2026 NFL Week 1 Digest
All 16 games of Week 1 in the 2026 NFL season are now graded. Before kickoff our model picked 11 of the 16 winners, one fewer than the market favourite. THE PLAY, our one headline call for each game, won 7 and lost 9, a gain of $1.45 on $80 staked. During play the live engine's win probability scored a Brier of 0.140 over 13,510 moments, level with the incumbent model at 0.140 and ahead of the market at 0.158, where lower is better.
Pregame calls
Before kickoff the model picked a winner in 16 games, and those picks won 11 and lost 5. The market favourite, the side the market priced above 50%, won 12 and lost 4. Against the spread our side won 4, lost 11 and pushed 1, and on totals it won 10 and lost 6. Scored as probabilities, our pregame win chances had a Brier score of 0.238 against 0.211 for the market, where lower is better, so the market's were the closer forecasts this week.
THE PLAY and the $5 ledger
THE PLAY is the one headline call we publish for each game, and the $5 ledger stakes every pregame pick at $5 at the price it showed. THE PLAY won 7 and lost 9 across 16 games, winning 43.8% of the time at an average price of 44.6 cents, a gain of $1.45 on $80 staked. The largest single return was a gain of $18.81 on Ja'Marr Chase under 50 rec yds in TB at CIN, priced at 21 cents.
Every pick in the ledger together, 3,978 of them, won 43.3% of the time at an average price of 45.5 cents and finished with a loss of $120.37 on $19,890 staked. By market, player props finished with a loss of $662.80, spreads a gain of $384.72, totals a gain of $111.12 and moneylines a gain of $46.59.
The live engine
During play the live engine reprices every game about every ten seconds. Across 13,510 in-game moments in 16 games its win probability scored a Brier of 0.140. The incumbent, a simpler baseline model, scored 0.140 and the market scored 0.158 on the 12,512 moments that had a market price. Lower is better.
| Quarter | Moments | Engine | Incumbent | Market |
|---|---|---|---|---|
| Q1 | 2,502 | 0.190 | 0.192 | 0.202 |
| Q2 | 4,637 | 0.172 | 0.172 | 0.200 |
| Q3 | 2,861 | 0.136 | 0.139 | 0.164 |
| Q4 | 3,510 | 0.065 | 0.062 | 0.069 |
| Game | 13,510 | 0.140 | 0.140 | 0.158 |
Overtime is left out of this grade, so 85 overtime moments were set aside.
In-game edges and hot plays
An in-game edge is a stretch where the engine disagreed with the market price on the same side, counted once at the first price it showed. Across 15 games the engine logged 1,132 edges, and the 1,118 that could be graded won 50.9% of the time at an average price of 53.1 cents. Held to the final they returned a loss of 3.5 cents per $1 contract after fees, and sold 15 minutes after entry they returned a loss of 5.8 cents.
Hot plays are the edges that come right after a score, a turnover or a big play. Across 15 games the engine logged 578 hot plays, and they won 55.7% of the time at an average price of 54.8 cents. Held to the final they returned a loss of 0.4 cents per $1 contract after fees, and sold 15 minutes after entry they returned a loss of 5.6 cents.
In DEN at KC, no market price reached the live engine during this game, so there was no edge to grade.
Live player props
Live prop projections were graded in 14 games, 410 props in all. At kickoff the average projection missed the final stat by 17.1, measured in each stat's own units, and by the end of the third quarter the average miss was 8.0. The Brier score of the projected chance of going over the line was 0.271 at kickoff and 0.118 at the end of the third quarter. The market's own chance scored 0.246 on the 26 props with a market price.
- Receiving yards, 150 props: an average miss of 22.6 yards at kickoff and 10.5 yards at the end of the third quarter.
- Receptions, 149 props: an average miss of 1.6 catches at kickoff and 0.8 catches at the end of the third quarter.
- Rushing yards, 83 props: an average miss of 18.8 yards at kickoff and 8.6 yards at the end of the third quarter.
