Win probability
Tuesday, 1 September 2026
20 matches selected · 2 tournaments · model last ran 21:50 UTC
Umpiry rates 20 matches on Tuesday, 1 September 2026. The closest is Darja Vidmanova v Jessica Bouzas Maneiro at 52 % — the model’s most uncertain call of the day. The most one-sided is Aryna Sabalenka v Maria Camila Osorio Serrano at 94 %. Probabilities come from a per-tour model trained on Elo, surface Elo, recent serve and return form and layoff.
| Time | Tournament | Round | Match | Probability | Verdict | H2H |
|---|---|---|---|---|---|---|
| 23:50 | US Open WTA · hard | R128 |  Vidmanova D. Bouzas Maneiro J. | 52 %48 % | Toss-up | 0–1 |
| 19:30 | US Open WTA · hard | R128 |  Sakkari M. Montgomery R. | 52 %48 % | Toss-up | 1–0 |
| 23:20 | US Open WTA · hard | R128 | Badosa P. Kasatkina D. | 53 %47 % | Toss-up | 4–4 |
| 18:00 | US Open WTA · hard | R128 |  Potapova A.Valentova T. | 55 %45 % | Toss-up | — |
| 20:30 | US Open ATP · hard | R128 |  Lennard Struff J. Ugo Carabelli C. | 63 %37 % | Slight edge | 1–0 |
| 18:30 | US Open WTA · hard | R128 | Keys M.Korneeva A. | 64 %36 % | Slight edge | 1–0 |
| 21:00 | US Open ATP · hard | R128 | Jodar R.Kokkinakis T. | 68 %32 % | Clear favourite | — |
| 03:30 | US Open ATP · hard | R128 | Tiafoe F.Damm M. | 69 %31 % | Clear favourite | 2–0 |
| 23:00 | US Open ATP · hard | R128 | Tien L. Borges N. | 72 %28 % | Clear favourite | 3–0 |
| 23:20 | US Open ATP · hard | R128 |  Musetti L. Fery A. | 72 %28 % | Clear favourite | 1–0 |
| 18:00 | US Open ATP · hard | R128 | Cobolli F.Comesana F. | 73 %27 % | Clear favourite | 2–0 |
| 02:00 | US Open ATP · hard | R128 | Shelton B. Griekspoor T. | 75 %25 % | Clear favourite | 1–0 |
| 21:00 | US Open ATP · hard | R128 |  Shang J.Trungelliti M. | 76 %24 % | Clear favourite | 0–1 |
| 18:00 | US Open ATP · hard | R128 |  Ruud C.Cerundolo J. | 80 %20 % | Clear favourite | 1–2 |
| 02:00 | US Open WTA · hard | R128 |  Swiatek I.Wang X. | 84 %16 % | Strong favourite | 3–0 |
| 23:00 | US Open ATP · hard | R128 |  Auger Aliassime F.Hijikata R. | 85 %15 % | Strong favourite | 1–0 |
| 20:00 | US Open ATP · hard | R128 | Fritz T.Blanch D. | 88 %12 % | Strong favourite | 1–0 |
| 20:30 | US Open WTA · hard | R128 | Andreeva M. Tjen J. | 90 %10 % | Strong favourite | 2–0 |
| 19:30 | US Open WTA · hard | R128 |  Rybakina E.Frodin T. | 94 %6 % | Strong favourite | 1–0 |
| 18:30 | US Open WTA · hard | R128 |  Sabalenka A. Camila Osorio Serrano M. | 94 %6 % | Strong favourite | 2–0 |
| Time | Tournament | Round | Match | Probability | Verdict | H2H |
|---|---|---|---|---|---|---|
| 18:30 | US Open WTA · hard | R128 | Sabalenka A.Camila Osorio Serrano M. | 94 %6 % | Strong favourite | 2–0 |
| 19:30 | US Open WTA · hard | R128 | Rybakina E.Frodin T. | 94 %6 % | Strong favourite | 1–0 |
| 20:30 | US Open WTA · hard | R128 | Andreeva M.Tjen J. | 90 %10 % | Strong favourite | 2–0 |
| 20:00 | US Open ATP · hard | R128 | Fritz T.Blanch D. | 88 %12 % | Strong favourite | 1–0 |
| 23:00 | US Open ATP · hard | R128 | Auger Aliassime F.Hijikata R. | 85 %15 % | Strong favourite | 1–0 |
| 02:00 | US Open WTA · hard | R128 | Swiatek I.Wang X. | 84 %16 % | Strong favourite | 3–0 |
| 18:00 | US Open ATP · hard | R128 | Ruud C.Cerundolo J. | 80 %20 % | Clear favourite | 1–2 |
| 21:00 | US Open ATP · hard | R128 | Shang J.Trungelliti M. | 76 %24 % | Clear favourite | 0–1 |
| 02:00 | US Open ATP · hard | R128 | Shelton B.Griekspoor T. | 75 %25 % | Clear favourite | 1–0 |
| 18:00 | US Open ATP · hard | R128 | Cobolli F.Comesana F. | 73 %27 % | Clear favourite | 2–0 |
| 23:20 | US Open ATP · hard | R128 | Musetti L.Fery A. | 72 %28 % | Clear favourite | 1–0 |
| 23:00 | US Open ATP · hard | R128 | Tien L.Borges N. | 72 %28 % | Clear favourite | 3–0 |
How to read this
Each row gives the model’s probability that the favourite wins, and the verdict says the same thing in words. Rows are ordered by how close the model thinks the match is, so the top of the table is where it is least sure. A 70 % favourite losing is not a broken model — it is the 30 %. Probabilities are not odds and take no account of any market.
How often the model has been right
| Tour | Correct |
|---|---|
| ATP / WTA | 66 % |
| Challenger (men) | 64 % |
| Challenger (women) | 68 % |
| ITF (men) | 66 % |
| ITF (women) | 64 % |
Measured on the predictions the model actually made, not on a backtest — see Methodology.
Yesterday
Monday, 31 August 2026 · 20 matches
Favourites won
14 / 20
Model expected
13.3
The model expected 13.3 favourites to win; 14 did. See yesterday’s page.
Biggest shock, last 7 days
Questions
- How is the probability calculated?
- A separate model for each tour, trained on Elo, surface-specific Elo, recent serve and return form and time since the player’s last match. It runs several times a day; the time of the last run is at the top of this page.
- How often is the model right?
- We publish it. The table above gives the hit rate for each tour family, measured on the predictions the model actually made — see Methodology for how it is computed.
- Why are the closest matches at the top?
- Rows are ordered by distance from 50 %, so the table opens where the model is least sure. “Most one-sided” reverses the order and groups the rows by tournament.
- Is this a betting tip?
- No. The page shows a model’s probability and how often that model has been right. There are no odds, no comparison with a market and no suggested stake.