Tennis Predictions
Model win probabilities for ATP & WTA matches, with a confidence rating per pick and a public accuracy record over every settled match.
107Upcoming
73.3%Accuracy
6303Settled
Perugia, Italy
clay
✓ Correct
High · 79%
vs
0–2
Perugia, Italy
clay
✓ Correct
High · 79%
vs
0–2
ATP Challenger Centurion 2, South Africa Men Singles
hard
✓ Correct
High · 70%
vs
1–2
Little Rock, USA
hard
✓ Correct
High · 73%
vs
2–1
Roland Garros
clay
✓ Correct
High · 87%
vs
2–3
Little Rock, USA
hard
✓ Correct
High · 68%
vs
2–1
Little Rock, USA
hard
✓ Correct
High · 66%
vs
2–0
Vicenza, Italy
clay
✗ Missed
High · 76%
vs
0–2
Roland Garros
clay
✗ Missed
High · 76%
vs
1–2
Roland Garros
clay
✓ Correct
High · 79%
vs
1–3
Kosice, Slovakia Men Singles
clay
✓ Correct
High · 76%
vs
2–1
ATP Challenger Chisinau, Moldova Men Singles
clay
✓ Correct
High · 66%
vs
0–2
WTA 125K Birmingham, Great Britain Women Singles
grass
✓ Correct
High · 76%
vs
0–2
Roland Garros
clay
✓ Correct
High · 88%
vs
2–0
Roland Garros
clay
✗ Missed
High · 79%
vs
2–1
Roland Garros
clay
✓ Correct
High · 71%
vs
3–2
WTA 125K Birmingham, Great Britain Women Singles
grass
✓ Correct
High · 66%
vs
2–0
WTA 125K Birmingham, Great Britain Women Singles
grass
✓ Correct
High · 66%
vs
2–1
WTA 125K Birmingham, Great Britain Women Singles
grass
✓ Correct
High · 74%
vs
2–0
WTA 125K Birmingham, Great Britain Women Singles
grass
✓ Correct
High · 80%
vs
1–2
Roland Garros
clay
✓ Correct
High · 67%
vs
1–2
Roland Garros
clay
✗ Missed
High · 76%
vs
2–3
Roland Garros
clay
✓ Correct
High · 89%
vs
1–3
Roland Garros
clay
✓ Correct
High · 82%
vs
2–0
Roland Garros
clay
✗ Missed
High · 74%
vs
2–3
Roland Garros
clay
✗ Missed
High · 73%
vs
3–2
Roland Garros
clay
✗ Missed
High · 70%
vs
2–0
Roland Garros
clay
✓ Correct
High · 71%
vs
2–0
Roland Garros
clay
✓ Correct
High · 67%
vs
2–3
Roland Garros
clay
✓ Correct
High · 72%
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.