Skip to main content

Track record

Accuracy

How the forecasts have actually scored against real results — measured across every scored class-round, with nothing left out. Endurance grids are large, so a car landing within a few places of its prediction is a strong result.

Evidence

23 Aug 2026, 19:05 UTC

Over 8 paired rounds, the model no difference demonstrated (last race order).

BaselineRaceRoundsModelBaselineGainVerdict
Last race orderGTD84.934.99+0.07no difference demonstrated
Last race orderGTDPRO83.383.11-0.27no difference demonstrated
Last race orderGTP72.862.99+0.13no difference demonstrated
Last race orderLMP252.792.87+0.09no difference demonstrated
Season form orderGTD84.935.06+0.14no difference demonstrated
Season form orderGTDPRO83.383.58+0.20no difference demonstrated
Season form orderGTP72.862.55-0.31does NOT beat the baseline
Season form orderLMP252.792.79+0.01no difference demonstrated

Paired bootstrap on the round-by-round difference: 0.067, 95% CI [-0.245, 0.336] in positions gained. Positive means the model is closer to the real finishing order than last race order is; the interval covers zero, so no difference has been demonstrated.

forward evaluation — each round was forecast before it ran and scored afterwards; not a backtest. Historical replays and the forward record are computed separately and never merged.

  • The model does not beat last race order, season form order on every measured comparison. That is stated rather than hidden.
  • Some comparisons straddle zero: a difference has not been demonstrated, in either direction.
  • Metrics are only comparable within this series. A position error over this field size means nothing next to another series' number.
Class-rounds scored
28
predictions graded
Mean position error
3.60
places off, on average
Podium hit rate
37%
predicted podium correct
Winner hit rate
14%
predicted winner correct

By class

GTP7R

Mean err.

2.86

Podium

48%

Winner

29%

LMP25R

Mean err.

2.84

Podium

47%

Winner

20%

GTD PRO8R

Mean err.

3.38

Podium

33%

Winner

0%

GTD8R

Mean err.

4.93

Podium

25%

Winner

13%

Round by round

RoundCarsMean errorPodiumExactWithin 3Winner
R1Daytona International Speedway113.641/31/114/11
R2Sebring International Raceway111.643/30/1111/11
R3Long Beach Street Circuit111.822/30/1110/11
R4Weathertech Raceway Laguna Seca112.911/31/117/11
R5Detroit Street Course112.911/34/117/11
R6Watkins Glen International112.182/34/118/11
R8Road America114.910/30/113/11

Does the forecast beat guesswork?

Combined win + podium forecast error across 28 scored class-rounds — lower is better — measured against two naive baselines: simply repeating the last race’s order, and ranking cars by their season points.

Model forecast error0.255lower is better

Last-race form

baseline error 0.252

+0.003Matches it

Season form

baseline error 0.267

0.012Beats it

“Matches it” means the model is statistically no worse than that baseline over the rounds scored so far. On a young season with few rounds, matching a strong season-form baseline while beating last-race form is an honest, expected result.

Calibration

Probabilities are calibrated on 9 real rounds of results, per class. Calibrated on real IMSA results, per class stratum.

Continuous evaluation

Every round is re-scored against simple baselines as results come in, so the track record above updates honestly over the season — no cherry-picking, nothing dropped.