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

MLB projections vs. the market

Week of Aug 17 to 23, 2026 (2026-W34) · model clean_v2 · generated Aug 24, 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 17 to 23, 2026 · reports, not picks
Games graded
67
2026-W34
Moneyline record
49-18
73.1% higher-prob side
our >50% side won
Moneyline Brier
0.229
better than 0.250 coin flip
lower is better
Totals avg miss
3.50
runs |proj − actual|
67 games
Totals vs market
+0.22
trails market (3.50 vs 3.28)
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 team41–1253
Model's side was the road team7–613
Model's side was the market favorite45–1358
Model's side was the market underdog4–48
Coin-flip calls (50-55%)33–1346
Moderate calls (55-65%)14–519
Strongest calls (65%+)not scored: below the n=5 floor (n=2)
Games with a total under 8.527–1037
Games with a total 8.5-9.516–824
Games with a total above 9.56–06
Totals splitOur avg missMarket'sn
Projection sat above the line3.593.3461
Projection sat below the line2.552.586
Lines under 8.53.313.1637
Lines 8.5-9.53.983.6524
Lines above 9.52.732.56
Confidence bucketWe saidIt happenedn
Coin-flip calls (50-55%)52.1%71.7%46
Moderate calls (55-65%)59.3%73.7%19
Strongest calls (65%+)not scored: below the n=5 floor (n=2)

League base rates for the same games: home teams went 48–19 (n=67); market favorites went 50–16 (75.8%, n=66); overs went 31–35 against the line (n=67). Every model result above sits inside that backdrop.

The three largest totals misses account for 11.9% of the week's total absolute totals error (27.8 of 234.5 runs across 67 games).

Strongest call that landed

TOR @ NYY (Aug 21): we had the home side at 67%; the home side won.

Final TOR 1, NYY 3; opening price on that side -231; total 7.5; the archived probables started.
Strongest call that missed

TOR @ NYY (Aug 22): we had the home side at 60%; the away side won. It stays in the record.

Final TOR 4, NYY 3; opening price on that side -110; 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, Aug 17 to 23, 2026

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

GameProjectedActualOff by
SEA @ MIL9.72212.3
SF @ CLE9.018.0
OAK @ KC8.6167.5

Every graded game

Projected total vs. actual, and whether our higher-probability moneyline side won · 67 games
GameProj totalActualMissHome win%ML side
ARI @ BOS8.8123.20.50Hit
ATL @ MIN9.963.90.44Miss
OAK @ KC8.7145.30.55Hit
LAD @ COL11.4164.60.46Hit
CWS @ CHC8.4123.60.59Hit
STL @ CIN8.8112.20.53Hit
BAL @ TB8.7134.30.51Hit
MIA @ PHI8.6112.40.53Hit
SD @ NYM8.835.80.57Hit
DET @ PIT9.0134.00.50Hit
ATL @ MIN9.454.40.46Miss
WSH @ TEX10.055.00.53Hit
DET @ PIT9.254.20.53Hit
NYY @ BAL9.745.70.50Miss
CWS @ CHC9.072.00.59Hit
SD @ NYM9.372.30.49Hit
OAK @ KC9.472.40.53Hit
LAA @ HOU9.345.30.60Miss
ARI @ BOS8.8134.20.52Hit
STL @ CIN9.036.00.51Miss
SEA @ MIL9.72212.30.57Hit
TOR @ TB8.9156.10.60Miss
SF @ CLE9.590.50.51Hit
MIA @ PHI8.7101.30.54Hit
LAD @ COL11.8131.20.38Hit
SEA @ MIL8.1124.00.52Miss
STL @ CIN8.890.20.52Hit
OAK @ KC8.6167.50.54Hit
LAD @ COL11.1101.10.41Hit
SD @ NYM9.463.40.46Miss
MIA @ PHI8.953.90.52Hit
SF @ CLE9.018.00.51Miss
WSH @ TEX9.463.40.51Miss
DET @ PIT8.871.80.54Hit
ARI @ BOS8.8134.20.52Miss
TOR @ TB8.7134.30.65Hit
NYY @ BAL9.181.10.51Miss
ATL @ MIN9.5100.50.50Hit
CWS @ CHC9.136.00.53Miss
LAA @ HOU9.454.40.54Hit
LAA @ TEX8.435.40.53Hit
CLE @ COL12.4102.40.38Hit
TB @ BAL8.980.90.51Hit
CHC @ SEA9.3111.70.50Hit
CIN @ ARI9.690.60.55Hit
NYM @ CWS8.6101.40.49Miss
MIN @ SD9.281.20.50Hit
PIT @ LAD9.190.10.59Hit
WSH @ MIA8.853.80.57Hit
STL @ PHI8.2134.80.54Hit
OAK @ HOU9.245.20.59Hit
SF @ BOS8.4101.60.55Hit
TOR @ NYY8.444.40.67Hit
ATL @ MIL7.534.50.51Hit
DET @ KC8.871.80.51Hit
TOR @ NYY8.171.10.60Miss
CHC @ SEA9.690.60.48Miss
ATL @ MIL9.054.00.59Hit
MIN @ SD9.1122.90.50Hit
DET @ KC9.045.00.52Hit
PIT @ LAD9.172.10.60Hit
STL @ PHI8.8156.20.52Hit
SF @ BOS8.853.80.54Hit
OAK @ HOU8.671.60.59Miss
TB @ BAL9.154.10.48Miss
CLE @ COL11.774.70.38Hit
WSH @ MIA8.662.60.59Hit

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: Why we show the losses

A rotating look at how we grade ourselves

Every projection is logged before first pitch, immutably, and graded after the game. Nothing is added or removed later. The misses stay in. A record you can only read forward is the only kind worth trusting.

Keep reading

The full record and the live board