The model columns show each model's probability for the home team. Games are sorted into the spots our replays found an edge in, with the record behind each. Once a game ends, the models are scored the way players are, and the week and season tallies show who's forecasting best. Imp. is importance: how much the league's playoff picture swings on the game, from simulated seasons (hover for the game's quality).
| Game | Elo | Spread | Books | Kalshi | Polymarket | Blend | System | Crowd | Sharp crowd | Imp. | Spot | Result |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DET at BUF | 64% | 66% | — | — | — | 67% | — | — | — | — | Tight agreement | DET 31, BUF 41 |
| CAR at ATL | 57% | 43% | 43% | 44% | 43% | 47% | — | — | — | 47 | Big disagreement | Sun 5:00 PM |
| CIN at HOU | 62% | 57% | 57% | 59% | 57% | 59% | — | — | — | 64 | Everything else | Sun 5:00 PM |
| MIN at CHI | 51% | 63% | 66% | 66% | 66% | 62% | — | — | — | 45 | Big disagreement | Sun 5:00 PM |
| NO at BAL | 72% | 71% | 77% | 79% | 79% | 77% | — | — | — | 46 | Clear favorite, mild disagreement | Sun 5:00 PM |
| CLE at TB | 58% | 74% | 78% | 79% | 79% | 73% | — | — | — | 51 | Big disagreement | Sun 5:00 PM |
| PHI at TEN | 33% | 30% | 26% | 25% | 25% | 27% | — | — | — | 39 | Clear favorite, mild disagreement | Sun 5:00 PM |
| PIT at NE | 66% | 66% | 68% | 69% | 69% | 70% | — | — | — | 59 | Tight agreement | Sun 5:00 PM |
| GB at NYJ | 52% | 40% | 38% | 39% | 39% | 42% | — | — | — | 44 | Big disagreement | Sun 5:00 PM |
| JAX at DEN | 53% | 57% | 58% | 59% | 59% | 57% | — | — | — | 54 | Everything else | Sun 8:05 PM |
| LV at LAC | 58% | 69% | 72% | 73% | 73% | 69% | — | — | — | 53 | Big disagreement | Sun 8:05 PM |
| WSH at DAL | 55% | 60% | 65% | 66% | 66% | 63% | — | — | — | 49 | Big disagreement | Sun 8:25 PM |
| SEA at ARI | 32% | 40% | 35% | 35% | 35% | 32% | — | — | — | 52 | Tight agreement | Sun 8:25 PM |
| MIA at SF | 67% | 84% | 87% | 90% | 90% | 83% | — | — | — | 43 | Big disagreement | Sun 8:25 PM |
| IND at KC | 70% | 69% | 72% | 73% | 74% | 74% | — | — | — | 40 | Tight agreement | Mon 12:20 AM |
| NYG at LAR | 70% | 70% | 74% | 75% | 75% | 73% | — | — | — | 52 | Clear favorite, mild disagreement | Tue 12:15 AM |
| Points this week | +12.0 | +13.4 | — | — | — | +14.1 | — | — | — | on 1 decided games | ||
| Right | 1/1 | 1/1 | — | — | — | 1/1 | — | — | — | |||
Elo and the market agree on the favorite within 4 points. Over 24 seasons (2,312 games) favorites here won 69.2% against a 67.7% forecast; in 2023–25 it ran hotter, 74% against 66%. Lean a little toward the favorite. The blend adds 2 points.
Elo and the market are 10 or more points apart. Over 24 seasons (943 games) Elo's side won 50% while Elo claimed 63% and the market 49%. The market was right almost every time. Take the market's number, or split the difference at most. This is where Elo is overconfident.
Both favor the same team by 60% or more, but they differ by 4 to 10 points. Replays: favorites won about as often as the average of the two forecasts said (no surplus either way). The blend without a bump. Nothing to exploit; take the average.
Moderate favorites where the models roughly agree. No edge found either way in the replays. The blend is as good as anything.
The models scored as players over every decided game this season, on their pre-kickoff numbers.
| # | Model | Games | Points |
|---|---|---|---|
| 1 | Closing spread | 17 | +78.2 |
| 2 | The blend | 17 | +77.4 |
| 3 | The System | 17 | +77.4 |
| 4 | Elo (the model) | 17 | +45.3 |