Model Performance

2023 Season · 2,986 graded predictions

2026 2025 2024 2023 2022 All

In-sample data: All predictions for this season were generated after games completed (historical backfill), so metrics reflect in-sample fit rather than true out-of-sample accuracy. Metrics will become trustworthy as the current season progresses and daily ETL generates pre-game predictions.

66%

Overall Accuracy

84%

Last 50 Games

0.2638

Brier Score (↓ better)

1.0334

Log Loss (↓ better)

0.6102

AUC (↑ better)

2,986

Predictions Graded

Calibration

When the model says X%, does the favored team win X% of the time? The vertical bar shows the predicted probability; the filled bar shows actual.

50–55%210 games49% actual(-4pp)

55–60%229 games51% actual(-6pp)

60–65%217 games60% actual(-3pp)

65–70%250 games63% actual(-4pp)

70–75%237 games69% actual(-3pp)

75–80%197 games75% actual(-2pp)

80–100%1646 games70% actual(-27pp)

Actual win rate Predicted

Score Projection Accuracy

How close were the Monte Carlo score projections to actual results?

4.7

Avg margin error (runs)

+1.0

Margin bias (under-projects)

58%

Own-line cover rate

Within 2 runs of projected margin29%

Within 5 runs of projected margin62%

Based on 2986 games with score projections.

D1 Diamond Top 25 — 2026 Season

Composite ranking of all D1 teams with ≥5 games played.

#	Team	Record	Elo	wOBA	FIP	Run Diff	Score
1	UCLAUCLA Bruins	35–3	1838	0.430	3.58	+5.4	90
2	GTGeorgia Tech Yellow Jackets	31–7	1787	0.489	4.03	+6.3	89
3	TEXTexas Longhorns	30–7	1800	0.425	3.07	+4.6	86
4	UNCNorth Carolina Tar Heels	34–6	1858	0.404	3.92	+4.7	86
5	UGAGeorgia Bulldogs	32–9	1780	0.466	3.95	+4.8	83
6	TA&MTexas A&M Aggies	30–7	1785	0.457	4.84	+5.3	83
7	MSSTMississippi State Bulldogs	29–10	1744	0.427	3.42	+4.9	80
8	ORSTOregon State Beavers	29–8	1751	0.387	3.12	+3.0	79
9	MISSOle Miss Rebels	29–11	1776	0.389	3.41	+2.9	78
10	AUBAuburn Tigers	27–12	1746	0.392	3.02	+2.9	77
11	MIAMiami Hurricanes	29–10	1721	0.427	4.03	+4.6	76
12	NEBNebraska Cornhuskers	30–9	1739	0.408	4.14	+2.8	75
13	FLAFlorida Gators	28–13	1725	0.376	2.96	+2.2	74
14	FSUFlorida State Seminoles	27–11	1749	0.389	3.57	+3.1	74
15	JVSTJacksonville State Gamecocks	32–8	1679	0.396	3.70	+3.6	73
16	WVUWest Virginia Mountaineers	26–9	1705	0.407	3.99	+3.8	73
17	BCBoston College Eagles	32–11	1740	0.378	4.04	+3.0	73
18	KUKansas Jayhawks	28–11	1731	0.399	4.35	+1.7	72
19	OUOklahoma Sooners	26–12	1724	0.387	4.06	+2.4	71
20	ALAAlabama Crimson Tide	27–13	1720	0.390	3.85	+2.5	71
21	OREOregon Ducks	27–11	1679	0.417	3.93	+3.2	71
22	ASUArizona State Sun Devils	28–13	1661	0.433	4.04	+2.9	71
23	CBUCalifornia Baptist Lancers	13–2	1572	0.417	3.35	+4.4	71
24	CCUCoastal Carolina Chanticleers	28–10	1752	0.394	4.88	+2.2	70
25	UVAVirginia Cavaliers	28–13	1691	0.414	4.26	+2.8	70

Minimum 5 games played. wOBA/FIP from FanGraphs.

By Confidence Tier

Accuracy when the model is highly confident in its pick.

Confidence	Games	Accuracy
≥ 60%	2547	69%
≥ 65%	2330	70%
≥ 70%	2080	70%
≥ 75%	1843	71%

Top Teams by Elo

Rolling Elo rating (1500 = average). Updated after every game result.

Rank	Team	Games	Elo
1	North Carolina Tar Heels	289	1858
2	UCLA Bruins	273	1838
3	Texas Longhorns	288	1800
4	Georgia Tech Yellow Jackets	273	1787
5	Texas A&M Aggies	290	1785
6	Georgia Bulldogs	276	1780
7	Ole Miss Rebels	279	1776
8	Coastal Carolina Chanticleers	226	1752
9	Oregon State Beavers	290	1751
10	Florida State Seminoles	275	1749

How to Read This

Overall Accuracy — % of games where the model's favored team won.

Brier Score — measures probability calibration quality. Lower is better.

Log Loss — penalises confident wrong predictions more harshly than Brier score. Lower is better.

AUC — probability that the model ranks a random home win above a random home loss. 0.5 = no skill; 1.0 = perfect.

Calibration chart — a perfectly calibrated model's bar would exactly touch the line in every bucket.

Elo ratings — self-correcting power ratings that update after every game. 1500 is average.