TennisEdge's AI model finds no betting value in J. De Jong vs L. Draxl (French Open on 2026-05-20) — the market is efficient, with J. De Jong favoured at 1.30.
Independent estimates of who wins, each from a different method. The blend is what the bot prices against the market.
| Method | J. De Jong | L. Draxl |
|---|---|---|
| Elo ratings-based, surface-weighted |
59.7% | 40.3% |
| Machine learning 29-feature gradient-boosted model |
56.3% | 43.7% |
| Serve / return point-by-point simulation |
44.4% | 55.6% |
| Blend what the bot actually prices off |
53.5% | 46.5% |
| Market implied de-vigged from the opening odds |
72.3% | 27.7% |
We publish how well these score against the closing market, including where they lose: how accurate are tennis predictions?
| Player | Surface | Elo | Record | Matches |
|---|---|---|---|---|
| J. De Jong | clay | 1752 | 139–88 | 227 |
| L. Draxl | hard | 1669 | 166–82 | 248 |
Our own ratings, computed from match results since 2018. Players with fewer than 5 rated matches are omitted rather than shown at a provisional starting value. Last updated July 21, 2026.
Level at 1–1 over 2 meetings. Full record.
| Date | Event | Surface | Winner | Score |
|---|---|---|---|---|
| May 20, 2026 | French Open | clay | J. De Jong | 2 - 1 |
| Jan. 22, 2025 | Oeiras 5 | hard | L. Draxl | 2 - 0 |
| L | T. Skatov | 2 - 1 | July 21, 2026 |
| L | S. Baez | 0 - 2 | July 16, 2026 |
| W | V. Gaubas | 2 - 0 | July 13, 2026 |
| L | J. Fonseca | 0 - 3 | July 1, 2026 |
| W | R. Hijikata | 3 - 2 | June 30, 2026 |
| L | T. Samuel | 0 - 2 | July 26, 2026 |
| W | S. Mochizuki | 0 - 2 | July 25, 2026 |
| W | C. Chidekh | 2 - 0 | July 24, 2026 |
| W | A. Holmgren | 1 - 2 | July 23, 2026 |
| W | M. Hurrion | 0 - 2 | July 21, 2026 |
All May 20, 2026 results & picks →
Math-only prediction: no LLM calls used