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 | 71.5 | +2.8%53% vs 50.2% mkt | 14% | +9.8% | 316 | |
| 2 | 63.5 | +2.1%53% vs 50.9% mkt | 10% | +12.8% | 339 | |
| 3 | 56.2 | +1.2%51% vs 49.8% mkt | 11% | +4.8% | 324 | |
| 4 | 55.6 | +0.1%51% vs 50.9% mkt | 12% | +4.2% | 339 | |
| 5 | 58.2 | 0.0%51% vs 51.0% mkt | 13% | +5.0% | 340 | |
| 6 | 55.0 | 0.0%51% vs 51.0% mkt | 12% | +3.9% | 340 | |
| 7 | 54.9 | 0.0%51% vs 51.0% mkt | 12% | +3.8% | 340 | |
| 8 | 57.3 | −0.2%54% vs 54.2% mkt | 12% | +8.3% | 433 | |
| 9 | 50.6 | −0.8%49% vs 49.8% mkt | 12% | +1.1% | 239 | |
| 10 | 51.6 | −1.2%53% vs 54.2% mkt | 13% | +2.8% | 443 | |
| 11 | 46.9 | −1.2%53% vs 54.2% mkt | 11% | +2.3% | 444 | |
| 12 | 46.7 | −1.6%49% vs 50.6% mkt | 11% | +1.6% | 259 | |
| 13 | 48.7 | −1.8%49% vs 50.8% mkt | 10% | +6.0% | 336 |
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 →