2026 NFL Week 6 Digest
All 14 games of Week 6 in the 2026 NFL season are now graded. Before kickoff our model picked 8 of the 14 winners, one fewer than the market favorite. THE PLAY, our one headline call for each game, won 6 and lost 8, a loss of $9.34 on $70 staked. During play the live engine's win probability scored a Brier of 0.187 over 12,513 moments, ahead of the incumbent model at 0.194 and ahead of the market at 0.189, where lower is better.
Pregame calls
Before kickoff the model picked a winner in 14 games, and those picks won 8 and lost 6. The market favorite, the side the market priced above 50%, won 9 and lost 5. Against the spread our side won 7 and lost 7, and on totals it won 8 and lost 6. Scored as probabilities, our pregame win chances had a Brier score of 0.245 against 0.251 for the market, where lower is better, so ours 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 6 and lost 8 across 14 games, winning 42.9% of the time at an average price of 51.0 cents, a loss of $9.34 on $70 staked. The largest single return was a gain of $7.82 on CLE wins in BAL at CLE, priced at 39 cents.
Every pick in the ledger together, 4,023 of them, won 40.2% of the time at an average price of 40.6 cents and finished with a loss of $185.20 on $20,115 staked. By market, player props finished with a gain of $345.03, spreads a loss of $600.98, totals a gain of $5.43 and moneylines a gain of $65.31.
The live engine
During play the live engine reprices every game about every ten seconds. Across 12,513 in-game moments in 14 games its win probability scored a Brier of 0.187. The incumbent, a simpler baseline model, scored 0.194 and the market scored 0.189. Lower is better.
| Quarter | Moments | Engine | Incumbent | Market |
|---|---|---|---|---|
| Q1 | 2,217 | 0.238 | 0.247 | 0.243 |
| Q2 | 4,192 | 0.244 | 0.252 | 0.239 |
| Q3 | 2,457 | 0.177 | 0.186 | 0.186 |
| Q4 | 3,647 | 0.096 | 0.101 | 0.101 |
| Game | 12,513 | 0.187 | 0.194 | 0.189 |
Overtime is left out of this grade, so 155 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 14 games the engine logged 964 edges, and the 880 that could be graded won 52.2% of the time at an average price of 53.0 cents. Held to the final they returned a loss of 2.2 cents per $1 contract after fees, and sold 15 minutes after entry they returned a loss of 5.5 cents.
Hot plays are the edges that come right after a score, a turnover or a big play. Across 14 games the engine logged 498 hot plays, and the 474 that could be graded won 54.0% of the time at an average price of 53.3 cents. Held to the final they returned a loss of 0.6 cents per $1 contract after fees, and sold 15 minutes after entry they returned a loss of 5.5 cents.
Live player props
Live prop projections were graded in 14 games, 418 props in all. At kickoff the average projection missed the final stat by 14.0, measured in each stat's own units, and by the end of the third quarter the average miss was 8.2. The Brier score of the projected chance of going over the line was 0.273 at kickoff and 0.126 at the end of the third quarter. The market's own chance scored 0.252 on the 363 props with a market price.
- Receiving yards, 154 props: an average miss of 18.3 yards at kickoff and 11.2 yards at the end of the third quarter.
- Receptions, 151 props: an average miss of 1.7 catches at kickoff and 0.9 catches at the end of the third quarter.
- Rushing yards, 85 props: an average miss of 16.4 yards at kickoff and 6.1 yards at the end of the third quarter.
- Passing yards, 28 props: an average miss of 49.9 yards at kickoff and 37.9 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 BAL at CLE: we gave CLE a 58% chance to win when the market gave them 41%, and CLE won 13 to 10. The worst came in TEN at IND: we gave IND a 78% chance to win when the market gave them 67%, and TEN won 26 to 20.
Every game
| Game | Final | Our winner | Spread | Total | THE PLAY | $5 result |
|---|---|---|---|---|---|---|
| SEA at DEN | DEN 17, SEA 14 (OT) | SEA 63%, lost | SEA −2.5, lost | Over 40.5, lost | NO: DEN by 2.0+, lost | −$5.00 |
| HOU at JAX | HOU 34, JAX 31 | JAX 51%, lost | HOU +2.5, won | Under 42.5, lost | Under 42.5, lost | −$5.00 |
| BAL at CLE | CLE 13, BAL 10 | CLE 58%, won | CLE +3, won | Over 39.5, lost | CLE wins, won | +$7.82 |
| CAR at PHI | CAR 25, PHI 14 | CAR 62%, won | CAR −3, won | Over 39.5, lost | Over 39.5, lost | −$5.00 |
| CHI at ATL | CHI 31, ATL 23 | ATL 56%, lost | ATL +1.5, lost | Over 51.5, won | ATL ML, lost | −$5.00 |
| NO at NYG | NO 34, NYG 27 | NYG 55%, lost | NYG +1.5, lost | Over 46.5, won | NYG ML, lost | −$5.00 |
| NYJ at NE | NE 26, NYJ 19 | NE 74%, won | NE −7.5, lost | Over 43.5, won | NE by 8.0+, lost | −$5.00 |
| PIT at TB | PIT 26, TB 19 (OT) | PIT 65%, won | PIT −1.5, won | Over 38.5, won | NO: TB by 2.0+, won | +$3.62 |
| TEN at IND | TEN 26, IND 20 | IND 78%, lost | IND −6.5, lost | Over 43.5, won | Over 43.5, won | +$4.46 |
| ARI at LA | ARI 18, LA 16 | LA 82%, lost | LA −12.5, lost | Under 51.5, won | Under 51.5, won | +$4.55 |
| BUF at LV | BUF 33, LV 30 | BUF 62%, won | LV +5.5, won | Over 53.5, won | Over 53.5, won | +$5.00 |
| LAC at KC | KC 22, LAC 6 | KC 78%, won | KC −7.5, won | Under 41.5, won | KC by 8.0+, won | +$5.20 |
| DAL at GB | GB 23, DAL 13 | GB 66%, won | GB −1.5, won | Over 53.5, lost | Over 53.5, lost | −$5.00 |
| WAS at SF | SF 23, WAS 17 | SF 75%, won | SF −7.5, lost | Over 52.5, lost | Over 52.5, lost | −$5.00 |
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.