Predictions · Week 2

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).

Our lock and bold call of the week, and our pick on every game, are for signed-in players. Sign in, it's free.
Locks went 84% over 24 seasons; this season's record is on the leaderboard.
GameEloSpreadBooksKalshiPolymarketBlendSystemCrowdSharp crowdImp.SpotResult
DET at BUF64%66%67%Tight agreementDET 31, BUF 41
CAR at ATL57%43%43%44%43%47%47Big disagreementSun 5:00 PM
CIN at HOU62%57%57%59%57%59%64Everything elseSun 5:00 PM
MIN at CHI51%63%66%66%66%62%45Big disagreementSun 5:00 PM
NO at BAL72%71%77%79%79%77%46Clear favorite, mild disagreementSun 5:00 PM
CLE at TB58%74%78%79%79%73%51Big disagreementSun 5:00 PM
PHI at TEN33%30%26%25%25%27%39Clear favorite, mild disagreementSun 5:00 PM
PIT at NE66%66%68%69%69%70%59Tight agreementSun 5:00 PM
GB at NYJ52%40%38%39%39%42%44Big disagreementSun 5:00 PM
JAX at DEN53%57%58%59%59%57%54Everything elseSun 8:05 PM
LV at LAC58%69%72%73%73%69%53Big disagreementSun 8:05 PM
WSH at DAL55%60%65%66%66%63%49Big disagreementSun 8:25 PM
SEA at ARI32%40%35%35%35%32%52Tight agreementSun 8:25 PM
MIA at SF67%84%87%90%90%83%43Big disagreementSun 8:25 PM
IND at KC70%69%72%73%74%74%40Tight agreementMon 12:20 AM
NYG at LAR70%70%74%75%75%73%52Clear favorite, mild disagreementTue 12:15 AM
Points this week+12.0+13.4+14.1on 1 decided games
Right1/11/11/1

The spots

Tight agreement 4 games

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.

  • BUF vs DET: Elo 64%, market 66%, blend 67% · DET 31, BUF 41
  • NE vs PIT: Elo 66%, market 68%, blend 70%
  • SEA at ARI: Elo 68%, market 65%, blend 68%
  • KC vs IND: Elo 70%, market 73%, blend 74%

Big disagreement 7 games

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.

  • CAR at ATL: Elo 43%, market 57%
  • CHI vs MIN: Elo 51%, market 66%
  • TB vs CLE: Elo 58%, market 78%
  • GB at NYJ: Elo 48%, market 62%
  • LAC vs LV: Elo 58%, market 72%
  • DAL vs WSH: Elo 55%, market 65%
  • SF vs MIA: Elo 67%, market 89%

Clear favorite, mild disagreement 3 games

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.

  • BAL vs NO: Elo 72%, market 78%, blend 77%
  • PHI at TEN: Elo 67%, market 75%, blend 73%
  • LAR vs NYG: Elo 70%, market 74%, blend 73%

Everything else 2 games

Moderate favorites where the models roughly agree. No edge found either way in the replays. The blend is as good as anything.

  • HOU vs CIN: Elo 62%, market 58%, blend 59%
  • DEN vs JAX: Elo 53%, market 58%, blend 57%

Season scoreboard

The models scored as players over every decided game this season, on their pre-kickoff numbers.

#ModelGamesPoints
1Closing spread17+78.2
2The blend17+77.4
3The System17+77.4
4Elo (the model)17+45.3