TennisEdge's AI model finds no betting value in A. Eala vs E. Rybakina (Berlin on 2026-06-18) — the market is efficient, with E. Rybakina favoured at 1.16.
Independent estimates of who wins, each from a different method. The blend is what the bot prices against the market.
| Method | A. Eala | E. Rybakina |
|---|---|---|
| Elo ratings-based, surface-weighted |
53.0% | 47.0% |
| Machine learning 29-feature gradient-boosted model |
39.7% | 60.3% |
| Serve / return point-by-point simulation |
63.3% | 36.7% |
| Blend what the bot actually prices off |
32.5% | 67.5% |
| Market implied de-vigged from the opening odds |
18.8% | 81.2% |
We publish how well these score against the closing market, including where they lose: how accurate are tennis predictions?
| Player | Surface | Elo | Record | Matches |
|---|---|---|---|---|
| A. Eala | hard | 1905 | 174–90 | 264 |
| E. Rybakina | hard | 2149 | 174–69 | 243 |
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. 3, 2026.
Level at 1–1 over 2 meetings. Full record.
| Date | Event | Surface | Winner | Score |
|---|---|---|---|---|
| June 18, 2026 | Berlin | grass | A. Eala | 2 - 0 |
| May 10, 2026 | Rome | clay | E. Rybakina | 2 - 0 |
| W | J. Pegula | 1 - 2 | Aug. 3, 2026 |
| W | N. Osaka | 0 - 2 | Aug. 1, 2026 |
| W | E. Svitolina | 2 - 0 | July 31, 2026 |
| W | L. Fernandez | 0 - 2 | July 29, 2026 |
| W | Q. Zheng | 2 - 1 | July 28, 2026 |
| L | E. Mertens | 2 - 0 | July 4, 2026 |
| W | C. McNally | 0 - 2 | July 2, 2026 |
| W | L. Boisson | 1 - 2 | June 30, 2026 |
| L | A. Eala | 2 - 0 | June 18, 2026 |
| W | T. Maria | 2 - 1 | June 12, 2026 |
All June 18, 2026 results & picks →
Math-only prediction: no LLM calls used