NCAA FOOTBALL · MODEL PERFORMANCE

The whole record, one page

Both halves of the record in one place: every graded pick with its edge and result, and every projection measured against the Vegas line on the same games. Locked before kickoff, graded after, nothing removed.

✓ WALK-FORWARD VALIDATED2025 walk-forward · 2026 logged before kickoff

135

Games priced, 2026

54.2%

Spreads win rate

Sep 12, 2026

Graded through

SEASON

PREMIUM ATSedge ≥ 6 pts

54.2%

13W – 11L · 24 graded · 95% CI 35.1–72.1%

AGAINST THE SPREAD · PREMIUM · EDGE ≥ 6 PTS

+3.5%

ROI, 1u at −110

+0.8u

Units won

ALL GRADED ATSevery decided pick

49.5%

47W – 48L · 95 graded · 95% CI 39.6–59.4%

AGAINST THE SPREAD · ALL GRADED

-5.5%

ROI, 1u at −110

-5.2u

Units lost

LINE QUALITY95 paired games

43.2%

Share of games BBMI landed closer than Vegas

computed from 95 logged games

13.22

BBMI margin MAE

12.23

Market margin MAE

Calibration by edge

889 priced · 95 decided

The tier each pick actually fired under, from the published criterion. The AS POSTED rows are the record and tie to the product cards above; they are never recomputed from today’s thresholds. One game sits in the premium cut but outside the all-graded cut: its published line equals the market’s, so the all-graded cut excludes it while its edge keeps it premium. That is why the two totals differ by 1.

EDGE (POINTS)	TIER AS POSTED	N	WIN %	ROI
AS POSTED · THE TIER EACH PICK ACTUALLY FIRED UNDER
Premium · edge ≥ 6, spread 14–23	Premium	8	62.5%	+19.4%
Premium ★ · edge ≥ 6, spread ≤ 14	Premium ★	16	50.0%	-4.5%
All picks as posted	TOTAL	24	54.2%	+3.5%
BY EDGE INTERVAL · DESCRIPTIVE, SAME PICKS
0–2	No pick	24	58.3%	+11.4%
2–4	No pick	19	47.4%	-9.5%
4–5	No pick	10	30.0%	-42.7%
5–6	Marginal	10	40.0%	-23.6%
6–10 · spread ≤ 14	Premium ★	9	44.4%	-15.1%
6–10 · spread 14–23	Premium	4	75.0%	+43.3%
10–18 · spread ≤ 14	Premium ★	7	57.1%	+9.1%
10–18 · spread 14–23	Premium	4	50.0%	-4.5%
Edge ≥ 6, spread wider than ±23	Marginal	8	50.0%	-4.5%
All decided	TOTAL	95	49.5%	-5.5%

The interval rows are descriptive, not the record: the same picks cut at today’s thresholds, so a pick can appear in a band that did not exist when it was posted. They will not add up to the figure at the top of the page. Read them for shape.

Season to date

2026

Cumulative win rate after each week, against the break-even this product is priced at. The curve is the running rate, not each week's own, so a late swing moves it less than an early one.

2 weeksbreak-even 52.4%now 54.2%

BY WEEK ▼	PICKS	WIN %	ROI	CUMULATIVE
9/12 ’26	16	37.5%	-28.4%	54.2%
9/4 ’26	8	87.5%	+67.1%	87.5%

BBMI vs Vegas

95 games

No picks here: line quality, head to head, on the same games logged below. Not a betting record, because a closer forecast is not a won bet.

CLOSER SPLIT1 ties

BBMI43.2%

VEGAS55.8%

MARGIN MAEVegas by 0.99 pts

BBMI13.22

VEGAS12.23

Lower MAE is the better projection. Computed from 95 logged games, not read from a published aggregate: this sport publishes no closer split.

Published, across every priced game. The rows above are computed from the 95 games logged below; these are the site’s own aggregates over 891 games, read rather than recomputed, with the verdict the Record card reached.

PROJECTED WINNER ACCURACYVegas by 4.2 pts

Share of games each projection’s implied winner was right

BBMI70.3%

VEGAS74.5%

BRIER SCOREVegas not published

Probability accuracy: rewards honest odds, not bold ones

BBMI0.193

VEGAS

MARGIN MAE, PTSVegas by 1.80 pts

Projected home margin vs actual margin, in pts

BBMI13.68

VEGAS11.88

GAME-TOTAL MAE, PTSVegas by 0.38 pts

Projected total vs actual combined score, in pts

BBMI12.96

VEGAS12.58

Where the lines diverge

135 games

Under 3 pts39.3%

3 to 7 pts40.0%

7 to 14 pts18.5%

14+ pts2.2%

How far apart the two lines were. This needs no result, so it counts every game carrying both lines (135), which is wider than the 95 graded games above.

Calibration

Brier 0.193 · Published · full 891-game sample

A calibrated 60% should win about 60% of the time. Predicted win probability against the actual win rate, over every graded game rather than only the ones a pick fired on. This panel is the only block on the page that does NOT follow the season chip: the scorecard publishes one cohort and no per-season cut, so showing it under a 2026 heading would be claiming a season it does not measure.

HOME WIN P	N	PRED	ACTUAL	GAP
< 35%	164	21.2%	30.5%	+9.3
35–45%	48	40.4%	52.1%	+11.6
45–55%	127	50.0%	48.0%	-2.0
55–65%	73	59.9%	50.7%	-9.2
≥ 65%	479	83.6%	78.1%	-5.5

GAP is actual minus predicted, so a positive number means the model was too cautious in that bucket and a negative one means too confident. Brier 0.193 over 891 graded games; lower is better, and 0.25 is what a coin flip scores.

