Here’s the test that matters: when we say a number, does it actually hit that often? Every pick is graded against its final pre-match number, and every one is here so you can check.
Across 544 graded picks, our pick won 61.4%. The table below shows how that holds up at each confidence level — including where we’ve run overconfident. Nothing’s hidden.
UFC — graded record coming soon
UFC predictions publish live now and are graded in public going forward; a full graded UFC record will appear here once fights settle. The numbers below are our tennis record.
Tennis
Our public tennis record — how often our picks won, an accuracy score, and every graded pick broken out by confidence level.
Graded picks
544
final pre-match predictions, all tours
How often our pick won
61.4%
across every graded pick
Accuracy score
0.242
lower is better; 0.25 = a coin flip
Does the number hold up?
How our picks did, by confidence level
| We said | Matches | Our pick won | Actual rate | Likely range | Accuracy score |
|---|---|---|---|---|---|
| 50-55% | 166 | 100 | 60.2% | 52.6–67.4% | 0.239 |
| 55-60% | 90 | 55 | 61.1% | 50.8–70.5% | 0.239 |
| 60-65% | 88 | 48 | 54.5% | 44.2–64.5% | 0.253 |
| 65-70% | 56 | 34 | 60.7% | 47.6–72.4% | 0.244 |
| 70-75% | 49 | 31 | 63.3% | 49.3–75.3% | 0.238 |
| 75-80% | 36 | 25 | 69.4% | 53.1–82.0% | 0.219 |
| 80-85% | 25 | 18 | 72.0% | 52.4–85.7% | 0.211 |
| 85-90% | 19 | 14 | 73.7% | 51.2–88.2% | 0.213 |
| 90-95% | 9 | 6 | 66.7% | 35.4–87.9% | 0.285 |
| 95-100% | 6 | 3 | 50.0% | 18.8–81.2% | 0.469 |
Grading uses final pre-match predictions only — numbers frozen before first serve. Retirements and walkovers are excluded.
Set-score accuracy
Every match page shows a "most likely score" — this is how often that exact score actually happened. Best-of-3 and best-of-5 aren't comparable: bo3 has 4 possible scores, bo5 has 6, so bo5 is the harder pick.
Best-of-3
33.3%
exact score correct, 92 of 276
Best-of-5
16.8%
exact score correct, 18 of 107
Upset calls
About 1 in 9 of our picks back the player our own ratings rank clearly lower — the other player rates clearly higher. We expect to lose these more often than we win them; the honest comparison is against underdogs in general, who win roughly a third of the time.
Upset-call record
23-37
38.3% of 60 graded calls
If we’d picked the higher-rated player
61.7%
how often siding with the ratings would have won
How often any underdog wins
~35%
roughly, across underdogs in general
ATP
63.0% of picks won over 311 picks · accuracy score 0.240
WTA
59.2% of picks won over 233 picks · accuracy score 0.243