Tennis Predictions
Model win probabilities for ATP & WTA matches, with a confidence rating per pick and a public accuracy record over every settled match.
263Upcoming
65.0%Accuracy
13125Settled
Hangzhou
hard
✗ Missed
Low · 53%
vs
2–1
Singapore
hard
✓ Correct
Medium · 64%
vs
2–0
Seoul
hard
✓ Correct
High · 69%
vs
1–2
Hangzhou
hard
✗ Missed
Medium · 56%
vs
0–2
Hangzhou
hard
✓ Correct
High · 67%
vs
0–2
Billie Jean King Cup
hard
✗ Missed
High · 90%
vs
1–2
Seoul
hard
✓ Correct
Medium · 63%
vs
0–2
Seoul
hard
✓ Correct
Low · 54%
vs
2–1
Billie Jean King Cup
hard
✓ Correct
High · 82%
vs
2–1
Billie Jean King Cup
hard
✓ Correct
Medium · 55%
vs
2–1
San Diego 2, USA,
hard
✗ Missed
Medium · 55%
vs
0–2
Buenos Aires, Argentina
clay
✗ Missed
Medium · 62%
vs
1–2
Buenos Aires, Argentina
clay
✗ Missed
Medium · 59%
vs
2–1
San Diego 2, USA,
hard
✓ Correct
Low · 54%
vs
0–2
Buenos Aires, Argentina
clay
✗ Missed
Low · 55%
vs
2–0
San Diego 2, USA,
hard
✓ Correct
High · 71%
vs
1–2
San Diego 2, USA,
hard
✓ Correct
Low · 51%
vs
1–2
San Diego 2, USA,
hard
✗ Missed
Low · 53%
vs
2–1
Genoa 2, Italy
clay
✓ Correct
High · 69%
vs
2–1
Tolentino, Italy
clay
✓ Correct
High · 66%
vs
1–2
Tolentino, Italy
clay
✓ Correct
High · 76%
vs
2–0
Saint Tropez, France
hard
✓ Correct
High · 73%
vs
2–1
Buenos Aires, Argentina
clay
✓ Correct
High · 79%
vs
1–2
WTA 125k Ankara, Turkiye Women Singles
hard
✗ Missed
Medium · 58%
vs
2–1
Porto, Portugal
hard
✓ Correct
High · 65%
vs
2–0
Genoa 2, Italy
clay
✓ Correct
Medium · 64%
vs
2–0
WTA 125k Ankara, Turkiye Women Singles
hard
✓ Correct
Medium · 57%
vs
2–0
Tolentino, Italy
clay
✗ Missed
High · 75%
vs
2–1
Plovdiv 4, Bulgaria
clay
✓ Correct
High · 80%
vs
0–2
Saint Tropez, France
hard
✓ Correct
High · 79%
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.