TennisEdge's AI model finds no betting value in B. Nakashima vs F. Cerundolo (London on 2026-06-20) — the market is efficient, with B. Nakashima favoured at 1.57.
Independent estimates of who wins, each from a different method. The blend is what the bot prices against the market.
| Method | B. Nakashima | F. Cerundolo |
|---|---|---|
| Elo ratings-based, surface-weighted |
71.3% | 28.7% |
| Machine learning 29-feature gradient-boosted model |
63.4% | 36.6% |
| Blend what the bot actually prices off |
65.0% | 35.0% |
| Market implied de-vigged from the opening odds |
60.2% | 39.8% |
We publish how well these score against the closing market, including where they lose: how accurate are tennis predictions?
| Player | Surface | Elo | Record | Matches |
|---|---|---|---|---|
| B. Nakashima | hard | 1848 | 175–101 | 276 |
| F. Cerundolo | clay | 1861 | 125–69 | 194 |
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 Aug. 1, 2026.
Level at 1–1 over 2 meetings. Full record.
| Date | Event | Surface | Winner | Score |
|---|---|---|---|---|
| July 17, 2026 | UTS Championship | hard | B. Nakashima | 3 - 1 |
| June 20, 2026 | London | grass | F. Cerundolo | 2 - 1 |
| L | T. Fritz | 1 - 2 | Aug. 1, 2026 |
| W | A. De Minaur | 0 - 2 | July 31, 2026 |
| W | J. Mensik | 2 - 1 | July 30, 2026 |
| W | T. M. Etcheverry | 2 - 0 | July 28, 2026 |
| W | L. Miguel | 0 - 3 | July 18, 2026 |
| L | A. Gea | 1 - 2 | July 31, 2026 |
| W | T. Boyer | 0 - 1 | July 30, 2026 |
| L | L. Miguel | 3 - 2 | July 18, 2026 |
| W | C. Norrie | 3 - 0 | July 18, 2026 |
| L | B. Nakashima | 1 - 3 | July 17, 2026 |
All June 20, 2026 results & picks →
Math-only prediction: no LLM calls used