2025 College Football Week 1 Model Backtest
Quick answer: In this retrospective 2025
Week 1 FBS-vs-FBS backtest, the frozen model went 38/48 (79.2%) with mean Brier
0.1609. Full 2025: 550/762 (72.2%). These were not live picks.
Ratings use final 2023-2024 FBS-vs-FBS games only. They were frozen before any
2025 result was graded. Historical pregame spreads may be blended, but their probability
mapping was calibrated on 2024 outcomes—not on the 2025 test results.
Week 1 scorecard
| Metric | Value |
|---|---|
| Games | 48 |
| Decided | 48 |
| Correct picks | 38/48 (79.2%) |
| Mean Brier | 0.1609 |
| Full-season accuracy | 550/762 (72.2%) |
Full-season method comparison
The headline is the blended ensemble. This table separates the ratings model from
the historical spread so market information is not misreported as pure model performance.
| Method | Games | Correct | Accuracy | Mean Brier |
|---|---|---|---|---|
| Elo model only | 762 | 495 | 65.0% | 0.221 |
| Market spread only | 762 | 564 | 74.0% | 0.1733 |
| 40/60 ensemble | 762 | 550 | 72.2% | 0.1804 |
Every Week 1 FBS-vs-FBS game: pick vs actual
| Date | Away | Home | Home WP | Pick | Actual | Result | Source |
|---|---|---|---|---|---|---|---|
| 2025-08-23 | Iowa State 24 | Kansas State 21 | 53.2% | Kansas State | Iowa State | MISS | ensemble |
| 2025-08-23 | Fresno State 7 | Kansas 31 | 77.3% | Kansas | Kansas | HIT | ensemble |
| 2025-08-23 | Sam Houston 24 | Western Kentucky 41 | 71.4% | Western Kentucky | Western Kentucky | HIT | ensemble |
| 2025-08-23 | Stanford 20 | Hawai’i 23 | 57.6% | Hawai’i | Hawai’i | HIT | ensemble |
| 2025-08-28 | Boise State 7 | South Florida 34 | 27.0% | Boise State | South Florida | MISS | ensemble |
| 2025-08-28 | Ohio 31 | Rutgers 34 | 63.9% | Rutgers | Rutgers | HIT | ensemble |
| 2025-08-28 | Wyoming 10 | Akron 0 | 41.6% | Wyoming | Wyoming | HIT | ensemble |
| 2025-08-28 | East Carolina 17 | NC State 24 | 78.4% | NC State | NC State | HIT | ensemble |
| 2025-08-28 | Jacksonville State 10 | UCF 17 | 62.7% | UCF | UCF | HIT | ensemble |
| 2025-08-29 | Buffalo 10 | Minnesota 23 | 80.4% | Minnesota | Minnesota | HIT | ensemble |
| 2025-08-29 | Nebraska 20 | Cincinnati 17 | 36.1% | Nebraska | Nebraska | HIT | ensemble |
| 2025-08-29 | Miami (OH) 0 | Wisconsin 17 | 66.7% | Wisconsin | Wisconsin | HIT | ensemble |
| 2025-08-29 | App State 34 | Charlotte 11 | 17.1% | App State | App State | HIT | ensemble |
| 2025-08-29 | Western Michigan 6 | Michigan State 23 | 77.4% | Michigan State | Michigan State | HIT | ensemble |
| 2025-08-29 | Kennesaw State 9 | Wake Forest 10 | 80.6% | Wake Forest | Wake Forest | HIT | ensemble |
| 2025-08-30 | Auburn 38 | Baylor 24 | 61.3% | Baylor | Auburn | MISS | ensemble |
| 2025-08-30 | Georgia Tech 27 | Colorado 20 | 50.1% | Colorado | Georgia Tech | MISS | ensemble |
| 2025-08-30 | UNLV 38 | Sam Houston 21 | 29.2% | UNLV | UNLV | HIT | ensemble |
| 2025-08-30 | Central Michigan 16 | San José State 14 | 83.9% | San José State | Central Michigan | MISS | ensemble |
| 2025-08-30 | Florida Atlantic 7 | Maryland 39 | 78.9% | Maryland | Maryland | HIT | ensemble |
| 2025-08-30 | Texas 7 | Ohio State 14 | 55.9% | Ohio State | Ohio State | HIT | ensemble |
| 2025-08-30 | Ball State 0 | Purdue 31 | 74.7% | Purdue | Purdue | HIT | ensemble |
| 2025-08-30 | Mississippi State 34 | Southern Miss 17 | 26.3% | Mississippi State | Mississippi State | HIT | ensemble |
| 2025-08-30 | Syracuse 26 | Tennessee 45 | 74.2% | Tennessee | Tennessee | HIT | ensemble |
| 2025-08-30 | Northwestern 3 | Tulane 23 | 72.3% | Tulane | Tulane | HIT | ensemble |
| 2025-08-30 | Toledo 16 | Kentucky 24 | 61.8% | Kentucky | Kentucky | HIT | ensemble |
| 2025-08-30 | Old Dominion 14 | Indiana 27 | 88.0% | Indiana | Indiana | HIT | ensemble |
