TennisEdge's AI model finds no betting value in S. Cirstea vs S. Bejlek (Wimbledon on 2026-06-29) — the market is efficient, with S. Cirstea favoured at 1.36.
Independent estimates of who wins, each from a different method. The blend is what the bot prices against the market.
| Method | S. Cirstea | S. Bejlek |
|---|---|---|
| Elo ratings-based, surface-weighted |
61.7% | 38.3% |
| Machine learning 29-feature gradient-boosted model |
52.1% | 47.9% |
| Blend what the bot actually prices off |
60.6% | 39.4% |
| Market implied de-vigged from the opening odds |
70.2% | 29.8% |
We publish how well these score against the closing market, including where they lose: how accurate are tennis predictions?
| Player | Surface | Elo | Record | Matches |
|---|---|---|---|---|
| S. Cirstea | hard | 1917 | 94–63 | 157 |
| S. Bejlek | clay | 1747 | 137–58 | 195 |
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 March 23, 2026.
S. Cirstea leads 1–0 over 1 meeting. Full record.
| Date | Event | Surface | Winner | Score |
|---|---|---|---|---|
| June 30, 2026 | Wimbledon | grass | S. Cirstea | 2 - 0 |
| L | L. Noskova | 1 - 2 | July 4, 2026 |
| W | K. Birrell | 2 - 0 | July 2, 2026 |
| W | S. Bejlek | 2 - 0 | June 30, 2026 |
| L | E. Raducanu | 0 - 2 | June 12, 2026 |
| W | M. Inglis | 2 - 1 | June 9, 2026 |
| W | Xiy. Wang | 1 - 2 | Aug. 2, 2026 |
| L | L. Tagger | 2 - 0 | July 24, 2026 |
| W | M. Timofeeva | 0 - 2 | July 23, 2026 |
| W | A. Blinkova | 1 - 2 | July 21, 2026 |
| L | C. Tauson | 2 - 0 | July 17, 2026 |
All June 29, 2026 results & picks →
MATCH: S. Cirstea (A) vs S. Bejlek (B) | Wimbledon 1/64 | grass | 2026-06-30 MODELS: ELO A 0.617 | ML A 0.521 | Model A 0.606 | Market A 0.702 (1.36) / B 0.298 (3.20) | value_pick B edge +9.5% Alignment: ELO ~ market (both favor A); ML dissents hard toward coin-flip (A 0.52). Market prices A ABOVE model (0.70 vs 0.606) -> no value on A; the math value sits on B (model 0.394 vs implied 0.298). FORM A (Cirstea): clay-court engine in great touch -> beat Sabalenka(2052,GRIND), Ostapenko(1890,GRIND), Noskova(1790,DOM); Rome SF, French QF. GRASS evidence thin + negative: LOST to Raducanu(1767) 4-6 2-6, only GRIND win vs Inglis(1623). Off 18 days -> rust risk. FORM B (Bejlek): WEAK grass -> blown out by Yastremska(1712) 6-1 6-2, LOST to Ka.Pliskova(1690) 3 sets; lone grass win a 3-set double-TB grind vs Siegemund(1688). Quality of wins well below A. FATIGUE: A well-rested (0 matches/14d, 18d off). B heavy: 3 matches/14d, ~270 court min, back-to-back, grueling 7-6 7-6 grind Jun 23. Edge A. NARRATIVE: No recent Final -> no let-down. RED FLAG: B took a WALKOVER (withdrawal) vs Sonmez on Jun 24 -> fitness concern entering a best-of-3 Slam. No venue history on grass for either. VERDICT: Real model+ML edge on underdog B and A is overpriced by market, BUT the qualitative case for backing B is undercut by poor grass form AND a fitness-flag walkover 6 days ago. Value exists on paper; conviction insufficient for a confident bet. LEAN B, no stake.