Every honest number TrueTail tracks, in one place, updating live from our own database - nothing here is a pick, and nothing here is hidden. If a model does not yet beat a baseline, this page says so.
Over 170 graded games, the game sim scores a Brier score of 0.2511 (lower is better). We do not yet beat always picking the home team (0.2488). We beat picking by season record (0.2566).
Sample: 170 games, 2026-07-06 to 2026-07-21.
WNBA v2 scores a Brier score of 0.2304 (lower is better). We beat always picking the home team (0.2592). We beat picking by season record (0.2351).
Sample: 196 games, 2026-05-08 to 2026-07-21.
Over graded props, the player sim scores a Brier score of 0.2012.
No backtest logged yet for the first-inning model - too early to claim anything.
Rolling 30-day window: 23 tails surfaced, 16 graded so far.
Early - n=16 graded. Not enough yet to draw a conclusion, shown honestly rather than hidden.
50.0% of graded tails beat the closing line, averaging -2.05% closing-line value (CLV).
This is a CLV record, not a win/loss record - beating the closing line is the honest leading indicator that a pick process is sharp; win/loss totals are graded separately per-slip in each member's own log, not aggregated here.
50% of graded slips with known provenance were graded automatically by the machine (closing-line grading), not by hand - over 2 graded slips network-wide.
Our own originated lines are being paper-tracked against the close - this section unlocks at n>=100 graded disagreements. No numbers here yet, on purpose.
Curious how any of this is computed? Read the methodology. Nothing on this page is a pick, and TrueTail accepts no wagers.