 Google DeepMind 48 h 50 24 mi Beats the official forecast by 21% 12 mph Behind the official forecast by 37%
1 Google DeepMind 60 h 48 32 mi Beats the official forecast by 16% 13 mph Behind the official forecast by 52%
1 Google DeepMind 72 h 46 46 mi Beats the official forecast by 12% 12 mph Behind the official forecast by 51%
1 Google DeepMind 96 h 42 84 mi Beats the official forecast by 11% 14 mph Behind the official forecast by 61%
1 Google DeepMind 120 h 38 140 mi Beats the official forecast by 5% 14 mph Behind the official forecast by 69%
1 NHC official 12 h 56 19 mi — 6 mph —
1 NHC official 24 h 54 22 mi — 7 mph —
1 NHC official 36 h 52 26 mi — 8 mph —
1 NHC official 48 h 50 30 mi — 9 mph —
1 NHC official 60 h 48 39 mi — 8 mph —
1 NHC official 72 h 46 52 mi — 8 mph —
1 NHC official 96 h 42 94 mi — 9 mph —
1 NHC official 120 h 38 148 mi — 8 mph —
3 WeatherNext 3 12 h 55 13 mi Beats the official forecast by 32% 10 mph Behind the official forecast by 73%
3 WeatherNext 3 24 h 53 17 mi Beats the official forecast by 20% 13 mph Behind the official forecast by 97%
3 WeatherNext 3 36 h 51 19 mi Beats the official forecast by 27% 16 mph Behind the official forecast by 103%
3 WeatherNext 3 48 h 49 22 mi Beats the official forecast by 25% 17 mph Behind the official forecast by 101%
3 WeatherNext 3 60 h 47 26 mi Beats the official forecast by 29% 18 mph Behind the official forecast by 124%
3 WeatherNext 3 72 h 45 35 mi Beats the official forecast by 32% 18 mph Behind the official forecast by 129%
3 WeatherNext 3 96 h 41 70 mi Beats the official forecast by 24% 18 mph Behind the official forecast by 113%
3 WeatherNext 3 120 h 38 126 mi Beats the official forecast by 15% 17 mph Behind the official forecast by 107%
3 GFS 12 h 60 32 mi Behind the official forecast by 31% 12 mph Behind the official forecast by 105%
3 GFS 24 h 58 38 mi Behind the official forecast by 48% 13 mph Behind the official forecast by 101%
3 GFS 36 h 56 42 mi Behind the official forecast by 47% 14 mph Behind the official forecast by 78%
3 GFS 48 h 54 49 mi Behind the official forecast by 43% 13 mph Behind the official forecast by 50%
3 GFS 60 h 52 62 mi Behind the official forecast by 44% 12 mph Behind the official forecast by 47%
3 GFS 72 h 50 73 mi Behind the official forecast by 28% 11 mph Behind the official forecast by 39%
3 GFS 96 h 46 109 mi Behind the official forecast by 5% 13 mph Behind the official forecast by 48%
3 GFS 120 h 42 160 mi Behind the official forecast by 2% 13 mph Behind the official forecast by 71%
5 HAFS-A 12 h 60 26 mi Behind the official forecast by 22% 16 mph Behind the official forecast by 169%
5 HAFS-A 24 h 58 31 mi Behind the official forecast by 30% 17 mph Behind the official forecast by 156%
5 HAFS-A 36 h 56 41 mi Behind the official forecast by 50% 15 mph Behind the official forecast by 99%
5 HAFS-A 48 h 54 53 mi Behind the official forecast by 72% 13 mph Behind the official forecast by 48%
5 HAFS-A 60 h 52 68 mi Behind the official forecast by 78% 13 mph Behind the official forecast by 69%
5 HAFS-A 72 h 50 87 mi Behind the official forecast by 72% 14 mph Behind the official forecast by 71%
5 HAFS-A 96 h 46 148 mi Behind the official forecast by 62% 17 mph Behind the official forecast by 106%
5 HAFS-A 120 h 42 210 mi Behind the official forecast by 48% 18 mph Behind the official forecast by 100%
6 HWRF 12 h 59 32 mi Behind the official forecast by 50% 15 mph Behind the official forecast by 150%
6 HWRF 24 h 57 39 mi Behind the official forecast by 69% 18 mph Behind the official forecast by 172%
6 HWRF 36 h 55 44 mi Behind the official forecast by 58% 20 mph Behind the official forecast by 160%
6 HWRF 48 h 53 51 mi Behind the official forecast by 61% 20 mph Behind the official forecast by 118%
