AI Predictions

Compare 29 open-source AI models predicting football matches across 17 competitions.

Quick Access

MatchesLeaderboardMethodologyBlogHome

European Competitions

🏆UEFA Champions League🏅UEFA Europa League💎UEFA Conference League

Domestic & International

🦁Premier League🐂La Liga⚽Bundesliga⚽Serie A🥖Ligue 1🌷Eredivisie🌙Turkish Super Lig🌍FIFA World Cup🇪🇺UEFA Euro🌐UEFA Nations League🏆Copa America🦁Africa Cup of Nations🌍World Cup Qualifiers - Europe🌎World Cup Qualifiers - South America

© 2026 AI Football Predictions. All rights reserved.

Built with Next.js, Tailwind CSS, and shadcn/ui

AI Predictions
HomeMatchesLeaderboardBlog
Methodology

How We Calculate Accuracy

Our methodology for measuring AI prediction performance and ranking models.

Tendency Accuracy Formula

We measure how often a model correctly predicts the match outcome (home win, draw, or away win).

Formula

Accuracy = (Correct Tendencies / Scored Predictions) × 100

Correct Tendencies

Predictions where the model earned tendency points (correctly predicted home win, draw, or away win)

Scored Predictions

Total predictions for matches that have finished and been scored (excludes pending/cancelled matches)

Technical Implementation

We use tendencyPoints > 0 as the correctness check. This ensures only genuinely correct predictions count, as the Kicktipp system awards points only when the predicted outcome matches the actual result.

What Counts as Correct?

Correct Tendency Predictions

  • ✓Home Win: Model predicted home team wins, and home team won
  • ✓Draw: Model predicted a draw, and match ended in a draw
  • ✓Away Win: Model predicted away team wins, and away team won

These predictions earn tendency points (2-6 points) based on the Kicktipp quota system, which rewards rarer correct predictions with more points.

NOT Counted in Accuracy

  • ✗Wrong Tendencies: Predicted home win but away team won (earns 0 tendency points)
  • −Pending Predictions: Matches that haven't been played yet
  • −Voided Predictions: Matches that were cancelled or postponed

Note: Exact score accuracy is tracked separately. Accuracy percentage focuses solely on outcome prediction (tendency), not exact scoreline.

Example Calculations

Model A Performance

Total predictions made:150
Matches scored:150
Correct tendencies (earned points):75
Wrong tendencies (0 points):75
Tendency Accuracy:50.0%

Calculation: (75 correct / 150 scored) × 100 = 50.0%

Model B Performance

Total predictions made:160
Matches scored:145 (15 pending)
Correct tendencies (earned points):65
Wrong tendencies (0 points):80
Tendency Accuracy:44.8%

Calculation: (65 correct / 145 scored) × 100 = 44.8% (pending matches excluded)

Why Tendency Accuracy Matters

Football prediction is inherently difficult. Historical data shows that professional bookmakers, with access to vast data and sophisticated models, achieve around 50-55% accuracy on outcome prediction.

Our accuracy metric gives you a true picture of model performance. If a model shows 52% tendency accuracy, it genuinely predicts the correct match outcome 52% of the time - better than random chance (33.3% with three outcomes: home/draw/away).

Combined with the Kicktipp quota system (which rewards rare correct predictions), this creates a realistic and transparent benchmark for comparing AI models.

Learn More

How Scoring WorksView Leaderboard
HomeMatchesLeaderboardBlog