College football · 2026
Track Record
How the picks held up, in public
2026 so far
pre-game predictions, scored once games are finalWinners picked
324-67
82.9% of 391 games
Beaver’s Picks: sides
195-191-5
50.5% · 52.4% breaks even
Beaver’s Picks: totals
200-191
51.2% · 52.4% breaks even
Average miss, margin
12.6
Vegas 11.8 · lower is better
Average miss, total
12.0
Vegas 11.9
Vegas gaps, against the spread
111-112
226 games with a 3+ pt gap
Are the win chances honest?
dots near the line mean yesWinners picked by week
Sam’s Picks
Sam’s projected score against the Vegas line, graded the same way as Beaver’sSam’s Picks: sides
1-0
100.0% · 52.4% breaks even
Sam’s Picks: totals
0-1
0.0% · 52.4% breaks even
Games with a Sam’s Pick
58
1 graded so far
How Vegas gaps have done
backtest, model’s side vs. the closing line, pushes excludedSpread
| Gap size | Games | Record | Model side won |
|---|---|---|---|
| 0 to 3 pts | 3,823 | 1,967-1,856 | 51.4% |
| 3 to 5 pts | 1,667 | 864-803 | 51.8% |
| 5 to 7 pts | 1,012 | 517-495 | 51.1% |
| 7 to 10 pts | 605 | 311-294 | 51.4% |
| 10+ pts | 292 | 135-157 | 46.2% |
Total
| Gap size | Games | Record | Model side won |
|---|---|---|---|
| 0 to 2 pts | 2,614 | 1,338-1,276 | 51.2% |
| 2 to 4 pts | 2,120 | 1,084-1,036 | 51.1% |
| 4 to 6 pts | 1,358 | 676-682 | 49.8% |
| 6 to 9 pts | 940 | 493-447 | 52.4% |
| 9+ pts | 319 | 167-152 | 52.3% |
52.4% is the break-even rate at standard odds. A gap means the model disagrees with Vegas, not that it is right; small samples swing a lot.
Backtest
7,582 games, 2017 to 2026, each season predicted using only earlier seasons| Model | Avg miss, margin | Beaver side |
|---|---|---|
| EnsembleIn use | 12.67 | 51.3% |
| Ridge | 12.75 | 51.6% |
| LightGBM | 12.80 | 51.1% |
| Elo baseline | 13.68 | 48.9% |
| Vegas closing line | 12.19 | n/a |
Average miss is points between the prediction and the real result. Brier score measures win-chance accuracy: 0.25 is a coin flip, lower is better.
Average miss by season
Beaver Model
0-1
0.0% against the spread
VS
Sam leads by 1 game
1 head-to-head games · Weeks 6–6
Sam
1-0
100.0% against the spread
Tale of the tape
every game both picked, graded the same wayBeaverSam
1-0100.0%
Winners picked
straight up
1-0100.0%
0-10.0%
Sides vs. Vegas
same line for both
1-0100.0%
0-10.0%
Totals vs. Vegas
over / under
0-10.0%
0-10.0%
Best bets
3+ pt spread gaps, 4+ pt total gaps
1-0100.0%
18.4
Average miss, margin
points, lower is better
5.4
41.0
Average miss, total
points, lower is better
41.0
0
Closer to the final margin
games
1
Agree or split
on the sideSame side
0%
0 of 1 games
When they agree
0-0
n/a together
When they split
0–1
games won: Beaver – Sam
Race against the spread
games over .500 on sidesWhere they split next
36 upcoming games with Beaver and Sam on opposite sidesGame by game
projected score (away–home) and each side’s picks, graded| Game | Beaver | Sam |
|---|---|---|
| USM at Troy Final 34–55 | 23–25 Southern Miss +9.5LUnder 51.5L | 16–32 Troy −9.5WUnder 51.5L |
Both are graded against the same Vegas line, the one shown on the game cards. Sam’s picks that first appeared after kickoff are left out. Sam’s picks come from Sam’s projected score, the same way Beaver’s do. Best bets are picks at least 3 points off the Vegas spread or 4 off the total. 52.4% breaks even at standard odds.