2026 NFL Week 5 Digest
All 15 games of Week 5 in the 2026 NFL season are now graded. Before kickoff our model picked 8 of the 15 winners, one fewer than the market favorite. THE PLAY, our one headline call for each game, won 8 and lost 7, a gain of $1.91 on $75 staked. During play the live engine's win probability scored a Brier of 0.178 over 12,865 moments, ahead of the incumbent model at 0.182 and behind the market at 0.172, where lower is better.
Pregame calls
Before kickoff the model picked a winner in 15 games, and those picks won 8 and lost 7. The market favorite, the side the market priced above 50%, won 9 and lost 5. Against the spread our side won 7, lost 7 and pushed 1, and on totals it won 6 and lost 9. Scored as probabilities, our pregame win chances had a Brier score of 0.214 against 0.209 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 8 and lost 7 across 15 games, winning 53.3% of the time at an average price of 51.4 cents, a gain of $1.91 on $75 staked. The largest single return was a gain of $5.20 on NE by 4.0+ in LV at NE, priced at 49 cents.
Every pick in the ledger together, 4,056 of them, won 42.0% of the time at an average price of 41.7 cents and finished with a gain of $835.78 on $20,280 staked. By market, player props finished with a gain of $688.22, spreads a gain of $332.23, totals a loss of $238.10 and moneylines a gain of $53.43.
The live engine
During play the live engine reprices every game about every ten seconds. Across 12,865 in-game moments in 15 games its win probability scored a Brier of 0.178. The incumbent, a simpler baseline model, scored 0.182 and the market scored 0.172. Lower is better.
| Quarter | Moments | Engine | Incumbent | Market |
|---|---|---|---|---|
| Q1 | 2,211 | 0.209 | 0.203 | 0.202 |
| Q2 | 4,436 | 0.196 | 0.197 | 0.195 |
| Q3 | 2,742 | 0.163 | 0.168 | 0.154 |
| Q4 | 3,476 | 0.149 | 0.160 | 0.137 |
| Game | 12,865 | 0.178 | 0.182 | 0.172 |
Overtime is left out of this grade, so 359 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 1,013 edges, and the 889 that could be graded won 49.0% of the time at an average price of 51.9 cents. Held to the final they returned a loss of 4.4 cents per $1 contract after fees, and sold 15 minutes after entry they returned a loss of 6.3 cents.
Hot plays are the edges that come right after a score, a turnover or a big play. Across 15 games the engine logged 547 hot plays, and the 505 that could be graded won 46.7% of the time at an average price of 52.4 cents. Held to the final they returned a loss of 6.9 cents per $1 contract after fees, and sold 15 minutes after entry they returned a loss of 5.9 cents.
Live player props
Live prop projections were graded in 15 games, 446 props in all. At kickoff the average projection missed the final stat by 16.4, measured in each stat's own units, and by the end of the third quarter the average miss was 8.5. The Brier score of the projected chance of going over the line was 0.258 at kickoff and 0.126 at the end of the third quarter. The market's own chance scored 0.239 on the 349 props with a market price.
- Receiving yards, 162 props: an average miss of 21.6 yards at kickoff and 10.5 yards at the end of the third quarter.
- Receptions, 159 props: an average miss of 1.5 catches at kickoff and 0.9 catches at the end of the third quarter.
- Rushing yards, 95 props: an average miss of 17.9 yards at kickoff and 9.3 yards at the end of the third quarter.
- Passing yards, 30 props: an average miss of 61.3 yards at kickoff and 36.0 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 CHI at GB: we gave GB a 58% chance to win when the market gave them 46%, and GB won 31 to 7. The worst came in CLE at NYJ: we gave CLE a 56% chance to win when the market gave them 43%, and NYJ won 17 to 12.
Every game
| Game | Final | Our winner | Spread | Total | THE PLAY | $5 result |
|---|---|---|---|---|---|---|
| TB at DAL | TB 24, DAL 16 | DAL 76%, lost | DAL −8.5, lost | Over 47.5, lost | DAL by 8.0+, lost | −$5.00 |
| PHI at JAX | JAX 19, PHI 17 | JAX 67%, won | PHI +7.5, won | Over 41.5, lost | Over 41.5, lost | −$5.00 |
| CHI at GB | GB 31, CHI 7 | GB 58%, won | GB +1.5, won | Under 47.5, won | GB ML, won | +$5.05 |
| CIN at MIA | CIN 31, MIA 24 | CIN 65%, won | MIA +7, push | Over 44.5, won | Over 44.5, won | +$4.46 |
| CLE at NYJ | NYJ 17, CLE 12 | CLE 56%, lost | CLE +2.5, lost | Over 38.5, lost | Over 38.5, lost | −$5.00 |
| HOU at TEN | HOU 26, TEN 3 | HOU 76%, won | HOU −6.5, won | Over 37.5, lost | Over 38.0, lost | −$5.00 |
| IND at PIT | PIT 34, IND 22 | IND 50%, lost | IND +3, lost | Over 41.5, won | NO: PIT by 3.0+, lost | −$5.00 |
| LV at NE | NE 45, LV 17 | NE 69%, won | NE −3.5, won | Under 45.5, lost | NE by 4.0+, won | +$5.20 |
| MIN at NO | MIN 23, NO 13 | MIN 61%, won | MIN −2.5, won | Over 41.5, lost | NO: NO by 2.0+, won | +$3.47 |
| NYG at WAS | WAS 27, NYG 27 (OT) | WAS 61%, lost | WAS −3.5, lost | Over 41.5, won | Over 41.5, won | +$4.55 |
| DEN at LAC | DEN 23, LAC 17 | DEN 69%, won | DEN −3.5, won | Over 41.5, lost | DEN -3.5, won | +$4.63 |
| DET at ARI | DET 45, ARI 21 | DET 75%, won | DET −5.5, won | Under 54.5, lost | Under 54.5, lost | −$5.00 |
| SF at SEA | SF 32, SEA 29 | SEA 60%, lost | SEA −3, lost | Over 46.5, won | Over 46.5, won | +$4.55 |
| BAL at ATL | BAL 30, ATL 23 (OT) | ATL 67%, lost | ATL −3, lost | Under 43.5, lost | ATL by 4.0+, lost | −$5.00 |
| BUF at LA | BUF 37, LA 34 (OT) | LA 60%, lost | LA −3, lost | Over 54.5, won | Over 54.5, won | +$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.