- Passing yards, 28 props: an average miss of 65.6 yards at kickoff and 32.6 yards at the end of the third quarter.
The best and worst calls
The best call is the pregame winner pick where we disagreed most with the market and were right, and the worst is the one where we disagreed most and were wrong. The best came in DAL at NYG: we gave NYG a 56% chance to win when the market gave them 42%, and NYG won 28 to 20. The worst came in BAL at IND: we gave IND a 61% chance to win when the market gave them 42%, and BAL won 41 to 23.
Every game
| Game | Final | Our winner | Spread | Total | THE PLAY | $5 result |
|---|---|---|---|---|---|---|
| NE at SEA | SEA 13, NE 10 | SEA 59%, won | NE +3, push | Under 44.5, won | Under 44.5, won | +$4.55 |
| SF at LA | SF 27, LA 7 | LA 68%, lost | LA −3.5, lost | Over 47.5, lost | Over 51.5, lost | −$5.00 |
| ATL at PIT | PIT 20, ATL 13 | PIT 57%, won | ATL +6.5, lost | Over 40.5, lost | Jahan Dotson 2+ receptions, lost | −$5.00 |
| BAL at IND | BAL 41, IND 23 | IND 61%, lost | IND +3, lost | Over 48.5, won | IND by 5.0+, lost | −$5.00 |
| BUF at HOU | BUF 36, HOU 31 | BUF 53%, won | HOU +1.5, lost | Over 44.5, won | DJ Moore 4+ receptions, won | +$4.09 |
| CHI at CAR | CHI 59, CAR 37 | CHI 54%, won | CAR +3, lost | Over 47.5, won | Tommy Tremble 15+ rec yds, won | +$7.20 |
| CLE at JAX | JAX 34, CLE 10 | JAX 67%, won | CLE +8.5, lost | Over 40.5, won | Deshaun Watson under 175 pass yds, lost | −$5.00 |
| NO at DET | DET 31, NO 30 (OT) | DET 67%, won | NO +7, won | Under 49.5, lost | Isaac TeSlaa 15+ rec yds, lost | −$5.00 |
| NYJ at TEN | NYJ 23, TEN 10 | TEN 70%, lost | TEN −1.5, lost | Over 39.5, lost | Over 47.5, lost | −$5.00 |
| TB at CIN | CIN 33, TB 27 | CIN 59%, won | TB +3.5, lost | Over 50.5, won | Ja'Marr Chase under 50 rec yds, won | +$18.81 |
| ARI at LAC | ARI 26, LAC 14 | LAC 67%, lost | ARI +8.5, won | Under 47.5, won | Trey McBride 6+ receptions, won | +$3.62 |
| GB at MIN | MIN 39, GB 22 | MIN 65%, won | MIN −1.5, won | Over 46.5, won | Kyler Murray under 225 pass yds, won | +$3.93 |
| MIA at LV | LV 27, MIA 13 | LV 56%, won | MIA +3, lost | Over 40.5, lost | Mike Washington Jr. under 30 rush yds, lost | −$5.00 |
| WAS at PHI | PHI 24, WAS 22 | PHI 70%, won | PHI −6, lost | Over 43.5, won | Over 47.5, lost | −$5.00 |
| DAL at NYG | NYG 28, DAL 20 | NYG 56%, won | NYG +3, won | Over 47.5, won | Over 51.5, lost | −$5.00 |
| DEN at KC | KC 31, DEN 10 | DEN 51%, lost | DEN +2.5, lost | Over 42.5, lost | Evan Engram 3+ receptions, won | +$4.26 |
How to read this
A win rate means little without the price paid, so every rate here sits beside the average price, and a price of 53 cents means the market put the chance at about 53%. A Brier score measures how far a probability sat from what happened, from 0 for a perfect forecast to 1 for a certain one that was wrong, so lower is better. In-game returns are per $1 contract after fees.
Every game, every edge and every prop behind these numbers is on the NFL results page, graded as each game finishes.