| 2025-08-30 | Alabama 17 | Florida State 31 | 18.0% | Alabama | Florida State | MISS | ensemble |
| 2025-08-30 | Marshall 7 | Georgia 45 | 91.6% | Georgia | Georgia | HIT | ensemble |
| 2025-08-30 | Temple 42 | Massachusetts 10 | 46.5% | Temple | Temple | HIT | ensemble |
| 2025-08-30 | Nevada 11 | Penn State 46 | 98.0% | Penn State | Penn State | HIT | ensemble |
| 2025-08-30 | Coastal Carolina 7 | Virginia 48 | 67.7% | Virginia | Virginia | HIT | ensemble |
| 2025-08-30 | UTSA 24 | Texas A&M 42 | 82.9% | Texas A&M | Texas A&M | HIT | ensemble |
| 2025-08-30 | LSU 17 | Clemson 10 | 66.6% | Clemson | LSU | MISS | ensemble |
| 2025-08-30 | New Mexico 17 | Michigan 34 | 95.1% | Michigan | Michigan | HIT | ensemble |
| 2025-08-30 | Missouri State 13 | USC 73 | 91.8% | USC | USC | HIT | ensemble |
| 2025-08-30 | UTEP 16 | Utah State 28 | 64.4% | Utah State | Utah State | HIT | ensemble |
| 2025-08-30 | Georgia State 7 | Ole Miss 63 | 96.5% | Ole Miss | Ole Miss | HIT | ensemble |
| 2025-08-31 | Rice 14 | Louisiana 12 | 78.2% | Louisiana | Rice | MISS | ensemble |
| 2025-08-31 | Eastern Michigan 27 | Texas State 52 | 82.3% | Texas State | Texas State | HIT | ensemble |
| 2025-08-31 | Georgia Southern 14 | Fresno State 42 | 47.3% | Georgia Southern | Fresno State | MISS | ensemble |
| 2025-08-31 | Hawai’i 6 | Arizona 40 | 78.5% | Arizona | Arizona | HIT | ensemble |
| 2025-08-31 | California 34 | Oregon State 15 | 42.9% | California | California | HIT | ensemble |
| 2025-08-31 | Utah 43 | UCLA 10 | 43.7% | Utah | Utah | HIT | ensemble |
| 2025-08-31 | Colorado State 21 | Washington 38 | 86.9% | Washington | Washington | HIT | ensemble |
| 2025-08-31 | Virginia Tech 11 | South Carolina 24 | 68.3% | South Carolina | South Carolina | HIT | ensemble |
| 2025-08-31 | Notre Dame 24 | Miami 27 | 40.8% | Notre Dame | Miami | MISS | ensemble |
| 2025-09-02 | TCU 48 | North Carolina 14 | 44.1% | TCU | TCU | HIT | ensemble |
Highest-confidence misses
Limited to the 25 most confident misses so the table
stays readable; the complete game-level record is preserved in the JSON artifact.
| Game | Pick | Confidence | Actual | Margin |
|---|---|---|---|---|
| Central Michigan at San José State | San José State | 83.9% | Central Michigan | 2 |
| Alabama at Florida State | Alabama | 82.0% | Florida State | 14 |
| Rice at Louisiana | Louisiana | 78.2% | Rice | 2 |
| Boise State at South Florida | Boise State | 73.0% | South Florida | 27 |
| LSU at Clemson | Clemson | 66.6% | LSU | 7 |
| Auburn at Baylor | Baylor | 61.3% | Auburn | 14 |
| Notre Dame at Miami | Notre Dame | 59.2% | Miami | 3 |
| Iowa State at Kansas State | Kansas State | 53.2% | Iowa State | 3 |
| Georgia Southern at Fresno State | Georgia Southern | 52.7% | Fresno State | 28 |
| Georgia Tech at Colorado | Colorado | 50.1% | Georgia Tech | 7 |
Methodology and interpretation
- Train: 2023 and 2024 final regular-season FBS-vs-FBS games.
- Test: 2025 final regular-season FBS-vs-FBS games, with ratings frozen.
- Model: opponent-adjusted Elo with score-margin adjustment and empirical home field.
- Ensemble rows: 40% Elo plus 60% historical spread-derived win probability.
- Brier measures probability error; lower is better and 0.25 is the coin-flip reference.
FAQ
Did this model exist in the 2025 season?
No. This is a retrospective reconstruction, clearly labeled as such. It does not claim
these picks were published before kickoff.
Why only FBS-vs-FBS?
It gives one comparable
opponent pool and avoids pretending schedules across NCAA divisions are interchangeable.
Is this betting advice?
No. It is a model audit and historical scorecard.
Related: 2026 CFB predictions
and the NFL Facts Stats Hub.
Sources
Retrospective backtest rebuilt 2026-09-06.
No mock data and no 2025 result used to fit the frozen ratings.