Skip to main content

Public validation record

2026 Football Model Performance

These results use official OSPR projections locked before kickoff and evaluated against final scores. Mirrored schedule records and live forecasts are excluded.

Evaluated through Oct 16, 2026

Accuracy calculated Oct 17, 2026 8:01 AM EDT

Reset

Performance summary

3,178 games evaluated with ospr-2026.1

Games evaluated

3,178

Winner accuracy

69.8%

2,217 correct

Average margin error

22.3

Lower is better

Average score error

13.1

Per-team points

Brier score

0.197

Probability accuracy

Close projection rate

14.5%

Correct and within 7

Regular season vs. playoffs

A direct comparison using the selected season, week, team, and OSPR model version.

Regular season

Games
3,178
Winner accuracy
69.8%
Margin error
22.3

Playoffs

Games
0
Winner accuracy
—
Margin error
—

Performance by week

Results for the selected model version and season phase.

Week Games Winner accuracy Margin error
Week 1 355 58.3% 22.0
Week 2 351 61.0% 23.3
Week 3 358 62.3% 21.9
Week 4 354 65.3% 23.5
Week 5 356 74.4% 22.6
Week 6 357 80.4% 22.7
Week 7 358 75.4% 22.0
Week 8 348 71.3% 21.8
Week 9 340 79.7% 20.5

Probability calibration

Observed win rate should approach the average predicted probability as sample sizes grow.

Probability Games Predicted Observed Gap Brier
0–9% 21 8.4% 4.8% -3.7 0.045
10–19% 209 15.8% 8.6% -7.2 0.084
20–29% 351 25.4% 21.1% -4.3 0.168
30–39% 487 35.1% 33.5% -1.6 0.222
40–49% 608 45.1% 43.1% -2.0 0.244
50–59% 533 54.9% 57.4% +2.6 0.246
60–69% 439 64.8% 71.5% +6.7 0.204
70–79% 356 74.8% 80.6% +5.9 0.158
80–89% 157 84.1% 88.5% +4.4 0.101
90–99% 17 91.6% 94.1% +2.5 0.057

Performance by prediction confidence

Newer snapshots use historical calibration and comparable sample size. Legacy snapshots fall back to rating-evidence confidence.

Confidence Games Winner accuracy Average margin error
High 2,686 70.7% 22.2 points
Medium 49 87.8% 23.3 points
Low 443 61.9% 22.6 points

Performance by risk indicator

A game may appear in more than one group because indicators describe different kinds of uncertainty.

Indicator Games Winner accuracy Average margin error
Limited Data 1,516 62.3% 22.9 points
Close Game 2,217 63.5% 22.1 points
Upset Possible 2,064 62.4% 21.9 points
Blowout Range 1 100.0% 23.8 points

Largest misses

The largest margin errors in this selection. A miss is a model result to learn from, not automatically a data error.

Date Matchup Projected Final Margin error
Sep 11, 2026 Farrell vs. Reynolds 25–24 84–0 82.5 points
Sep 25, 2026 Normandy vs. Rocky River 14–28 0–83 68.7 points
Oct 16, 2026 Springfield Northwestern vs. Benjamin Logan 15–25 0–78 68.5 points
Oct 16, 2026 Trimble vs. Waterford 21–24 0–69 65.9 points
Sep 18, 2026 Trotwood-Madison vs. Taft 23–17 72–0 65.6 points

Evaluated games

The game-level record behind the summary above.

