Public results · auto-settled · no betting advice
Splits our home-side picks from our away-side picks. If one side wins markedly more than the other, the model is mis-pricing home-court advantage.
Recent trend
| League | Model | Win rate | Hits / attempts | Settled | Avg confidence |
|---|---|---|---|---|---|
| MLB | elo-v1 | Sample too small (n=15) | 5 / 8 | 15 | 54.2% |
| NHL | elo-v1 | Sample too small (n=9) | 8 / 9 | 9 | 57.1% |
| LOL | lol-elo-v1 | Sample too small (n=3) | 2 / 3 | 3 | 64.4% |
| NBA | elo-v1 | Sample too small (n=2) | 2 / 2 | 2 | 63.6% |
| League | Model | MAE | Bias | Scored | Avg confidence |
|---|---|---|---|---|---|
| EUROPA-LEAGUE | europa-league-elo-v1 | Sample too small (n=0) | — | 0 | 54.5% |
| MLB | score-model-v1 | Sample too small (n=0) | — | 0 | 54.9% |
| NBA | score-model-v1 | Sample too small (n=0) | — | 0 | 53.1% |
| NHL | score-model-v1 | Sample too small (n=0) | — | 0 | 51.9% |
Monthly trend
| League | Model | Win rate | Hits / attempts | Settled | Avg confidence |
|---|---|---|---|---|---|
| MLB | elo-v1 | 58.3% | 119 / 204 | 212 | 54.0% |
| NHL | elo-v1 | Sample too small (n=9) | 8 / 9 | 9 | 57.1% |
| LOL | lol-elo-v1 | Sample too small (n=3) | 2 / 3 | 3 | 64.4% |
| NBA | elo-v1 | Sample too small (n=2) | 2 / 2 | 2 | 63.6% |
| League | Model | MAE | Bias | Scored | Avg confidence |
|---|---|---|---|---|---|
| EUROPA-LEAGUE | europa-league-elo-v1 | Sample too small (n=0) | — | 0 | 54.5% |
| MLB | score-model-v1 | Sample too small (n=0) | — | 0 | 54.9% |
| NBA | score-model-v1 | Sample too small (n=0) | — | 0 | 53.1% |
| NHL | score-model-v1 | Sample too small (n=0) | — | 0 | 51.9% |
All-time
| League | Model | Win rate | Hits / attempts | Settled | Avg confidence |
|---|---|---|---|---|---|
| MLB | elo-v1 | 54.4% | 1016 / 1868 | 1887 | 53.8% |
| NBA | elo-v1 | 44.4% | 12 / 27 | 37 | 61.4% |
| NHL | elo-v1 | Sample too small (n=9) | 8 / 9 | 9 | 57.1% |
| LOL | lol-elo-v1 | Sample too small (n=3) | 2 / 3 | 3 | 64.4% |
| League | Model | MAE | Bias | Scored | Avg confidence |
|---|---|---|---|---|---|
| EUROPA-LEAGUE | europa-league-elo-v1 | Sample too small (n=0) | — | 0 | 54.5% |
| MLB | score-model-v1 | Sample too small (n=0) | — | 0 | 54.9% |
| NBA | score-model-v1 | Sample too small (n=0) | — | 0 | 53.1% |
| NHL | score-model-v1 | Sample too small (n=0) | — | 0 | 51.9% |
Brier is a three-class normalized score (0–1, lower is better); not yet benchmarked against a favourite baseline or market odds.
| League | Model | Win rate | Hits / attempts | Brier | Settled |
|---|---|---|---|---|---|
| FIFA World Cup | wc-elo-v1 | 62.0% | 57 / 92 | 0.2567 | 92 |
| LaLiga | laliga-elo-v1 | 52.2% | 36 / 69 | 0.2777 | 69 |
| Ligue 1 | ligue1-elo-v1 | 55.6% | 30 / 54 | 0.3040 | 54 |
| Premier League | epl-elo-v1 | 40.0% | 20 / 50 | 0.3315 | 50 |
| Serie A | seriea-elo-v1 | 56.0% | 28 / 50 | 0.2844 | 50 |
| Bundesliga | bundesliga-elo-v1 | 53.3% | 24 / 45 | 0.2890 | 45 |
| UEFA Europa League | europa-league-elo-v1 | Sample too small (n=18) | 12 / 18 | 0.2663 | 18 |
Spread Brier uses the model's cover probability (0.25 ≈ coin flip, lower is better). Same auto-settled data as above, published unfiltered.
| League | Model | Win rate | Hits / attempts | Brier | Avg cover prob | Settled |
|---|---|---|---|---|---|---|
| EUROPA-LEAGUE | europa-league-elo-v1 | Sample too small (n=18) | 7 / 18 | — | — | 18 |
| NHL | score-model-v1 | Sample too small (n=9) | 7 / 9 | — | — | 9 |
| NBA | score-model-v1 | Sample too small (n=2) | 1 / 2 | — | — | 2 |
| MLB | score-model-v1 | Sample too small (n=1) | 0 / 1 | — | — | 1 |
| League | Model | Win rate | Hits / attempts | Settled | Avg confidence |
|---|---|---|---|---|---|
| NBA | score-model-v1 | Sample too small (n=2) | 2 / 2 | 2 | 52.2% |
| League | Model | Market | MAE | Bias | Scored |
|---|---|---|---|---|---|
| EUROPA-LEAGUE | europa-league-elo-v1 | First-half total | Sample too small (n=0) | — | 0 |
| NBA | score-model-v1 | First-half total | Sample too small (n=0) | — | 0 |
| EUROPA-LEAGUE | europa-league-elo-v1 | Away team total | Sample too small (n=0) | — | 0 |
| NBA | score-model-v1 | Away team total | Sample too small (n=0) | — | 0 |
| NHL | score-model-v1 | Away team total | Sample too small (n=0) | — | 0 |
| EUROPA-LEAGUE | europa-league-elo-v1 | Home team total | Sample too small (n=0) | — | 0 |
| NBA | score-model-v1 | Home team total | Sample too small (n=0) | — | 0 |
| NHL | score-model-v1 | Home team total | Sample too small (n=0) | — | 0 |
Perfect calibration
When we say '70% to win,' how often do those teams actually win? Points hugging the dashed line mean the model's confidence is honest. Blue = beats prediction (under-confident), red = worse than prediction (over-confident), green = within ±5%.
Moneyline model · 1907 settled games (voids excluded)