Season script report

Most Predictable WTA Players

Every match, our model publishes a win probability, and prices its own uncertainty. This board compares each player's actual results with that script: straight-sets players land where the model expected, wild cards keep tearing the script up. A season-level read with sample sizes and confidence intervals, never a career label.

The metronome · 2024
Karolina Muchova
2 upsets where the model expected 7.7 · 19-6 in 25 matches · model called it right 92.0% of the time
The wild card · 2024
Ashlyn Krueger
19 upsets where the model expected only 13.0 · 14-22 in 36 matches · model called it right 47.2% of the time

Script vs chaos: the two ends of 2024

Bars show extra upsets: how many more (or fewer) times the model's favorite fell in this player's matches than the model itself expected. Verdicts in the table are assigned only when the difference is statistically meaningful for that sample. Everyone else stays "On serve". How to read this →

Full board · 97 players with ≥20 matches (2429 matches, source: out-of-sample backtest)

# Player Verdict Upsets Expected Extra Model hit Confidence W-L M
1 Karolina Muchova Straight sets 2 7.7 -5.7 ±4.4 92.0% 69.1% 19-6 25
2 Qinwen Zheng Straight sets 9 16.0 -7.0 ±6.4 83.3% 70.4% 39-15 54
3 Elina Svitolina Straight sets 9 14.9 -5.9 ±6.0 79.1% 65.5% 27-16 43
4 Tamara Korpatsch Straight sets 3 6.6 -3.6 ±4.0 85.0% 67.2% 4-16 20
5 Nao Hibino Straight sets 3 6.4 -3.4 ±4.0 85.0% 67.9% 4-16 20
6 Xiyu Wang Straight sets 10 14.8 -4.8 ±5.9 75.6% 63.9% 19-22 41
7 Beatriz Haddad Maia Straight sets 16 21.6 -5.6 ±7.1 71.9% 62.1% 33-24 57
8 Martina Trevisan On serve 6 9.1 -3.1 ±4.7 77.8% 66.1% 7-20 27
9 Danielle Collins On serve 12 16.2 -4.2 ±6.3 76.0% 67.7% 35-15 50
10 Peyton Stearns On serve 12 15.7 -3.7 ±6.0 71.4% 62.6% 21-21 42
11 Katie Boulter On serve 12 15.8 -3.8 ±6.2 73.3% 64.9% 27-18 45
12 Arantxa Rus On serve 12 15.6 -3.6 ±5.9 70.0% 60.9% 17-23 40
13 Petra Martic On serve 7 9.8 -2.8 ±4.7 73.1% 62.4% 9-17 26
14 Coco Gauff On serve 12 15.8 -3.8 ±6.5 80.6% 74.4% 47-15 62
15 Karolina Pliskova On serve 9 12.1 -3.1 ±5.4 74.3% 65.4% 20-15 35
16 Emma Raducanu On serve 8 10.6 -2.6 ±5.0 71.4% 62.2% 16-12 28
17 Naomi Osaka On serve 10 12.7 -2.7 ±5.5 72.2% 64.8% 20-16 36
18 Elena Rybakina On serve 9 11.8 -2.8 ±5.7 82.0% 76.5% 41-9 50
19 Donna Vekic On serve 14 16.9 -2.9 ±6.2 68.2% 61.6% 25-19 44
20 Marie Bouzkova On serve 14 16.8 -2.8 ±6.2 68.9% 62.7% 25-20 45
21 Iga Swiatek On serve 8 10.4 -2.4 ±5.5 85.2% 80.7% 47-7 54
22 Jasmine Paolini On serve 15 17.7 -2.7 ±6.5 68.8% 63.1% 33-15 48
23 Marta Kostyuk On serve 15 17.6 -2.6 ±6.5 70.0% 64.7% 31-19 50
24 Taylor Townsend On serve 9 11.0 -2.0 ±5.2 71.0% 64.7% 15-16 31
25 Jessica Pegula On serve 12 14.3 -2.3 ±6.0 73.9% 69.0% 35-11 46
26 Elisabetta Cocciaretto On serve 12 13.9 -1.9 ±5.7 69.2% 64.5% 18-21 39
27 Magda Linette On serve 17 19.1 -2.1 ±6.6 66.0% 61.8% 26-24 50
28 Paula Badosa On serve 18 20.1 -2.1 ±6.9 67.3% 63.5% 37-18 55
29 Madison Keys On serve 9 10.5 -1.5 ±5.1 73.5% 69.0% 23-11 34
30 Varvara Gracheva On serve 12 13.7 -1.7 ±5.6 67.6% 63.1% 15-22 37
31 Harriet Dart On serve 6 7.0 -1.0 ±4.1 70.0% 64.8% 8-12 20
32 Aryna Sabalenka On serve 13 14.5 -1.5 ±6.4 80.3% 78.0% 54-12 66
33 Linda Noskova On serve 13 14.4 -1.4 ±5.9 69.0% 65.7% 26-16 42
34 Jaqueline Cristian On serve 12 13.3 -1.3 ±5.7 68.4% 65.0% 18-20 38
35 Mayar Sherif On serve 7 8.0 -1.0 ±4.4 69.6% 65.2% 9-14 23
36 Daria Kasatkina On serve 20 21.6 -1.6 ±7.1 64.9% 62.2% 35-22 57
37 Katerina Siniakova On serve 17 18.4 -1.4 ±6.6 66.0% 63.2% 26-24 50
38 Clara Tauson On serve 9 10.0 -1.0 ±5.0 70.0% 66.7% 14-16 30
39 Lesia Tsurenko On serve 10 11.0 -1.0 ±5.0 65.5% 62.1% 10-19 29
40 Jelena Ostapenko On serve 14 14.8 -0.8 ±6.1 68.2% 66.3% 28-16 44