Aug 21, 2026

Padua Franciscan vs. South Range

Correct
Projected
17–26
Final
7–46
Projected winner
South Range
Margin error
29.9

Aug 21, 2026

Mansfield Madison vs. Shelby

Correct
Projected
16–28
Final
0–54
Projected winner
Shelby
Margin error
42.9

Aug 21, 2026

Lexington vs. Ontario

Missed
Projected
26–21
Final
7–35
Projected winner
Lexington
Margin error
32.3

Aug 21, 2026

Defiance vs. Napoleon

Missed
Projected
17–26
Final
9–8
Projected winner
Napoleon
Margin error
9.7

Aug 21, 2026

Cleveland Central Catholic vs. Hawken

Correct
Projected
18–24
Final
24–29
Projected winner
Hawken
Margin error
1.3

Aug 21, 2026

Medina Buckeye vs. Cloverleaf

Missed
Projected
27–19
Final
6–10
Projected winner
Medina Buckeye
Margin error
11.6

Aug 21, 2026

Ashland vs. Bay

Correct
Projected
27–21
Final
28–7
Projected winner
Ashland
Margin error
14.8

Aug 21, 2026

West Geauga vs. Fairview Park

Missed
Projected
21–24
Final
27–0
Projected winner
Fairview Park
Margin error
29.7

Aug 21, 2026

Streetsboro vs. Copley

Missed
Projected
25–24
Final
20–28
Projected winner
Streetsboro
Margin error
9.5

Aug 21, 2026

Akron Springfield vs. Waterloo

Correct
Projected
16–17
Final
3–8
Projected winner
Waterloo
Margin error
3.6

Aug 21, 2026

Ravenna vs. Field

Missed
Projected
17–22
Final
28–7
Projected winner
Field
Margin error
26.8

Aug 21, 2026

ND Cathedral Latin vs. Struthers

Correct
Projected
24–20
Final
42–16
Projected winner
ND Cathedral Latin
Margin error
21.8

Aug 21, 2026

Marlington vs. Warrensville Heights

Missed
Projected
16–18
Final
31–6
Projected winner
Warrensville Heights
Margin error
26.9

Aug 21, 2026

Louisville vs. New Philadelphia

Missed
Projected
22–23
Final
20–10
Projected winner
New Philadelphia
Margin error
10.8

Aug 21, 2026

Hubbard vs. Brookfield

Correct
Projected
21–23
Final
7–14
Projected winner
Brookfield
Margin error
5.5

Aug 21, 2026

Howland vs. Niles McKinley

Correct
Projected
19–14
Final
26–12
Projected winner
Howland
Margin error
9.3

Aug 21, 2026

hARVEY vs. Berkshire

Correct
Projected
24–20
Final
27–22
Projected winner
hARVEY
Margin error
0.6

Aug 21, 2026

Coventry vs. Girard

Correct
Projected
13–28
Final
0–47
Projected winner
Girard
Margin error
31.0

Aug 21, 2026

Alliance vs. Canal Fulton Northwest

Correct
Projected
23–24
Final
0–16
Projected winner
Canal Fulton Northwest
Margin error
15.4

Aug 21, 2026

Turpin vs. Archbishop McNicholas

Missed
Projected
26–19
Final
10–31
Projected winner
Turpin
Margin error
28.4

Aug 21, 2026

Talawanda vs. Taylor

Missed
Projected
22–23
Final
33–6
Projected winner
Taylor
Margin error
28.9

Aug 21, 2026

Stebbins vs. Archbishop Carroll

Correct
Projected
20–17
Final
41–6
Projected winner
Stebbins
Margin error
32.5

Aug 21, 2026

Sidney vs. Bellefontaine

Missed
Projected
21–18
Final
14–35
Projected winner
Sidney
Margin error
24.2

Aug 21, 2026

Loveland vs. Monroe

Missed
Projected
26–15
Final
6–39
Projected winner
Loveland
Margin error
44.6

Aug 21, 2026

Lima Senior vs. Piqua

Correct
Projected
24–22
Final
42–13
Projected winner
Lima Senior
Margin error
27.0

How to interpret these numbers

Winner accuracy shows whether OSPR favored the team that won. Average margin error shows how far the projected point margin was from the final margin.

Brier score measures probability quality from 0 to 1; lower is better. Calibration compares predicted win probabilities with observed outcomes.

Small groups can swing sharply, so every percentage is shown with its evaluated game count.

Injuries, roster changes, weather, and information not reflected in recorded results may affect individual games.