NFL Picks for Week 1: The Model Went 10-5
By Verdexed Analytics
16 NFL games on Week 1. The model went 10-5 on the week, with 1 pick voided. Season to date through September 14: 10-5 (66.7%), Brier 0.222.
Every pick below is exactly as it was logged before kickoff that morning: the served probability (the model blended with the market), the model on its own, the market's vig-free number, then the final. Nothing is rewritten after the fact, and a voided pick stays on the board with its reason. The live record, the hit rate by confidence band and every void are on the NFL accuracy page.
The board
| Date | Game | Pick | Verdexed | Model alone | Market | Final | Result |
|---|---|---|---|---|---|---|---|
| September 9 | NE at SEA | SEA | 55% | 52% | 60% | SEA 13-10 | Hit |
| September 10 | SF at LAR | LAR | 55% | 49.9% | 63% | SF 27-7 | Miss |
| September 13 | GB at MIN | MIN | 70% | 78% | 54% | MIN 39-22 | Hit |
| September 13 | ARI at LAC | LAC | 68% | 61% | 80% | ARI 26-14 | Miss |
| September 13 | BAL at IND | BAL | 67% | 70% | 61% | BAL 41-23 | Hit |
| September 13 | DAL at NYG | DAL | 66% | 69% | 60% | NYG 28-20 | Miss |
| September 13 | CLE at JAX | JAX | 65% | 57% | 79% | JAX 34-10 | Hit |
| September 13 | WSH at PHI | PHI | 65% | 62% | 70% | PHI 24-22 | Hit |
| September 13 | CHI at CAR | CHI | 63% | 64% | 61% | CHI 59-37 | Hit |
| September 13 | TB at CIN | CIN | 59% | 56% | 64% | CIN 33-27 | Hit |
| September 13 | BUF at HOU | BUF | 58% | 63% | 50.4% | BUF 36-31 | Hit |
| September 13 | MIA at LV | MIA | 58% | 69% | 40% | LV 27-13 | Void (Model ran on the 2025 Dolphins, blind to the quarterback change (Malik Willis starting for Tua Tagovailoa); ruled invalid and flagged before kickoff on Sep 13, 2026 (11:20 AM ET, kickoff 4:05 PM). The owner's own pick was LV.) |
| September 13 | ATL at PIT | PIT | 57% | 49.7% | 72% | PIT 20-13 | Hit |
| September 13 | NYJ at TEN | TEN | 57% | 60% | 52% | NYJ 23-10 | Miss |
| September 13 | NO at DET | DET | 57% | 47% | 73% | DET 31-30 | Hit |
| September 14 | DEN at KC | DEN | 55% | 61% | 46% | KC 31-10 | Miss |
Where the model and the market split
MIA at LV: the model took MIA (69%), the market LV; the served pick was MIA and voided. NO at DET: the model took NO (53%), the market DET; the served pick was DET and the pick hit. ATL at PIT: the model took ATL (50.3%), the market PIT; the served pick was PIT and the pick hit. DEN at KC: the model took DEN (61%), the market KC; the served pick was DEN and the pick missed. SF at LAR: the model took SF (50.1%), the market LAR; the served pick was LAR and the pick missed. MIN over GB: model 78%, market 54%, a 24-point gap; the pick hit.
The firmest calls
The firmest calls: MIN 70% over GB (hit), LAC 68% over ARI (miss), BAL 67% over IND (hit).
Season to date
Through September 14: 10-5 (66.7%) on graded regular-season picks since September 1, Brier score 0.222. Picks at 60% or better went 5-2.
Responsible play
This is model output, not betting advice. Verdexed publishes its model's probabilities and edges for informational and entertainment purposes only. Nothing here is a recommendation to place a wager, and no outcome is guaranteed, even the model's highest-confidence picks lose regularly.
You must be of legal betting age in your jurisdiction and located where sports wagering is legal to bet. Sports betting is not available everywhere; know and follow the laws where you are. Never bet more than you can afford to lose, and never chase losses.
If gambling is affecting you or someone you know, help is available. In the US, call or text 1-800-GAMBLER (1-800-426-2537), or visit ncpgambling.org. Please play responsibly.