41 Viktoriya Tomova On serve 17 17.8 -0.8 ±6.4 63.8% 62.2% 21-26 47
42 Yue Yuan On serve 19 19.8 -0.8 ±6.7 62.7% 61.2% 27-24 51
43 Diana Shnaider On serve 21 21.7 -0.7 ±7.2 65.6% 64.4% 41-20 61
44 Emma Navarro On serve 22 22.7 -0.7 ±7.3 65.1% 63.9% 43-20 63
45 Greet Minnen On serve 11 11.5 -0.5 ±5.2 64.5% 63.0% 12-19 31
46 Sara Sorribes Tormo On serve 12 12.5 -0.5 ±5.5 66.7% 65.3% 17-19 36
47 Elise Mertens On serve 17 17.5 -0.5 ±6.5 66.0% 65.1% 26-24 50
48 Liudmila Samsonova On serve 18 18.2 -0.2 ±6.5 63.3% 62.8% 26-23 49
49 Clara Burel On serve 14 13.9 +0.1 ±5.7 63.2% 63.3% 16-22 38
50 Ajla Tomljanovic On serve 8 8.0 +0.0 ±4.4 63.6% 63.8% 9-13 22
51 Maria Sakkari On serve 11 10.9 +0.1 ±5.2 65.6% 65.9% 18-14 32
52 Yulia Putintseva On serve 18 17.9 +0.1 ±6.5 64.7% 65.0% 34-17 51
53 Anastasia Potapova On serve 19 18.7 +0.3 ±6.5 59.6% 60.2% 26-21 47
54 Camila Osorio On serve 13 12.8 +0.2 ±5.4 59.4% 60.1% 16-16 32
55 Caroline Dolehide On serve 15 14.6 +0.4 ±5.9 63.4% 64.4% 17-24 41
56 Victoria Azarenka On serve 16 15.5 +0.5 ±6.1 64.4% 65.6% 30-15 45
57 Anna Kalinskaya On serve 18 17.3 +0.7 ±6.5 64.7% 66.1% 33-18 51
58 Ons Jabeur On serve 12 11.3 +0.7 ±5.1 60.0% 62.2% 16-14 30
59 Diane Parry On serve 18 17.1 +0.9 ±6.3 60.0% 61.9% 24-21 45
60 Kamilla Rakhimova On serve 12 11.2 +0.8 ±5.1 60.0% 62.5% 15-15 30
61 Daria Saville On serve 10 9.3 +0.7 ±4.7 60.0% 62.9% 11-14 25
62 Sorana Cirstea On serve 11 10.1 +0.9 ±4.8 59.3% 62.7% 12-15 27
63 Amanda Anisimova On serve 12 11.0 +1.0 ±5.0 57.1% 60.8% 17-11 28
64 Mirra Andreeva On serve 16 14.7 +1.3 ±6.1 67.3% 70.0% 34-15 49
65 Nadia Podoroska On serve 13 11.8 +1.2 ±5.3 61.8% 65.3% 10-24 34
66 Dayana Yastremska On serve 14 12.7 +1.3 ±5.5 58.8% 62.6% 15-19 34
67 Caroline Garcia On serve 11 9.8 +1.2 ±4.9 60.7% 64.9% 14-14 28
68 Bernarda Pera On serve 12 10.8 +1.2 ±5.1 61.3% 65.3% 12-19 31
69 Sara Errani On serve 8 7.0 +1.0 ±4.2 65.2% 69.7% 10-13 23
70 Magdalena Frech On serve 21 19.3 +1.7 ±6.7 60.4% 63.7% 28-25 53
71 Anastasia Pavlyuchenkova On serve 16 14.4 +1.6 ±5.9 62.8% 66.4% 25-18 43
72 Lin Zhu On serve 12 10.5 +1.5 ±4.9 57.1% 62.5% 12-16 28
73 Sloane Stephens On serve 17 15.1 +1.9 ±5.9 56.4% 61.2% 19-20 39
74 Marketa Vondrousova On serve 9 7.6 +1.4 ±4.4 64.0% 69.7% 15-10 25
75 Rebecca Sramkova On serve 13 11.3 +1.7 ±5.1 56.7% 62.5% 21-9 30
76 Yafan Wang On serve 13 11.1 +1.9 ±5.1 58.1% 64.1% 15-16 31
77 Cristina Bucsa On serve 15 13.0 +2.0 ±5.5 57.1% 63.0% 14-21 35
78 Anna Karolina Schmiedlova On serve 13 11.1 +1.9 ±5.0 53.6% 60.3% 11-17 28
79 Tatjana Maria On serve 16 13.8 +2.2 ±5.7 59.0% 64.6% 13-26 39
80 Lucia Bronzetti On serve 19 16.6 +2.4 ±6.2 57.8% 63.1% 19-26 45
81 Sofia Kenin On serve 15 12.6 +2.4 ±5.4 57.1% 64.0% 14-21 35
82 Katie Volynets On serve 13 10.7 +2.3 ±5.1 56.7% 64.3% 13-17 30
83 Caroline Wozniacki On serve 12 9.7 +2.3 ±4.8 55.6% 64.0% 15-12 27
84 Veronika Kudermetova On serve 19 16.0 +3.0 ±6.0 53.7% 60.9% 16-25 41
85 Viktorija Golubic On serve 11 8.5 +2.5 ±4.5 52.2% 63.1% 11-12 23
86 Barbora Krejcikova On serve 12 9.3 +2.7 ±4.8 57.1% 66.9% 16-12 28
87 Ekaterina Alexandrova On serve 22 18.1 +3.9 ±6.5 55.1% 63.0% 26-23 49
88 Laura Siegemund On serve 16 12.4 +3.6 ±5.3 50.0% 61.1% 17-15 32
89 Elina Avanesyan On serve 21 16.8 +4.2 ±6.2 53.3% 62.8% 24-21 45
90 Ana Bogdan On serve 14 10.5 +3.5 ±5.0 50.0% 62.3% 12-16 28
91 Anhelina Kalinina On serve 21 16.6 +4.4 ±6.1 50.0% 60.6% 19-23 42
92 Jessica Bouzas Maneiro On serve 11 7.9 +3.1 ±4.3 47.6% 62.4% 10-11 21
93 Erika Andreeva Wild card 12 8.4 +3.6 ±4.5 52.0% 66.5% 9-16 25
94 Leylah Fernandez Wild card 21 16.0 +5.0 ±6.2 53.3% 64.4% 24-21 45
95 Xinyu Wang Wild card 21 15.5 +5.5 ±6.0 47.5% 61.3% 20-20 40
96 Anna Blinkova Wild card 21 15.0 +6.0 ±5.8 43.2% 59.4% 12-25 37
97 Ashlyn Krueger Wild card 19 13.0 +6.0 ±5.5 47.2% 64.0% 14-22 36

