Going in, our model had favored Pittsburgh Steelers at 62% win probability, and the pick won.
Out or doubtful: 1 Steelers, 2 Jets.
PICK: PIT
TIER B
PICK WONATS ✗
PIT 62%
NYJ 38%
Model confidence: PIT 62%
Our line: PIT -4.1
ODDS
SPREAD
PIT -3.0
MARKET SPREAD · MARKET AVG
PIT -4.1
OUR LINE
MISSED
VS SPREAD
MONEYLINE
PIT · OUR WIN PROBABILITY
62%
PIT · MARKET WIN PROBABILITY
59%
DIFFERENCE
+3%
SOURCE
PIT
NYJ
PIT WIN %
Closing line
-155
+130
58.7%
TEAM COMPARISON2025 SEASON · EFFICIENCY, SCORING, TENDENCIES · RANK IN PARENTHESES · FULL-SEASON NUMBERS, NOT AS OF WEEK 1
+0.007Net EPA / play-0.274
+0.025 (16)Offense EPA / play-0.127 (29)
+0.018 (18)Defense EPA / play+0.147 (31)
44.0% (17)Offense success %40.7% (29)
GAME NARRATIVE
PIT B-tier pick hits. Model was directionally correct.
NAILED IT
Model projected PIT by 4.1. Actual: 2 points. The model was within 2.1 points of the real margin.
INSTANT CLASSIC
The win probability swung past 50% 7 times. One of the wildest games of the week.
BAD BEAT
Missed the spread by just 1.0 point, a bad-beat loss.
Another data point for the model. B-tier picks continue to track.
SITUATIONAL TRENDS
Historical splits, shown for context only. We tested them: picking the situations that beat break-even in training goes 770–760 (50.3%) out of sample, so they are not a betting signal and are not coloured like one.
Every stat on this page is free, and so is the model's pick for this game. Pro is the separate question of which games we would actually bet, and at what stake, plus player props, unit sizing, and the full profit-and-loss ledger.