6 HWRF 60 h 51 59 mi Behind the official forecast by 53% 19 mph Behind the official forecast by 128%
6 HWRF 72 h 49 72 mi Behind the official forecast by 41% 17 mph Behind the official forecast by 115%
6 HWRF 96 h 45 136 mi Behind the official forecast by 46% 19 mph Behind the official forecast by 133%
6 HWRF 120 h 41 227 mi Behind the official forecast by 60% 20 mph Behind the official forecast by 125%
6 GEFS mean 12 h 60 29 mi Behind the official forecast by 25% 18 mph Behind the official forecast by 206%
6 GEFS mean 24 h 58 36 mi Behind the official forecast by 45% 19 mph Behind the official forecast by 194%
6 GEFS mean 36 h 56 44 mi Behind the official forecast by 57% 20 mph Behind the official forecast by 175%
6 GEFS mean 48 h 54 51 mi Behind the official forecast by 54% 21 mph Behind the official forecast by 149%
6 GEFS mean 60 h 52 61 mi Behind the official forecast by 43% 22 mph Behind the official forecast by 175%
6 GEFS mean 72 h 50 73 mi Behind the official forecast by 28% 22 mph Behind the official forecast by 186%
6 GEFS mean 96 h 46 111 mi Behind the official forecast by 6% 23 mph Behind the official forecast by 169%
6 GEFS mean 120 h 42 170 mi Behind the official forecast by 8% 23 mph Behind the official forecast by 184%
8 NAVGEM 12 h 58 45 mi Behind the official forecast by 120% 21 mph Behind the official forecast by 252%
8 NAVGEM 24 h 56 56 mi Behind the official forecast by 141% 16 mph Behind the official forecast by 143%
8 NAVGEM 36 h 55 83 mi Behind the official forecast by 190% 12 mph Behind the official forecast by 65%
8 NAVGEM 48 h 54 110 mi Behind the official forecast by 242% 10 mph Behind the official forecast by 19%
8 NAVGEM 60 h 52 129 mi Behind the official forecast by 219% 11 mph Behind the official forecast by 33%
8 NAVGEM 72 h 50 141 mi Behind the official forecast by 159% 12 mph Behind the official forecast by 63%
8 NAVGEM 96 h 46 165 mi Behind the official forecast by 68% 13 mph Behind the official forecast by 53%
8 NAVGEM 120 h 42 207 mi Behind the official forecast by 41% 12 mph Behind the official forecast by 31%
9 HAFS-B 12 h 59 27 mi Behind the official forecast by 29% 19 mph Behind the official forecast by 214%
9 HAFS-B 24 h 57 30 mi Behind the official forecast by 27% 17 mph Behind the official forecast by 153%
9 HAFS-B 36 h 55 43 mi Behind the official forecast by 54% 19 mph Behind the official forecast by 147%
9 HAFS-B 48 h 53 56 mi Behind the official forecast by 85% 17 mph Behind the official forecast by 98%
9 HAFS-B 60 h 51 74 mi Behind the official forecast by 94% 18 mph Behind the official forecast by 128%
9 HAFS-B 72 h 49 97 mi Behind the official forecast by 92% 21 mph Behind the official forecast by 168%
9 HAFS-B 96 h 45 159 mi Behind the official forecast by 73% 24 mph Behind the official forecast by 184%
9 HAFS-B 120 h 41 240 mi Behind the official forecast by 68% 27 mph Behind the official forecast by 201%
10 HMON 12 h 59 30 mi Behind the official forecast by 44% 16 mph Behind the official forecast by 174%
10 HMON 24 h 57 39 mi Behind the official forecast by 65% 21 mph Behind the official forecast by 221%
10 HMON 36 h 55 48 mi Behind the official forecast by 79% 23 mph Behind the official forecast by 208%
10 HMON 48 h 53 55 mi Behind the official forecast by 84% 23 mph Behind the official forecast by 174%
10 HMON 60 h 51 79 mi Behind the official forecast by 105% 25 mph Behind the official forecast by 211%
10 HMON 72 h 49 98 mi Behind the official forecast by 92% 26 mph Behind the official forecast by 239%
10 HMON 96 h 45 140 mi Behind the official forecast by 54% 30 mph Behind the official forecast by 248%
10 HMON 120 h 41 206 mi Behind the official forecast by 47% 31 mph Behind the official forecast by 251%
