A calibrated win probability for every horse in the field.
Stridometrics models every race and gives every horse a win probability. When we say 30%, it happens about 30% of the time: measured on 69,392 horses in 9,543 races since August 17, 2026, updated November 14, 2026. See the calibration record.
One full race free every day. No account, no card required.
Win or lose, it stays on the board. We publish first and grade in public.
When we say 30%, it happens about 30% of the time.
We publish every prediction and grade it in public. Calibration measures accuracy, not profit. You can still lose money. Here is the full record.
Historical calibration, 2023 to 2025
754,746 horses in 102,163 races from 2023 to 2025, all races the model never trained on, graded against the official results.
102,163 races · 754,746 runners
Live calibration since August 17, 2026
Every horse we have predicted since August 17, 2026, 69,392 so far, graded against the official results. Updated November 14, 2026.
9,543 races · 69,392 runners
On October 5, 2026 we moved to a new generation of our model. Every win probability published from that day on comes from it. The live chart keeps every graded prediction from both generations, so nothing has been removed from the record.
The board's implied win chances add up to more than 100%, because the takeout is built into every price. Ours add up to 100% in every race.
Free race record since July 28: 101 races graded, wins and losses. See every one.
A full free race, every day
Get tomorrow's free race by email
One email a morning: today's full race with win probabilities, and yesterday's graded, win or lose. That's it.
One email a day. We never share your address, and unsubscribing takes one click.
Check your inbox.
Click the confirmation link we just sent and you're in. The link works once and lasts 7 days.
We are signing up founding members before the doors open.
Founding members get the founding rate, locked for life. Nothing is for sale yet. Join the list and you get the founding page 48 to 72 hours before the public, and the free race every morning in the meantime.
Everything on one card
Win probabilities for every horse
Each runner gets a win probability, shown next to the morning line, so you can compare our view with the market's.
Best-bet highlights
We surface the spots the model likes most, with clear context, so you spend less time digging and more time deciding.
Pace dynamics & projected collapses
Dedicated models read how a race is likely to unfold: early speed, pressure, and projected pace collapses that reshape the finish.
Exotic & multi-race strategy ideas
Suggested exotic and multi-race tickets, framed as ideas you can take, leave, or adapt to your own play.
Built on serious modeling
Several models combined into one calibrated probability, cross-validated and judged on held-out races they never trained on.
Every track. Pick the window that fits.
One pass covers every track we model, for a day or for 30 days. No per-track add-ons, no long-term commitment, and nothing renews unless you turn it on.
PricingFrequently asked questions
Can I try it for free?
Yes. Every day we publish one full race free, with a win probability for every horse, and grade it in public the next morning. No account and no card needed. Passes for every race go on sale at launch, and the founders list hears first.
Do you place bets for me?
No. Stridometrics provides analysis, picks, and suggestions as opinions for informational and entertainment purposes. You decide what to do with them and place any wagers yourself, elsewhere.
What does a subscription cover?
A pass covers every track we model for the period you choose: one racing day with the Day Pass, or 30 days with the 30-Day Pass. No per-track add-ons. See the pricing page for details.
Can I cancel anytime?
Yes. Passes simply expire at the end of their period; there is no long-term commitment.
Are the statistics real?
Yes. The historical numbers come from races the model never trained on, from 2023 to 2025. Everything we have predicted since August 17, 2026 is graded in public on the calibration page and in the public record. Calibration measures accuracy, not profit. You can still lose money. Past performance does not guarantee future results.