AI Model Statistics
This is the model's raw hit-rate on the exact 1X2 result across every match it analyses, not the win-rate of our published tips. Our tips combine multiple markets (double chance, over/under, Asian handicap) and win far more often. These figures are cumulative since March 2026 and include earlier model versions; our current model (v4) performs more strongly, see the Ensemble section below. See our tip results. What do these numbers mean?
Outcome Distribution
Over/Under 1.5 Distribution
O/U 1.5 Model Accuracy: 77.6% (1337/1723 correct)
Over/Under 2.5 Distribution
O/U Model Accuracy: 53.6% (1186/2212 correct)
Over/Under 3.5 Distribution
O/U 3.5 Model Accuracy: 65.2% (1123/1723 correct)
Both Teams to Score (BTTS)
BTTS Model Accuracy: 55.5% (956/1723 correct)
Asian Handicap Results
AH Model Accuracy: 44.1% (674/1527 correct, 27 push)
1X2 Model Accuracy by Competition
This is the raw 1X2 (home/draw/away) hit-rate of the model. Our published tips also use double chance, over/under and Asian-handicap markets, so their win-rate differs; see the archive for tip results.
| Competition | Matches | Correct | Accuracy |
|---|---|---|---|
| Serie A | 80 | 47 | 58.8%+25.5 |
| Eredivisie | 59 | 31 | 52.5%+19.2 |
| Serie B | 71 | 36 | 50.7%+17.4 |
| 2. Bundesliga | 65 | 32 | 49.2%+15.9 |
| Primeira Liga | 67 | 32 | 47.8%+14.5 |
| Ekstraklasa | 71 | 33 | 46.5%+13.2 |
| 3. Liga | 65 | 30 | 46.2%+12.9 |
| 1. Division | 98 | 45 | 45.9%+12.6 |
| Ligue 1 | 66 | 29 | 43.9%+10.6 |
| Bundesliga | 64 | 28 | 43.8%+10.5 |
| Jupiler Pro League | 79 | 34 | 43%+9.7 |
| La Liga | 90 | 38 | 42.2%+8.9 |
| Allsvenskan | 88 | 36 | 40.9%+7.6 |
| League One | 96 | 39 | 40.6%+7.3 |
| Brazilian Série A | 101 | 41 | 40.6%+7.3 |
| Premier League | 215 | 84 | 39.1%+5.8 |
| Segunda División | 121 | 46 | 38%+4.7 |
| Super League 1 | 53 | 20 | 37.7%+4.4 |
| Ligue 2 | 55 | 20 | 36.4%+3.1 |
| Süper Lig | 65 | 23 | 35.4%+2.1 |
Recent AI Predictions
| Date | Match | 1X2 | AIC | O/U 1.5 | O/U 2.5 | O/U 3.5 | BTTS | AH Line | Actual | Result |
|---|---|---|---|---|---|---|---|---|---|---|
| 09 Jul 2026 | UEFA Europa Conference LeagueStjarnan vs Vikingur Gota | Home Win | 44% | — | Over 2.5 ✅ | — | — | -0.5 (Home) ✅ | Home Win (3-1) | ✅ |
| 09 Jul 2026 | UEFA Europa Conference LeagueFK Sarajevo vs Inter Turku | Draw | 46% | — | Over 2.5 ❌ | — | — | +0.0 (Away) | Draw (1-1) | ✅ |
| 09 Jul 2026 | UEFA Europa Conference LeagueDinamo Tirana vs FC Astana | Home Win | 43% | — | Over 2.5 ❌ | — | — | -0.5 (Home) ❌ | Away Win (0-1) | ❌ |
| 09 Jul 2026 | UEFA Europa Conference LeaguePetrovac vs FK Zalgiris Vilnius | Draw | 42% | — | Over 2.5 ✅ | — | — | +0.0 (Away) | Away Win (1-3) | ❌ |
| 09 Jul 2026 | UEFA Europa Conference LeaguePenybont vs FC Santa Coloma | Home Win | 43% | — | Over 2.5 ❌ | — | — | -0.5 (Home) ❌ | Away Win (0-1) | ❌ |