Products & rules

thresholds from config

These are the definitions in force today. They change through the season as the model is refined, and a change applies from its date forward only: a pick is never refitted to a rule that did not exist when it fired, and the log is never edited to match a newer one. Every pick is counted in the record exactly as it posted.

PRODUCT	THE BET	PREMIUM	PREMIUM ★
Spreads · Premium	Against the spread, the sign of the edge picks the side. Promotes on edge and on how tight the posted spread is.	edge ≥ 6, spread ≤ 23	spread ≤ 14
Spreads · all graded	Every pick the model fires, including the marginal band.	every decided pick
Totals	Full-game over / under. In calibration, not yet a graded product.	in calibration, not yet a graded product

Thresholds are read from the published config, never restated here.

All sports →

The log

135 rows

Every priced game, with the market’s number beside ours and which one landed closer. BBMI ERR and VEGAS ERR are each side’s projected margin against the actual, so CLOSER is decided by those two columns and nothing else.

SIDE is the team the pick took, read from the row’s own stored pick. Every row in view stores one.

									FINAL
2026-09-12	South Florida @ Army	-3.5	-2.8	0.7	South Florida	58%	No pick	WIN	28–24	6.8	7.5	BBMI
2026-09-12	Ohio State @ Texas	-1.5	-0.5	1.0	Ohio State	51%	No pick	WIN	23–24	0.5	0.5	TIE
2026-09-12	Louisiana Tech @ LSU	-34.5	-33.5	1.0	Louisiana Tech	99%	No pick	WIN	14–45	2.5	3.5	BBMI
2026-09-12	Alabama @ Kentucky	+8.5	+7.4	1.1	Kentucky	30%	No pick	LOSS	45–17	20.6	19.5	VEGAS
2026-09-12	Arkansas @ Utah	-12.5	-11.1	1.4	Arkansas	79%	No pick	LOSS	10–43	21.9	20.5	VEGAS
2026-09-12	UTSA @ Texas State	-2.5	-3.9	1.4	Texas State	61%	No pick	LOSS	31–26	8.9	7.5	VEGAS
2026-09-12	Bowling Green @ Nebraska	-30.5	-32.1	1.6	Nebraska	99%	No pick	WIN	7–56	16.9	18.5	BBMI
2026-09-12	Old Dominion @ Virginia Tech	-19.5	-21.1	1.6	Virginia Tech	93%	No pick	WIN	21–44	1.9	3.5	BBMI
2026-09-12	Jacksonville State @ Ohio	-1.5	+0.3	1.8	Jacksonville State	49%	No pick	LOSS	27–29	2.3	0.5	VEGAS
2026-09-12	Texas Tech @ Oregon State	+25.5	+27.4	1.9	Texas Tech	3%	No pick	LOSS	35–24	16.4	14.5	VEGAS
2026-09-12	Maryland @ Connecticut	+11.5	+9.5	2.0	Connecticut	25%	No pick	LOSS	38–14	14.5	12.5	VEGAS
2026-09-12	Louisiana @ USC	-30.5	-32.8	2.3	USC	99%	No pick	LOSS	30–49	13.8	11.5	VEGAS
2026-09-12	Duke @ Illinois	-6.5	-8.8	2.3	Illinois	74%	No pick	LOSS	31–27	12.8	10.5	VEGAS
2026-09-12	Utah State @ Washington	-28.5	-31.0	2.5	Washington	99%	No pick	LOSS	14–16	29.0	26.5	VEGAS
2026-09-12	Navy @ Florida Atlantic	+4.5	+1.9	2.6	Florida Atlantic	45%	No pick	WIN	30–38	9.9	12.5	BBMI
2026-09-12	Wake Forest @ Purdue	+3.5	+0.4	3.1	Purdue	49%	No pick	WIN	38–36	1.6	1.5	VEGAS
2026-09-12	San Diego State @ UCLA	-12.5	-9.3	3.2	San Diego State	75%	No pick	LOSS	10–28	8.7	5.5	VEGAS
2026-09-12	Southern Miss @ Auburn	-29.5	-33.7	4.2	Auburn	99%	No pick	WIN	8–43	1.3	5.5	BBMI
2026-09-12	Memphis @ Boise State	-9.5	-5.1	4.4	Memphis	64%	No pick	LOSS	20–38	12.9	8.5	VEGAS
2026-09-12	UCF @ Pittsburgh	-6.5	-10.9	4.4	Pittsburgh	78%	No pick	LOSS	7–12	5.9	1.5	VEGAS
2026-09-12	Tennessee @ Georgia Tech	+12.5	+7.9	4.6	Georgia Tech	29%	No pick	LOSS	45–24	13.1	8.5	VEGAS
2026-09-12	Buffalo @ FIU	-9.5	-4.7	4.8	Buffalo	63%	No pick	LOSS	20–33	8.3	3.5	VEGAS
2026-09-12	California @ Syracuse	-3.5	+1.4	4.9	California	46%	No pick	WIN	21–18	1.6	6.5	BBMI
2026-09-12	Western Kentucky @ Georgia	-39.5	-33.8	5.7	Western Kentucky	99%	No pick	LOSS	20–70	16.2	10.5	VEGAS
2026-09-12	Penn State @ Temple	+24.5	+18.6	5.9	Temple	9%	No pick	WIN	27–9	0.6	6.5	BBMI

All picks locked before kickoff and graded against the closing line. Past performance is not a guarantee.