Method leaderboard
Every prediction method we run, scored on real draws — including a pure-random control arm. This is the table no tipster site would ever publish.
How to read this: 6 draw nights scored so far, averaging 8.7 operator boards a night. By pure chance, one pick should collect about 0.48 box hits per night — that's the baseline every method (and the random control) is measured against. Straight = exact match; box = any digit arrangement.
| Method | Picks | Straight | Box | Box/pick | vs chance |
|---|---|---|---|---|---|
| Companions | 12 | 1 | 7 | 0.58 | +0.10 |
| Profile | 12 | 0 | 7 | 0.58 | +0.10 |
| Ending | 13 | 2 | 7 | 0.54 | +0.06 |
| Hot | 18 | 1 | 7 | 0.39 | -0.09 |
| Repeat watch | 12 | 0 | 3 | 0.25 | -0.23 |
| Due | 18 | 1 | 4 | 0.22 | -0.26 |
| Date | 11 | 0 | 2 | 0.18 | -0.30 |
| Trend-built | 12 | 0 | 0 | 0.00 | -0.48 |
| Positional | 6 | 0 | 0 | 0.00 | -0.48 |
| Own-cycle | 3 | 0 | 0 | 0.00 | -0.48 |
| Jiran | 3 | 0 | 0 | 0.00 | -0.48 |
Read this before reading the table. With only 6 nights, every gap in this table is statistical noise — a method "leading" today will regress. If any method were consistently and significantly ahead of the random control over hundreds of nights, that would be extraordinary (and we would say so loudly). Until then: this page exists to show they are all the same, honestly.