Serve projections: who we read best, and worst

Before every match we project how many aces each player will serve. The bar is how much closer that projection lands than the naive forecast anyone can build without a model, which is the average of the player's own last 5 matches. Positive means we add something on that player. Ranking by raw error would just rank the tour by serve volume, so the comparison is always against each player's own baseline.

We read it our projection beats the player's own last-5 average, and the whole 95% interval agrees Level the gap is inside the noise for this sample, where most players belong Baseline wins the last-5 average reads this player better than we do

Full board below, 110 players with at least 12 matches in 2025 where both our projection and the last-5 baseline could be scored (source: out-of-sample backtest). A verdict is printed only when the 95% interval of the per-match comparison stays on one side of zero. Everyone else is level with the baseline for this sample, which is where most players belong. The serve record does not cover 2024, so this board shows 2025, the most recent season whose serve projections we can score.

# Player Verdict Edge Our miss Baseline miss Actual avg Projected avg M

How this is measured, and what it does not claim

An upset is a match where our model's favorite loses. The model does not expect zero upsets: a 55/45 call is expected to go wrong 45 times out of 100. Adding those probabilities across a player's schedule gives their expected upsets, tailored to the exact opponents they faced. The board compares that number with the upsets that actually happened: fewer than expected earns Straight sets, more than expected earns Wild card, and anything within the statistical noise for that sample stays On serve, which with 60-plus matches is where most players genuinely belong.

Two independent model vintages agree on who broke script within a season, but a wild-card season does not predict a wild-card next season. That is why this is a season report, not a career trait, and why sample sizes and 95% intervals are always shown. The full reasoning, including the proper-scoring-rule version of this metric (the Brier delta) that backs the verdicts, is in the explainer.

The serve board answers a different question with a different metric, and the two never mix. Upsets are about who wins, and are scored against the model's own expectation. Aces and double faults are counts, and are scored against the forecast anyone could make without a model, the average of that player's last five matches. A player can be perfectly on script and still be the one whose serve we read worst.

Recent seasons use our as-published daily record (the same reconciled predictions behind the performance page); earlier seasons use a strict out-of-sample backtest of the current model. One source per season, never mixed. Probabilities and calibration are public on the model transparency page.