Home / Insights / MLB Model vs Market
Model vs Market · Week in Review

MLB projections vs. the market

Week of Aug 31 to Sep 6, 2026 (2026-W36) · model clean_v2 · generated Sep 7, 2026

A report, not advice. Every projection below was logged before first pitch in our immutable record and graded after the game. nothing is added or removed later. We publish no pick, lean or edge; this page reports how our numbers did, including the misses. The market's line is shown for context only.

How we did

Graded MLB games, Aug 31 to Sep 6, 2026 · reports, not picks
Games graded
67
2026-W36
Moneyline record
32-35
47.8% higher-prob side
our >50% side won
Moneyline Brier
0.252
vs 0.250 coin flip
lower is better
Totals avg miss
3.38
runs |proj − actual|
67 games
Totals vs market
-0.05
leads market (3.38 vs 3.43)
67 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 splitRecordn
Model's side was the home team19–2443
Model's side was the road team13–922
Model's side was the market favorite23–2245
Model's side was the market underdog9–1019
Coin-flip calls (50-55%)22–2648
Moderate calls (55-65%)10–919
Strongest calls (65%+)not scored: below the n=5 floor (n=0)
Games with a total under 8.519–1332
Games with a total 8.5-9.511–1829
Games with a total above 9.52–46
Totals splitOur avg missMarket'sn
Projection sat above the line3.463.5261
Projection sat below the line2.592.56
Lines under 8.52.812.9732
Lines 8.5-9.53.983.9729
Lines above 9.53.483.256
Confidence bucketWe saidIt happenedn
Coin-flip calls (50-55%)51.8%45.8%48
Moderate calls (55-65%)58.4%52.6%19
Strongest calls (65%+)not scored: below the n=5 floor (n=0)

League base rates for the same games: home teams went 28–39 (n=67); market favorites went 32–32 (50.0%, n=64); overs went 36–27 against the line (n=67). Every model result above sits inside that backdrop.

The three largest totals misses account for 16.1% of the week's total absolute totals error (36.4 of 226.5 runs across 67 games).

Strongest call that landed

WSH @ LAD (Sep 4): we had the home side at 61%; the home side won.

Final WSH 3, LAD 5; opening price on that side -325; total 8; the archived probables started.
Strongest call that missed

OAK @ SEA (Sep 4): we had the home side at 60%; the away side won. It stays in the record.

Final OAK 7, SEA 6; opening price on that side -235; total 7; 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, Aug 31 to Sep 6, 2026

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

GameProjectedActualOff by
SF @ PIT9.02516.0
STL @ LAD9.32111.7
BOS @ BAL9.818.8

Every graded game

Projected total vs. actual, and whether our higher-probability moneyline side won · 67 games
GameProj totalActualMissHome win%ML side
SF @ PIT9.02516.00.52Hit
SEA @ BOS8.8156.20.52Miss
NYY @ LAA8.3101.60.46Hit
CWS @ HOU9.363.30.51Miss
MIA @ KC9.090.00.51Miss
BAL @ COL11.565.50.44Miss
STL @ LAD9.32111.70.53Miss
PHI @ ARI8.780.70.44Hit
NYM @ TB8.780.70.52Hit
MIL @ CHC9.7133.30.57Miss
SD @ CIN10.373.30.50Miss
TOR @ CLE9.872.80.57Hit
DET @ MIN9.5177.50.53Hit
OAK @ TEX9.2133.80.60Hit
ATL @ WSH9.7144.30.51Hit
SEA @ BOS8.8112.20.57Miss
NYM @ TB8.7145.30.59Miss
ATL @ WSH9.190.10.50Miss
BAL @ COL11.4110.40.46Miss
CWS @ HOU8.826.80.55Hit
TOR @ CLE8.9112.10.49Hit
NYY @ LAA8.091.00.46Hit
MIA @ KC9.1155.90.52Miss
SF @ PIT9.390.30.50Hit
OAK @ TEX8.5112.50.52Miss
DET @ MIN9.1177.90.60Miss
MIL @ CHC9.3144.70.47Hit
SD @ CIN10.2100.20.46Miss
TB @ TEX8.862.80.51Hit
OAK @ SEA9.1111.90.53Miss
STL @ LAD8.353.30.60Hit
BOS @ BAL10.0111.00.50Miss
MIL @ CHC8.735.70.50Miss
MIA @ KC9.6100.40.53Hit
CWS @ HOU9.281.20.56Hit
TOR @ CLE9.690.60.51Miss
SF @ PIT9.072.00.50Miss
STL @ COL11.5131.50.48Hit
NYY @ SD8.753.70.48Miss
ARI @ HOU8.944.90.51Hit
CHC @ MIA8.371.30.50Miss
SF @ NYM9.4166.60.60Hit
ATL @ PHI7.670.60.50Miss
DET @ CLE9.072.00.57Hit
OAK @ SEA9.4133.60.60Miss
LAA @ PIT8.617.60.53Hit
MIN @ CWS10.055.00.46Miss
TB @ TEX9.6133.40.50Hit
BOS @ BAL9.818.80.52Miss
MIL @ CIN10.3176.70.50Hit
TOR @ KC9.4111.60.53Miss
WSH @ LAD8.780.70.61Hit
ATL @ PHI9.063.00.55Hit
LAA @ PIT8.471.40.60Miss
MIL @ CIN10.282.20.50Hit
DET @ CLE8.662.60.59Miss
MIN @ CWS8.8101.20.47Hit
WSH @ LAD8.6112.40.59Hit
TB @ TEX8.890.20.50Miss
TOR @ KC10.173.10.50Miss
CHC @ MIA8.8112.20.50Miss
NYY @ SD9.063.00.50Hit
SF @ NYM9.5144.50.59Miss
ARI @ HOU9.172.10.46Hit
OAK @ SEA9.181.10.52Miss
BOS @ BAL9.454.40.50Hit
STL @ COL11.0176.00.46Miss

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: Brier score

A rotating look at how we grade ourselves

For our moneyline probabilities, Brier squares the gap between the win probability we published and what happened (1 or 0), then averages it. 0.250 is a coin flip; lower is better. Reported live, never smoothed.

Keep reading

The full record and the live board