MLB Model vs Market: Week in Review (Sep 21 to 27, 2026)

How we did

Graded MLB games, Sep 21 to 27, 2026 · reports, not picks

Games graded

69

2026-W39

Moneyline record

43-26

62.3% higher-prob side

our >50% side won

Moneyline Brier

0.246

better than 0.250 coin flip

lower is better

Totals avg miss

3.65

runs |proj − actual|

69 games

Totals vs market

-0.04

leads market (3.65 vs 3.70)

69 lined games

Where the week's results came from

A fixed set of splits, published every week whether it flatters us or not · slices under n=5 show their count and no rate

Moneyline split	Record	n
Model's side was the home team	27–25	52
Model's side was the road team	15–1	16
Model's side was the market favorite	32–19	51
Model's side was the market underdog	10–6	16
Coin-flip calls (50-55%)	29–16	45
Moderate calls (55-65%)	13–9	22
Strongest calls (65%+)	not scored: below the n=5 floor (n=2)
Games with a total under 8.5	32–19	51
Games with a total 8.5-9.5	8–6	14
Games with a total above 9.5	not scored: below the n=5 floor (n=4)

Totals split	Our avg miss	Market's	n
Projection sat above the line	3.7	3.76	66
Projection sat below the line	not scored: below the n=5 floor (n=2)
Lines under 8.5	3.51	3.5	51
Lines 8.5-9.5	4.02	4.32	14
Lines above 9.5	not scored: below the n=5 floor (n=4)

1 projection landed exactly on the line, so the above/below splits do not sum to the lined-game count.

Confidence bucket	We said	It happened	n
Coin-flip calls (50-55%)	51.8%	64.4%	45
Moderate calls (55-65%)	59.5%	59.1%	22
Strongest calls (65%+)	not scored: below the n=5 floor (n=2)

League base rates for the same games: home teams went 29–40 (n=69); market favorites went 38–29 (56.7%, n=67); overs went 33–35 against the line (n=69). Every model result above sits inside that backdrop.

The three largest totals misses account for 15.0% of the week's total absolute totals error (37.7 of 252.1 runs across 69 games).

Strongest call that landed

CIN @ ATL (Sep 23): we had the home side at 72%; the home side won.

Final CIN 2, ATL 3; opening price on that side -252; total 7.5; the archived probables started.

Strongest call that missed

MIA @ CHC (Sep 23): we had the home side at 66%; the away side won. It stays in the record.

Final MIA 3, CHC 2; opening price on that side -178; total 6.5; the archived probables started.

One week is a small sample. These are counts of where the results came from, not conclusions about skill; the season-long record is the number that matters.

The biggest misses

We show them on purpose · totals, Sep 21 to 27, 2026

The point of a public track record is that the misses stay in. Our three largest totals misses this week:

Game	Projected	Actual	Off by
CWS @ KC	8.8	25	16.2
CLE @ KC	8.4	21	12.6
ARI @ COL	11.1	20	8.9

Every graded game

Projected total vs. actual, and whether our higher-probability moneyline side won · 69 games

