New here? Get a 7-day free trial.Full access to every number and matchup. Then $15/mo or $110/yr, cancel anytime.Start free trial →
How our NBA game model's projected score has graded against the market and the final result: straight-up winners, against the spread, and totals over/under.
Propaholics NBA model track record: every game graded three ways, straight-up winner, against the spread, and total over/under, plus how far the projected score landed from the final. Only live picks made before tip-off count, starting with opening night, and the record is shown honestly, wins and losses.
1 game. Average projection error: 9.3 pts on the margin, — pts on the total. Pushes are excluded from win %.
| Date | Matchup | Final | Proj | Winner | Spread | Total |
|---|---|---|---|---|---|---|
| Oct 20, 26 | BOS @ DET | 113-121 | — | BOS✗ | DET +1.5✓ | Over 220.5✓ |
The cards at the top show the model's straight-up winner record, its against-the-spread record, and its over/under record, plus the average error between the projected and actual score. It covers every game the model has called live this season, and grows every game night.
The spread and total posted when the pick was last made before tip-off, and the actual final score. The winner pick is graded straight up, the spread pick against that spread, and the total pick against that total, with pushes excluded from the win percentage.
It is a second opinion, not a market-beater. Beating the spread and the total is the hardest benchmark there is, and the record here is shown honestly so you can judge it for yourself.
With opening night of the 2026-27 season. Only picks made live before each game count, nothing is filled in after the fact, and each game is graded once its final score is in.