Monte Carlo Engine

Tennis Tournament Simulations

For every live ATP tournament we simulate the entire remaining bracket 20,000 times on our Elo & Glicko-2 player ratings. Completed matches are locked in, every match still to play is sampled from its win probability — what comes out is each player's chance of reaching every round and lifting the trophy.

Updated Jun 10, 09:44 20,000 simulations / draw Calibrated probabilities How it works

's-Hertogenbosch 2026

ATP 250 grass Round of 32 in play
20,000 simulations
draw updated Jun 10, 09:44
21 players still in the running
Alex De Minaur De Minaur 22.9% title chance
Felix Auger Aliassime Auger Aliassime 20.2% title chance
Daniil Medvedev Medvedev 19.5% title chance
R16 QF 77.8% SF 57.4% F 40.2% Title 22.9% E[wins] 2.98 Elo 1809 Seed 2 Country AUS
R16 QF 74.2% SF 54.5% F 32.7% Title 20.2% E[wins] 2.82 Elo 1857 Seed 1 Country CAN
R16 QF 76.3% SF 54.2% F 31.9% Title 19.5% E[wins] 2.82 Elo 1966 Seed 3 Country RUS
R16 QF 60.0% SF 35.8% F 15.9% Title 6.6% E[wins] 2.18 Elo 1655 Seed 4 Country FRA
R16 55.7% QF 40.9% SF 21.1% F 9.2% Title 3.9% E[wins] 1.31 Elo 1660 Seed 6 Country NED
R16 QF 55.5% SF 20.1% F 8.2% Title 3.5% E[wins] 1.87 Elo 1690 Country CRO
R16 QF 55.0% SF 18.5% F 8.7% Title 3.1% E[wins] 1.85 Elo 1669 Seed 5 Country FRA
R16 65.0% QF 39.1% SF 14.8% F 6.3% Title 2.8% E[wins] 1.28 Elo 1653 Country POL
R16 QF 40.0% SF 19.8% F 7.0% Title 2.4% E[wins] 1.69 Elo 1483 Country FRA
R16 QF 44.5% SF 14.3% F 5.1% Title 2.1% E[wins] 1.66 Elo 1602 Country POR
R16 QF 45.0% SF 13.5% F 6.2% Title 2.1% E[wins] 1.67 Elo 1612 Country FRA
R16 44.3% QF 30.1% SF 14.0% F 5.5% Title 2.0% E[wins] 0.96 Elo 1679 Country NED
R16 QF 22.2% SF 10.5% F 4.6% Title 1.7% E[wins] 1.39 Elo 1642 Country USA
R16 52.6% QF 14.0% SF 7.3% F 2.8% Title 1.2% E[wins] 0.78 Elo 1593 Country HUN
R16 61.2% QF 28.6% SF 8.5% F 3.1% Title 1.2% E[wins] 1.03 Elo 1602 Seed 8 Country BEL
R16 36.6% QF 8.4% SF 4.4% F 1.8% Title 0.9% E[wins] 0.52 Elo 1505 Country NED
R16 47.4% QF 11.8% SF 6.0% F 2.3% Title 0.9% E[wins] 0.68 Elo 1590 Country POL
R16 63.4% QF 15.3% SF 7.1% F 2.6% Title 0.9% E[wins] 0.89 Elo 1647 Country CHN
R16 38.8% QF 15.7% SF 4.8% F 1.7% Title 0.8% E[wins] 0.62 Elo 1525 Country AUS
R16 QF 29.0% SF 9.3% F 2.5% Title 0.6% E[wins] 1.41 Elo 1467 Country CHN
R16 35.0% QF 16.6% SF 4.1% F 1.4% Title 0.5% E[wins] 0.58 Elo 1519 Country FIN
Eliminated (7)
Denis Shapovalov · out in R32 Elias Ymer · out in R32 Gabriel Diallo · out in R32 Jaume Munar · out in R32 Jenson Brooksby · out in R32 Mees Rottgering · out in R32 Terence Atmane · out in R32
Elo + Glicko-2 rating model · per-simulation skill uncertainty sampling · played results locked in · qualifiers priced with field-average ratings

