How accurate are our probabilities?

Our whole approach rests on one thing: when we say a horse has a 30% chance, it should win about 30% of the time. Here's the proof — measured against real results, published openly.

Probabilities highly accurate
±0.9pp
average gap between predicted and actual

Across 12,215 runners the model has assessed, its predicted win probabilities land within 0.9 percentage points of what actually happened, on average.

In plain terms: when we say 30%, horses win close to 30%. That's what makes the value calculations on the race page trustworthy — the probabilities are real.

Predicted chance vs actual win rate

Every horse the model assigns a probability to, grouped by predicted chance, compared to how often those horses actually won. The closer "Actual" is to "Predicted", the more trustworthy the number.

Predicted Chance Predicted Avg Actual Win Rate Difference Runners Accuracy
0–5% 3.0% 4.1% +1.1pp 2518
5–10% 7.4% 7.8% +0.4pp 4049
10–15% 12.3% 12.6% +0.3pp 2626
15–20% 17.2% 17.2% 0.0pp 1411
20–25% 22.3% 20.1% -2.2pp 666
25–30% 27.2% 28.2% +1.0pp 319
30–35% 32.5% 37.8% +5.3pp 201
35%+ 42.3% 36.7% -5.6pp 425

pp = percentage points. Green = within 3pp · Amber = within 7pp · Red = needs attention. Based on 12,215 runners across 46 racing days.

Accuracy by race type

Whether the probabilities hold up across different kinds of race. Predicted is the model's average chance; actual is how often those horses won.

Flat Handicap
Predicted11.5%
Actual11.4%
Difference -0.1pp
6311 runners · see the races →
Novice / Maiden
Predicted12.2%
Actual12.4%
Difference +0.2pp
2625 runners · see the races →
Jump Handicap
Predicted11.1%
Actual12.9%
Difference +1.8pp
1361 runners · see the races →
Other
Predicted11.6%
Actual12.1%
Difference +0.5pp
1057 runners · see the races →
Nan
Predicted9.4%
Actual10.2%
Difference +0.8pp
352 runners · see the races →
Group
Predicted14.4%
Actual13.0%
Difference -1.5pp
301 runners · see the races →
Listed
Predicted13.2%
Actual12.5%
Difference -0.7pp
208 runners · see the races →

Why we show you this

Most racing products show you their winners. We show you how accurate our numbers are — including where they're not perfect.

A well-calibrated probability is the foundation of finding value. If the model says a horse has a 25% chance and the market is offering odds that imply 15%, that gap is only meaningful if the 25% is real. This page is our evidence that it is — updated continuously from settled results.

If the numbers ever drift, you'll see it here first. That's the deal.