Tennis Predictions
Model win probabilities for ATP & WTA matches, with a confidence rating per pick and a public accuracy record over every settled match.
152Upcoming
64.3%Accuracy
9975Settled
Umag
clay
✓ Correct
High · 78%
vs
2–0
Winston-Salem W01
hard
✗ Missed
Low · 52%
vs
2–1
Umag
clay
✗ Missed
Low · 54%
vs
0–2
Winston-Salem M01
hard
✓ Correct
Low · 51%
vs
1–2
Umag
clay
✗ Missed
Medium · 56%
vs
1–2
Umag
clay
✓ Correct
High · 75%
vs
2–1
WTA 125K Newport, USA Women Singles
grass
✗ Missed
Low · 52%
vs
0–2
WTA Athens, Greece Women Singles
hard
✓ Correct
High · 85%
vs
0–2
WTA Athens, Greece Women Singles
hard
✓ Correct
High · 73%
vs
1–2
Winston-Salem W01
hard
✗ Missed
High · 71%
vs
0–2
ATP Challenger Liege, Belgium Men Singles
clay
✗ Missed
High · 71%
vs
2–0
WTA Athens, Greece Women Singles
hard
✗ Missed
High · 69%
vs
2–1
Winston-Salem W01
hard
✓ Correct
Medium · 63%
vs
2–0
WTA 125K Newport, USA Women Singles
grass
✗ Missed
Low · 51%
vs
0–2
Umag
clay
✓ Correct
High · 89%
vs
0–2
Umag
clay
✓ Correct
Medium · 58%
vs
1–0
Gstaad
clay
✓ Correct
High · 68%
vs
0–2
Wimbledon, Women
grass
✗ Missed
Medium · 59%
vs
1–2
Umag
clay
✓ Correct
Medium · 57%
vs
0–2
Bogota, Colombia
clay
✓ Correct
High · 65%
vs
2–0
Winston-Salem W01
hard
✓ Correct
Medium · 55%
vs
0–2
Umag
clay
✓ Correct
High · 73%
vs
2–0
Winston-Salem M01
hard
✗ Missed
Low · 50%
vs
0–2
Winston-Salem M01
hard
✓ Correct
Medium · 57%
vs
1–2
Winston-Salem M01
hard
✗ Missed
Low · 53%
vs
1–0
WTA Athens, Greece Women Singles
hard
✓ Correct
High · 73%
vs
2–0
Trieste, Italy
clay
✓ Correct
High · 75%
vs
1–2
Gstaad
clay
✓ Correct
High · 80%
vs
2–0
Contrexeville, France
clay
✗ Missed
Low · 52%
vs
2–0
WTA Athens, Greece Women Singles
hard
✓ Correct
Medium · 65%
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.