Skip to main content
The ledger · week 4, 2026

Week 4 graded: 11‑5, market 9‑7

We beat the market this week. Every pick was published before kickoff; here are the results, including the ones we got wrong.

6 Oct 2026 · 2 min read
11-5model, week 4

Every week we grade every pick we published, against the result and against the market. Week 4: the model went 11-5; the market favourite went 9-7. We beat the market this week.

11-5Model, week 469%
9-7Market, week 456%
0.206Brier scorelower is better; 0.25 is a coin flip
36-28Season recordmarket 62% of 64

Where we were wrong

BUF at 78% (NE 29 @ BUF 26). DET at 69% (DET 26 @ CAR 32). NO at 52% (ATL 45 @ NO 24). The most confident misses are the ones worth learning from, so they go first.

Us vs the market

We were right where the market was wrong 4 times (JAX, DAL, CLE, NYG); the market was right where we were wrong 2 times (GB, IND).

GamePickModel %ScoreModelMarket
TEN @ BALBAL81%18-24RightRight
LAC @ SEASEA80%23-30RightRight
DEN @ SFSF80%14-24RightRight
NE @ BUFBUF78%29-26WrongWrong
DET @ CARDET69%26-32WrongWrong
MIA @ MINMIN69%10-15RightRight
KC @ LVKC68%30-27RightRight
NYJ @ CHICHI66%12-23RightRight
JAX @ CINJAX62%22-17RightWrong
LAR @ PHILAR58%24-20RightRight
DAL @ HOUDAL53%34-30RightWrong
PIT @ CLECLE53%24-27RightWrong
ATL @ NONO52%45-24WrongWrong
ARI @ NYGNYG51%24-36RightWrong
GB @ TBTB51%17-14WrongRight
IND @ WASWAS50%30-13WrongRight

Every week 4 pick, most confident first

Read this before you bet

Picking winners is not beating the price. Across 2025 our flat-bet ROI at posted odds was negative. Use the model as one view of the game, not as a tip.

Sources: results_dashboard.json (2026-10-06T09:00:44.322632Z). Every number here comes straight from our pipeline.