Our 8am predictions landed within 10 minutes 86% of the time

Most wait-time apps ask you to trust them. We publish the scoreboard instead — recomputed from our own archive on a timer, bad days included.

3,404predictions scored
5 minmedian error
86%within 10 minutes
+5 minmedian bias (we run high)

By hour of day

How often the prediction for a ride landed within 5, 10 and 15 minutes of the posted wait, by park-local hour. Hours with under 30 scored predictions are withheld rather than shown from noise.

Hour≤5 min≤10 min≤15 minMedian errorn
8am73% 86% 94%5 min49
9am64% 78% 86%5 min138
10am59% 76% 85%5 min250
11am66% 77% 84%5 min309
12pm66% 81% 89%5 min271
1pm81% 90% 94%5 min93
2pm80% 89% 96%5 min93
3pm70% 87% 94%5 min94
4pm72% 86% 93%5 min92
5pm79% 86% 89%5 min209
6pm78% 90% 94%5 min204
7pm82% 87% 92%5 min218
8pm82% 84% 89%5 min418
9pm84% 89% 90%5 min401
10pm88% 92% 93%5 min318
11pm96% 98% 98%5 min231

By park

Park≤10 minMedian errorn
Tokyo Disneyland 91% 5 min316
Hong Kong Disneyland 84% 5 min301
Tokyo DisneySea 77% 5 min295
Disneyland 72% 5 min247
Michigan's Adventure 100% 5 min188
Valleyfair 100% 5 min185
Worlds of Fun 100% 5 min180
Canada's Wonderland 73% 5 min155
Efteling 93% 5 min140
Disneyland Park 85% 5 min136
California Adventure 89% 5 min123
Phantasialand 78% 0 min111
Six Flags St. Louis 100% 5 min85
Magic Kingdom 94% 0 min84
Walt Disney Studios 52% 10 min82

Window: 2026-08-26 to 2026-08-26 · recomputed every few hours · generated 2026-08-26

How this is measured — and how it can't be gamed

Walk-forward, no exceptions. Each day is scored using only baselines and day-of-week factors built from the days before it — the numbers the model would genuinely have shown you. A prediction never sees its own day.

One prediction per ride per hour per day. The hour's "actual" is the median of that hour's recorded snapshots. We do not score every polling tick, because that would let the sampling rate inflate the sample size.

Scored against posted waits. The model predicts the wait the park will post, so that is what it is scored against. Visitor-reported actual waits are a separate dataset with its own page per ride.

Only predictions the model was ready to make. A ride is scored once it has enough prior snapshots to carry a baseline — the same bar the product itself uses before showing a typical wait.

Everything counts. The page recomputes from the complete archive on a timer. There is no mechanism for leaving a bad day out.