Stuttgart 2026

ATP 250 grass Round of 16 in play
20,000 simulations
draw updated Jun 10, 09:44
16 players still in the running
Taylor Fritz Fritz 30.3% title chance
Ben Shelton Shelton 26.2% title chance
Alexander Bublik Bublik 12.1% title chance
R16 QF 82.6% SF 67.3% F 48.9% Title 30.3% E[wins] 3.29 Elo 1871 Seed 2 Country USA
R16 QF 82.6% SF 65.5% F 44.3% Title 26.2% E[wins] 3.19 Elo 1948 Seed 1 Country USA
R16 QF 71.1% SF 54.8% F 25.2% Title 12.1% E[wins] 2.63 Elo 1713 Seed 3 Country KAZ
R16 QF 78.6% SF 51.0% F 24.7% Title 11.8% E[wins] 2.66 Elo 1867 Seed 4 Country CZE
R16 QF 67.1% SF 30.2% F 12.0% Title 4.8% E[wins] 2.14 Elo 1834 Seed 6 Country USA
R16 QF 41.6% SF 12.6% F 6.7% Title 3.5% E[wins] 1.65 Elo 1500 Country AUS
R16 QF 60.7% SF 16.1% F 7.4% Title 2.5% E[wins] 1.87 Elo 1687 Country GER
R16 QF 28.9% SF 17.0% F 5.0% Title 1.5% E[wins] 1.52 Elo 1523 Country GER
R16 QF 17.4% SF 8.8% F 3.8% Title 1.2% E[wins] 1.31 Elo 1707 Country ESP
R16 QF 58.4% SF 13.0% F 4.4% Title 1.2% E[wins] 1.77 Elo 1619 Country JPN
R16 QF 54.7% SF 16.1% F 4.3% Title 1.1% E[wins] 1.76 Elo 1550 Country FRA
R16 QF 17.4% SF 8.8% F 2.9% Title 0.9% E[wins] 1.30 Elo 1570 Country USA
R16 QF 32.9% SF 10.4% F 2.7% Title 0.8% E[wins] 1.47 Elo 1677 Country AUS
R16 QF 45.3% SF 12.0% F 2.8% Title 0.7% E[wins] 1.61 Elo 1560 Country BEL
R16 QF 39.3% SF 7.7% F 2.5% Title 0.7% E[wins] 1.50 Elo 1533 Country ITA
R16 QF 21.4% SF 8.3% F 2.1% Title 0.6% E[wins] 1.32 Elo 1544 Country AUS
Eliminated (12)
Alejandro Davidovich Fokina · out in R32 Aleksandar Kovacevic · out in R32 Alexis Galarneau · out in R32 Corentin Moutet · out in R32 Daniel Altmaier · out in R32 Diego Dedura · out in R32 Fabian Marozsan · out in R32 Pierre Hugues Herbert · out in R32 Quentin Halys · out in R32 Roberto Bautista Agut · out in R32 Roman Safiullin · out in R32 Tom Gentzsch · out in R32
Elo + Glicko-2 rating model · per-simulation skill uncertainty sampling · played results locked in · qualifiers priced with field-average ratings

Track record — tested against history, no hindsight

Before going live, the engine was made to re-forecast 30 historical ATP tournaments (2023–2025) from each one's opening day — with the model trained only on data through 2022, so it could never peek at the answers. These are the results, straight from that test.

33% champions named
pre-tournament (top pick)
67% champions in our
top 5 picks
100% top-5 hit rate
at Grand Slams
21% for comparison: just
picking the #1 seed

By tournament tier

TiernTop-1Top-5
Grand Slams1242%100%
Masters 10001030%50%
ATP 500520%40%
ATP 250333%33%

Do the probabilities mean what they say?

When we predicted…It happenedn
0–1% (avg 0.2%)0.1%6,650
1–2% (avg 1.5%)0.7%1,347
2–5% (avg 3.3%)3.0%1,985
5–10% (avg 7.2%)6.9%1,641
10–20% (avg 14.4%)13.8%1,721
20–30% (avg 24.5%)23.9%961
30–50% (avg 40.4%)42.0%1,597
50–70% (avg 58.8%)59.6%1,379
70–90% (avg 78.5%)79.4%528
90–100% (avg 98.7%)98.9%379

Every round-reach probability from the test, grouped into bands and compared with what actually happened — predicted and observed match within about a point in every band. That's what makes a 30% title chance a number you can act on, not a vibe.

Backtest generated Jun 09, 23:41 · 20,000 simulations per tournament · methodology in how the simulations work · more model audits on model transparency.

How the simulations work

Where do these probabilities come from?

Every player carries Elo, Glicko-2 and surface-specific strength ratings rebuilt from 39,000+ ATP matches. A calibrated model turns any rating gap into a match win probability, and we then play out the entire remaining bracket 20,000 times — sampling every not-yet-played match from its probability. A player's title chance is simply the share of those 20,000 tournaments he wins.

Why simulate instead of just picking the favourite?

Because the draw matters. Two equally strong players can have very different title chances if one has byes and qualifiers ahead while the other faces seeds from the second round. Simulation prices the whole path — including the matches your rivals might lose for you — which a single head-to-head number can't capture.

How accurate are these forecasts?

Backtested on 30 historical ATP tournaments (2023–2025): the pre-tournament favourite by our model won 33% of events and the champion came from our top 5 in 67% (100% at Grand Slams). More importantly, the probabilities are calibrated: when we say a player has a 40% chance of reaching a round, it happens about 40% of the time. See model transparency.

When do the forecasts update?

On every daily prediction run while a tournament is live: finished matches are locked in, ratings refresh, and the remaining bracket is re-simulated — so the odds sharpen round by round until the final.

1 · Rate

Every player carries continuously updated Elo, Glicko-2 and surface-specific strength ratings, rebuilt from 39,000+ ATP matches since 2015.

2 · Simulate

The remaining bracket is played out 20,000 times. Each hypothetical match is sampled from the rating model's win probability; rating uncertainty is resampled per simulation so volatile players get honest long shots.

3 · Verify

Backtested on 30 historical tournaments: round-reach probabilities are calibrated within a point of observed frequencies. See model transparency.