the yahngorithmModel grades · 2026
Every spread model and every flag, graded against the closing line on each final game — the hindsight-free record. Break-even is 52.4%. Backtests say expect ~50%; see the guide. 182 games graded so far.
ATS = record betting the side the model favored over the market (a win = that side covered the close). Win % is of decided bets; 52.4% is break-even at −110. Edge ≥ 2 = only games the model was ≥ 2 pts off the close. MAE = average miss between the predicted and actual final margin, in points — with the closing line's own MAE on the same games below it. Lower is better; green = the model beat the market at raw prediction. (Beating the market on MAE is a different thing from beating it ATS.)
Spread models vs. the close
The closing line missed the final margin by 12.5 points on average across these 182 games — that's the bar.
| Model | ATS | Win % | Edge ≥ 2 | MAE |
|---|---|---|---|---|
| SP+ model | 88–92–2 | 48.9% | 59–67 | 13.5 close 12.5 |
| Yahn model | 89–89–2 | 50.0% | 61–61 | 13.3 close 12.5 |
Flags — betting the implied side
| Flag | ATS | Win % |
|---|---|---|
| bad_spot | 2–2 | 50.0% |
| letdown | 4–3 | 57.1% |
| lookahead | 7–13 | 35.0% |
| revenge | 9–6 | 60.0% |
| rlm | 5–2 | 71.4% |
| short_week | 3–4 | 42.9% |
| steam | 15–4 | 78.9% |
| travel | 11–9 | 55.0% |
A model "wins" a game when the side it favored over the market went on to cover the closing number. Small samples early — one week is noise. Watch the trend across the season, not any single number.