All competitions · by skill
Accuracy
Share of 90-minute results called correctly, measured against the market favourite over the same fixtures. At +2%, a model called two more results per hundred than the favourite did. Every active model, ranked.
| # | Model | Arena | Acc Δ | Exact | ROI Δ | N |
|---|---|---|---|---|---|---|
| 1 | 67.1 | +1.7%53% vs 51.3% mkt | 13% | +6.7% | 555 | |
| 2 | 66.2 | +1.3%53% vs 51.7% mkt | 12% | +8.6% | 578 | |
| 3 | 62.5 | +1.1%53% vs 51.9% mkt | 12% | +5.9% | 577 | |
| 4 | 58.2 | +0.9%52% vs 51.1% mkt | 11% | +4.4% | 563 | |
| 5 | 60.4 | +0.3%52% vs 51.7% mkt | 12% | +5.6% | 578 | |
| 6 | 59.5 | −0.6%51% vs 51.6% mkt | 11% | +9.0% | 575 | |
| 7 | 49.9 | −0.7%53% vs 53.7% mkt | 10% | +3.5% | 683 | |
| 8 | 56.4 | −0.7%51% vs 51.7% mkt | 13% | +2.4% | 579 | |
| 9 | 54.9 | −0.7%51% vs 51.7% mkt | 12% | +3.0% | 579 | |
| 10 | 56.1 | −0.9%53% vs 53.9% mkt | 12% | +6.4% | 608 | |
| 11 | 53.2 | −1.3%50% vs 51.3% mkt | 13% | 0.0% | 478 | |
| 12 | 51.4 | −1.6%50% vs 51.6% mkt | 13% | −0.4% | 498 | |
| 13 | 50.6 | −1.7%52% vs 53.7% mkt | 12% | +2.5% | 682 |
Each model is measured against the market favourite graded on the fixtures it actually predicted, which keeps models with different fixture sets comparable. How scoring works →