Final: San Francisco 49ers 17, Seattle Seahawks 13.
Going in, our model had favored Seattle Seahawks at 63% win probability, and the pick lost.
Out or doubtful: 2 49ers, 3 Seahawks.
PICK: SEA
TIER B
PICK LOST (STRAIGHT UP)ATS: LOST
SF 37%
SEA 63%
Model confidence: SEA 63%
Our line: SEA -4.6
ODDS
SPREAD
SEA +2.5
MARKET SPREAD · MARKET AVG
SEA -4.6
OUR LINE
MISSED
VS SPREAD
MONEYLINE
SEA · OUR WIN PROBABILITY
63%
SEA · MARKET WIN PROBABILITY
45%
DIFFERENCE
+18%
SOURCE
SF
SEA
SEA WIN %
Closing line
-135
+114
44.6%
TEAM COMPARISON2025 SEASON · EFFICIENCY, SCORING, TENDENCIES · RANK IN PARENTHESES · FULL-SEASON NUMBERS, NOT AS OF WEEK 1
+0.018Net EPA / play+0.150
+0.088 (6)Offense EPA / play+0.033 (13)
+0.070 (24)Defense EPA / play-0.117 (2)
48.3% (4)Offense success %46.3% (7)
GAME NARRATIVE
SEA B-tier pick misses. SF takes it.
MISSED
Model picked SEA but SF won. Projected margin was 4.6, the model overestimated by 8.6 points.
INSTANT CLASSIC
The win probability swung past 50% 11 times. One of the wildest games of the week.
BAD BEAT
Missed the spread by just 1.5 points, a bad-beat loss.
Every model misses. The edge comes from the aggregate, not any single game.
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.