Tennis Predictions
Model win probabilities for ATP & WTA matches, with a confidence rating per pick and a public accuracy record over every settled match.
67Upcoming
71.9%Accuracy
4698Settled
Braunschweig, Germany
clay
✓ Correct
High · 81%
vs
2–0
Braunschweig, Germany
clay
✗ Missed
High · 72%
vs
2–0
Contrexeville, France
clay
✓ Correct
High · 69%
vs
0–2
Trieste, Italy
clay
✓ Correct
High · 65%
vs
0–2
Iasi, Romania
clay
✓ Correct
High · 71%
vs
2–0
Braunschweig, Germany
clay
✓ Correct
High · 84%
vs
2–0
Trieste, Italy
clay
✓ Correct
High · 76%
vs
2–0
Braunschweig, Germany
clay
✗ Missed
High · 74%
vs
2–0
Milano, Italy
clay
✗ Missed
High · 88%
vs
2–1
Brasov, Romania
clay
✗ Missed
High · 70%
vs
0–2
Trieste, Italy
clay
✓ Correct
High · 65%
vs
0–2
ATP Challenger Liege, Belgium Men Singles
clay
✓ Correct
High · 67%
vs
2–0
Contrexeville, France
clay
✓ Correct
High · 87%
vs
2–1
Contrexeville, France
clay
✗ Missed
High · 70%
vs
0–2
Braunschweig, Germany
clay
✓ Correct
High · 75%
vs
0–2
Trieste, Italy
clay
✓ Correct
High · 70%
vs
2–1
Wimbledon, Men
grass
✗ Missed
High · 66%
vs
3–2
Quito, Ecuador Men Singles
clay
✓ Correct
High · 81%
vs
1–2
Wimbledon, Men
grass
✓ Correct
High · 75%
vs
3–1
Wimbledon, Women
grass
✓ Correct
High · 82%
vs
1–2
Wimbledon, Men
grass
✗ Missed
High · 80%
vs
0–3
Troyes, France
clay
✓ Correct
High · 75%
vs
0–2
Wimbledon, Women
grass
✗ Missed
High · 78%
vs
2–0
Troyes, France
clay
✗ Missed
High · 75%
vs
0–2
Wimbledon, Women
grass
✗ Missed
High · 77%
vs
0–2
Milano, Italy
clay
✓ Correct
High · 78%
vs
1–2
Brasov, Romania
clay
✓ Correct
High · 84%
vs
1–2
Wimbledon, Women
grass
✓ Correct
High · 78%
vs
1–2
Wimbledon, Men
grass
✓ Correct
High · 67%
vs
3–1
Milano, Italy
clay
✗ Missed
High · 77%
vs
0–2
⚡ This page, via API Pro
Everything on this page is available as JSON via the Tennis API (Sports Addon, $5/mo):
GET
/tennis/api/v2/predictions/?upcoming=true
How to read this: the bar shows our model's win probability for each player; the confidence pill rates how much signal the model had for this match-up. Accuracy is measured over every settled prediction — not a curated subset. Not betting advice; no outcome is guaranteed.