11 UKMET 12 h 30 31 mi Behind the official forecast by 20% 23 mph Behind the official forecast by 316%
11 UKMET 24 h 29 39 mi Behind the official forecast by 34% 24 mph Behind the official forecast by 289%
11 UKMET 36 h 28 47 mi Behind the official forecast by 65% 27 mph Behind the official forecast by 282%
11 UKMET 48 h 27 55 mi Behind the official forecast by 77% 28 mph Behind the official forecast by 197%
11 UKMET 60 h 26 69 mi Behind the official forecast by 83% 28 mph Behind the official forecast by 236%
11 UKMET 72 h 25 97 mi Behind the official forecast by 97% 30 mph Behind the official forecast by 275%
11 UKMET 96 h 23 151 mi Behind the official forecast by 56% 33 mph Behind the official forecast by 269%
11 UKMET 120 h 21 257 mi Behind the official forecast by 71% 34 mph Behind the official forecast by 263%
12 Canadian GEM 12 h 31 32 mi Behind the official forecast by 21% 24 mph Behind the official forecast by 334%
12 Canadian GEM 24 h 30 41 mi Behind the official forecast by 26% 26 mph Behind the official forecast by 341%
12 Canadian GEM 36 h 29 50 mi Behind the official forecast by 61% 28 mph Behind the official forecast by 307%
12 Canadian GEM 48 h 28 70 mi Behind the official forecast by 83% 31 mph Behind the official forecast by 253%
12 Canadian GEM 60 h 27 93 mi Behind the official forecast by 108% 31 mph Behind the official forecast by 278%
12 Canadian GEM 72 h 26 112 mi Behind the official forecast by 94% 33 mph Behind the official forecast by 360%
12 Canadian GEM 96 h 24 186 mi Behind the official forecast by 78% 35 mph Behind the official forecast by 293%
12 Canadian GEM 120 h 22 276 mi Behind the official forecast by 83% 37 mph Behind the official forecast by 307%

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.

5°N 20°N 35°N 50°N 140°W 122°W 105°W 88°W
Map of Tropical Disturbance Rachel. The best track, where the storm actually went, has 67 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 (67 positions)
  • NHC official Sep 27, 06:00 UTC
  • NHC official Oct 1, 12:00 UTC
  • NHC official Oct 5, 12:00 UTC
  • NHC official Oct 9, 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

19 mi 12 h 22 mi 24 h 26 mi 36 h 30 mi 48 h 39 mi 60 h 52 mi 72 h 94 mi 96 h 148 mi 120 h
Average official track miss in miles by how far ahead. 12 hours 19 miles over 56 forecasts. 24 hours 22 miles over 54 forecasts. 36 hours 26 miles over 52 forecasts. 48 hours 30 miles over 50 forecasts. 60 hours 39 miles over 48 forecasts. 72 hours 52 miles over 46 forecasts. 96 hours 94 miles over 42 forecasts. 120 hours 148 miles over 38 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 56 19 mi 6 mph 78 mph 77 mph
24 h 54 22 mi 7 mph 79 mph 78 mph
36 h 52 26 mi 8 mph 81 mph 79 mph
48 h 50 30 mi 9 mph 81 mph 80 mph
60 h 48 39 mi 8 mph 81 mph 81 mph
72 h 46 52 mi 8 mph 79 mph 82 mph
96 h 42 94 mi 9 mph 77 mph 82 mph
120 h 38 148 mi 8 mph 75 mph 79 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 78 mph and where the storm actually went averaged 77 mph. At 24 hours the forecast averaged 79 mph and where the storm actually went averaged 78 mph. At 36 hours the forecast averaged 81 mph and where the storm actually went averaged 79 mph. At 48 hours the forecast averaged 81 mph and where the storm actually went averaged 80 mph. At 60 hours the forecast averaged 81 mph and where the storm actually went averaged 81 mph. At 72 hours the forecast averaged 79 mph and where the storm actually went averaged 82 mph. At 96 hours the forecast averaged 77 mph and where the storm actually went averaged 82 mph. At 120 hours the forecast averaged 75 mph and where the storm actually went averaged 79 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.