| 09 Jul 2026 | UEFA Europa Conference LeagueNSI Runavik vs Hamrun Spartans | Home Win | 48% | — | Over 2.5 ❌ | — | — | -0.5 (Home) ❌ | Draw (1-1) | ❌ |
| 09 Jul 2026 | UEFA Europa Conference LeagueGlentoran vs Rīgas FS | Home Win | 43% | — | Over 2.5 ✅ | — | — | -0.3 (Home) ❌ | Away Win (1-2) | ❌ |
| 09 Jul 2026 | UEFA Europa LeagueVojvodina vs Ferencvarosi TC | Home Win | 46% | — | Over 2.5 ✅ | — | — | -0.8 (Home) ❌ | Away Win (1-2) | ❌ |
| 09 Jul 2026 | UEFA Europa LeagueHNK Hajduk Split vs Žilina | Draw | 53% | — | Over 2.5 ❌ | — | — | +0.0 (Away) | Home Win (2-0) | ❌ |
| 09 Jul 2026 | UEFA Europa LeagueCSKA Sofia vs Derry City | Draw | 53% | — | Over 2.5 ✅ | — | — | +0.0 (Away) | Home Win (3-2) | ❌ |
| 09 Jul 2026 | UEFA Europa Conference LeagueVllaznia Shkodër vs Malisheva | Away Win | 40% | — | Over 2.5 ✅ | — | — | +0.0 (Away) | Home Win (2-1) | ❌ |
| 09 Jul 2026 | UEFA Europa Conference LeagueEuropa vs Shkendija | Home Win | 41% | — | Over 2.5 ✅ | — | — | -1.0 (Home) ❌ | Away Win (0-5) | ❌ |
| 09 Jul 2026 | UEFA Europa Conference LeagueCaernarfon Town vs FC Levadia Tallinn | Away Win | 37% | — | Over 2.5 ✅ | — | — | -0.3 (Home) ❌ | Away Win (0-5) | ✅ |
| 09 Jul 2026 | UEFA Europa Conference LeagueUS Mondorf-les-bains vs Dinamo Tbilisi | Home Win | 66% | — | Over 2.5 ✅ | — | — | -0.8 (Home) ❌ | Away Win (1-2) | ❌ |
| 09 Jul 2026 | UEFA Europa LeagueSheriff Tiraspol vs Aluminij | Away Win | 60% | — | Over 2.5 ❌ | — | — | -0.3 (Home) ❌ | Draw (0-0) | ❌ |
Ensemble Model
Our v4 GradientBoosting model — the AI behind every tip we publish — currently scores 47.6% accuracy on 925 settled matches since deployment. This is in line with the inherent difficulty of 3-way football outcomes (random = 33.3%). Accuracy will stabilise as more data accumulates.
Ensemble Score Distribution & Accuracy
Model Calibration
Does a higher confidence score actually mean a more accurate prediction? This chart answers that. We group every settled prediction by the internal confidence score the model assigned, then show the real win-rate for each group. A rising staircase is what you want to see, it means the model knows when it is more likely to be right.
Each bar groups model predictions by internal confidence score (0–100). The height shows how often those predictions were actually correct on settled matches. A rising pattern means the model’s confidence is meaningful: higher scores genuinely correspond to more accurate predictions. Data covers our core leagues where the model has proven signal. Hover for sample sizes. This is the model’s internal ranking score across every match it analyses — not the per-tip AI Confidence shown on the tips and homepage.
Model accuracy is calculated on settled matches only. The current model uses form, goals average and H2H data as input features. Accuracy improves as more live data is collected.
More transparency: Tip results & track record · How accurate are AI predictions?