SharpJuice

2026 season to date · 500 graded games

Season results

253–238–9

Against the spread, 51.5% (95% range 47–56%). Break-even at standard −110 pricing is 52.4%.

Closing line moved toward the model
57%
228 of 399 line moves
Average closing line value
0.19 pts
per pick, snapshot to close
Edges of 3+ points
45–42–2
51.7%
Average miss: model vs. market
11.7 vs 11.5
points per game

Win probability (games with a Kalshi price, n=229): Brier score model 0.210 vs. Kalshi 0.207 (lower is better).

Win % by weekAgainst Sunday's line · dark line = 52.4% break-even
0%20%40%60%80%Week 0Week 1Week 2Week 3Week 4Week 5Week 6Week 7Week 8Week 9
Win % by size of edgePoints between model and Sunday's line · dark line = 52.4% break-even
0%20%40%60%80%< 11–22–33–55+

By week

WeekATSWin %Model missMarket miss
Week 06–2–075.0%12.213.4
Week 116–26–138.1%13.913.6
Week 228–21–057.1%11.010.8
Week 334–22–160.7%8.58.7
Week 433–23–258.9%11.711.4
Week 527–28–149.1%13.513.1
Week 630–27–152.6%11.611.5
Week 731–26–254.4%10.910.9
Week 815–40–127.3%11.410.8
Week 933–23–058.9%13.213.1

By edge size

EdgeATSWin %
< 1 pts101–83–354.9%
1–2 pts64–62–250.8%
2–3 pts43–51–245.7%
3–5 pts33–29–253.2%
5+ pts12–13–048.0%

Miss = average absolute difference between projected and actual margin. Closing line value = how far the closing spread moved toward the model's side after Sunday's snapshot; closes for Weeks 0–5 are DraftKings via ESPN, later weeks are our last capture before kickoff. Weeks 0–1 used a three-model average (Action Network added in Week 2).