Game	Proj total	Actual	Miss	Home win%	ML side
TOR @ BAL	8.8	7	1.8	0.53	Hit
WSH @ DET	8.7	11	2.3	0.52	Hit
MIN @ SF	9.2	7	2.2	0.50	Miss
LAA @ OAK	10.8	16	5.2	0.50	Hit
CIN @ ATL	9.5	4	5.5	0.57	Miss
NYM @ TEX	9.4	9	0.4	0.47	Hit
MIL @ PHI	8.6	10	1.4	0.59	Hit
STL @ PIT	8.0	2	6.0	0.57	Hit
CLE @ BOS	7.7	5	2.7	0.50	Hit
TB @ NYY	8.1	7	1.1	0.54	Miss
MIN @ SF	8.5	5	3.5	0.48	Hit
MIA @ CHC	9.0	10	1.0	0.57	Miss
SD @ LAD	9.1	7	2.1	0.52	Hit
HOU @ SEA	8.5	7	1.5	0.59	Miss
ARI @ COL	11.6	9	2.6	0.44	Hit
WSH @ DET	8.4	4	4.4	0.53	Miss
CWS @ KC	8.8	25	16.2	0.50	Miss
SD @ LAD	8.1	6	2.1	0.64	Miss
CIN @ ATL	8.1	5	3.1	0.71	Hit
ARI @ COL	11.2	8	3.2	0.38	Hit
CWS @ KC	9.1	9	0.1	0.51	Hit
NYM @ TEX	8.9	9	0.1	0.46	Hit
MIL @ PHI	8.1	5	3.0	0.50	Miss
STL @ PIT	8.3	6	2.3	0.53	Miss
HOU @ SEA	8.8	11	2.2	0.57	Hit
TB @ NYY	8.8	11	2.1	0.52	Hit
LAA @ OAK	10.4	10	0.4	0.50	Hit
MIA @ CHC	8.4	5	3.4	0.67	Miss
WSH @ DET	8.8	6	2.8	0.59	Miss
CLE @ BOS	8.0	1	7.0	0.54	Hit
TOR @ BAL	8.8	6	2.8	0.52	Hit
MIN @ SF	8.8	6	2.8	0.48	Hit
NYM @ TEX	8.5	4	4.5	0.50	Hit
MIA @ CHC	8.6	3	5.6	0.60	Hit
LAA @ SEA	8.8	10	1.2	0.55	Miss
MIL @ PHI	9.0	6	3.0	0.52	Miss
CIN @ ATL	8.6	13	4.4	0.64	Miss
SD @ LAD	8.0	6	2.0	0.60	Miss
ARI @ COL	11.1	20	8.9	0.43	Hit
STL @ PIT	8.2	3	5.2	0.59	Hit
CLE @ BOS	8.4	1	7.5	0.51	Miss
HOU @ OAK	10.1	12	1.9	0.51	Miss
TB @ NYY	8.0	10	2.0	0.55	Hit
CWS @ KC	9.1	10	0.9	0.51	Miss
STL @ MIL	8.8	12	3.2	0.57	Hit
ATL @ MIA	8.6	3	5.6	0.53	Hit
PIT @ DET	8.6	15	6.4	0.50	Hit
LAA @ SEA	8.6	12	3.4	0.52	Miss
TB @ PHI	8.3	2	6.3	0.52	Miss
CLE @ KC	8.4	21	12.6	0.47	Hit
NYM @ WSH	8.8	13	4.2	0.54	Hit
CIN @ TOR	8.8	11	2.2	0.53	Hit
TEX @ MIN	8.6	12	3.4	0.50	Hit
COL @ CWS	8.5	7	1.5	0.60	Hit
LAD @ SF	8.5	2	6.5	0.36	Hit
ARI @ SD	9.4	15	5.6	0.47	Hit
CIN @ TOR	8.6	6	2.6	0.58	Miss
COL @ CWS	8.8	15	6.2	0.64	Miss
CLE @ KC	9.3	16	6.7	0.50	Hit
LAD @ SF	8.7	7	1.7	0.37	Hit
HOU @ OAK	10.4	15	4.6	0.50	Miss
ARI @ SD	9.4	17	7.6	0.50	Hit
NYM @ WSH	8.9	8	0.9	0.46	Hit
TB @ PHI	8.6	13	4.4	0.50	Miss
STL @ MIL	8.9	5	3.9	0.55	Hit
ATL @ MIA	8.9	11	2.1	0.50	Hit
LAA @ SEA	8.5	12	3.5	0.55	Hit
TEX @ MIN	8.8	8	0.8	0.52	Miss
PIT @ DET	8.7	7	1.7	0.50	Hit

What the market says

A market we deliberately don't model: the market's own record

MLB run line

42.8% of −1.5 favorites cover

Across 11,972 final regular-season games with a standard run line, the moneyline favorite laying −1.5 covered 42.8% of the time and won outright 58.3%. We publish no run-line projection, because the market prices this one efficiently, so this is the market's record, not ours.

Market benchmark, not a Nebula projection.

One number: Lined vs unlined

A rotating look at how we grade ourselves

A model-vs-market number only counts games where we captured BOTH our projection and the market's line. Scoring on anything else would quietly flatter the model, so we don't.

Keep reading

The full record and the live board

Full track record All insights MLB board How we grade

How we did

Where the week's results came from

The biggest misses

Every graded game

What the market says

One number: Lined vs unlined

Keep reading

Get the weekly projections recap