A record of picks tells you what won. Calibration tells you whether the probabilities meant anything: when we say 60%, does it happen 60% of the time? Below, every settled prediction, scored two ways — the sharp market (devigged) and our own model — with the uncomfortable comparison in plain sight.
Our model (Elo + form): 0.617
Our model (Elo + form): 1.028
Our model (Elo + form): 0.4pp
Each point is a 10-point probability band (min. 30 observations). The closer to the diagonal, the better calibrated. Every match contributes its three outcomes.
| Band | Sharp market (devigged) — Predicted (avg) | Observed | Obs. | Our model (Elo + form) — Predicted (avg) | Observed | Obs. |
|---|---|---|---|---|---|---|
| 0–10% | 7.4% | 5.6% | 270 | 7.5% | 7.1% | 112 |
| 10–20% | 16.2% | 17.5% | 1657 | 16.4% | 16.8% | 1056 |
| 20–30% | 25.3% | 25.1% | 5261 | 26% | 25.9% | 6205 |
| 30–40% | 34.3% | 33.6% | 2748 | 34.7% | 34.6% | 2646 |
| 40–50% | 44.8% | 43.9% | 1680 | 44.8% | 43.9% | 2047 |
| 50–60% | 54.6% | 56.2% | 1077 | 54.3% | 56% | 1024 |
| 60–70% | 64.4% | 63.9% | 598 | 63.9% | 64.3% | 381 |
| 70–80% | 74.6% | 79.2% | 240 | 74.1% | 75.2% | 105 |
| 80–90% | 83.7% | 86.1% | 72 | 83% | 88.2% | 34 |
Lower Brier and log-loss are better; calibration error is the observation-weighted average gap between predicted and observed. The honest headline: the devigged sharp market is better calibrated than our model — which is precisely why this site prices everything against the market instead of selling you model predictions. Methodology: probabilities as displayed at logging time, no retro-fitting; outcomes from official results.
Full methodology →