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

MLB projections vs. the market

Week of Aug 3 to 9, 2026 (2026-W32) · model clean_v2 · generated Aug 15, 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 3 to 9, 2026 · reports, not picks
Games graded
83
2026-W32
Moneyline record
49-34
59.0% higher-prob side
our >50% side won
Moneyline Brier
0.243
better than 0.250 coin flip
lower is better
Totals avg miss
3.46
runs |proj − actual|
83 games
Totals vs market
+0.16
trails market (3.46 vs 3.30)
83 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 team37–2259
Model's side was the road team12–1224
Model's side was the market favorite40–2969
Model's side was the market underdog8–513
Coin-flip calls (50-55%)28–2149
Moderate calls (55-65%)21–1334
Strongest calls (65%+)not scored: below the n=5 floor (n=0)
Games with a total under 8.520–929
Games with a total 8.5-9.526–2349
Games with a total above 9.53–25
Totals splitOur avg missMarket'sn
Projection sat above the line3.483.2868
Projection sat below the line3.363.415
Lines under 8.53.072.7129
Lines 8.5-9.53.473.4649
Lines above 9.55.535.25

Reliability: Not shown for this week. The serving calibrator changed on Aug 4 and this window spans that date, so the published probabilities in it come from two different calibrators. Averaging them together would describe neither. The win-loss counts above are unaffected.

League base rates for the same games: home teams went 49–34 (n=83); market favorites went 45–37 (54.9%, n=82); overs went 37–42 against the line (n=83). Every model result above sits inside that backdrop.

The three largest totals misses account for 12.6% of the week's total absolute totals error (36.1 of 287.0 runs across 83 games).

Strongest call that landed

TB @ COL (Aug 3): we had the away side at 64%; the away side won.

Final TB 13, COL 9; opening price on that side -160; total 11.5; the archived probables started.
Strongest call that missed

TOR @ PHI (Aug 8): we had the home side at 64%; the away side won. It stays in the record.

Final TOR 7, PHI 5; opening price on that side -160; total 10; the archived probables started.

The serving calibrator changed on Aug 4, inside this window; each game is scored on the probability that was actually served for it.

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 3 to 9, 2026

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

GameProjectedActualOff by
CWS @ BOS9.02314.0
STL @ NYY8.62011.4
TB @ COL11.22210.8

Every graded game

Projected total vs. actual, and whether our higher-probability moneyline side won · 83 games
GameProj totalActualMissHome win%ML side
STL @ NYY8.62011.40.59Miss
SF @ TEX9.963.90.49Hit
SD @ ARI9.963.90.54Hit
WSH @ PHI9.890.80.56Hit
TOR @ HOU9.445.40.56Miss
PIT @ MIL8.971.90.56Miss
TB @ COL11.22210.80.36Hit
LAD @ CHC8.9156.10.56Hit
CWS @ BOS9.1166.90.51Hit
SD @ ARI10.8132.20.53Miss
STL @ NYY8.826.80.57Hit
TOR @ HOU9.690.60.52Hit
PIT @ MIL8.662.60.59Hit
MIN @ KC9.6100.40.50Miss
WSH @ PHI9.654.60.61Hit
MIA @ ATL9.363.30.52Hit
NYM @ CLE8.380.30.50Hit
LAD @ CHC8.662.60.44Miss
OAK @ CIN8.990.10.57Hit
LAA @ BAL9.345.30.52Hit
MIA @ ATL8.953.90.50Miss
SF @ TEX9.363.30.51Hit
CWS @ BOS9.045.00.49Miss
SD @ ARI10.3143.60.46Miss
STL @ NYY9.245.20.59Miss
PIT @ MIL8.162.10.53Hit
LAD @ CHC9.4133.60.52Hit
OAK @ CIN9.354.30.54Hit
TOR @ HOU9.490.40.62Miss
NYM @ CLE8.7112.30.46Hit
WSH @ PHI9.7144.30.51Miss
TB @ COL11.847.80.44Hit
DET @ SEA9.163.00.60Hit
MIN @ KC9.536.50.52Hit
LAA @ BAL8.171.10.58Hit
NYM @ CLE9.3199.70.44Hit
PIT @ MIL8.771.70.57Hit
LAA @ BAL8.853.90.57Miss
MIA @ ATL9.1144.90.52Hit
OAK @ CIN9.0112.00.60Hit
MIN @ KC9.272.20.52Miss
SD @ ARI10.264.20.51Miss
TOR @ CHC7.652.60.53Hit
DET @ SEA8.9112.10.52Miss
WSH @ PHI9.8100.20.61Hit
CWS @ BOS9.02314.00.53Hit
HOU @ SD8.690.40.50Miss
BAL @ TEX9.836.80.53Hit
TB @ SEA8.635.60.52Miss
COL @ STL9.154.10.59Hit
OAK @ BOS8.9145.10.59Hit
NYM @ PIT9.3100.70.47Hit
CLE @ CWS9.1100.90.50Miss
LAA @ MIA8.771.60.60Miss
TOR @ PHI9.090.00.63Miss
ATL @ NYY9.054.00.53Hit
TOR @ PHI9.3122.70.64Miss
CIN @ WSH9.9100.10.44Miss
LAD @ ARI9.536.50.44Hit
CLE @ CWS8.290.80.50Miss
DET @ SF8.880.80.50Hit
ATL @ NYY9.190.10.47Miss
LAA @ MIA8.771.70.54Hit
OAK @ BOS9.5100.50.59Miss
HOU @ SD9.054.00.50Hit
TB @ SEA9.154.00.50Miss
COL @ STL8.7145.30.57Miss
MIN @ MIL9.272.20.52Hit
NYM @ PIT9.490.40.50Miss
BAL @ TEX9.563.50.47Miss
CHC @ KC9.390.30.46Miss
NYM @ PIT8.9123.10.50Hit
LAA @ MIA8.7156.30.54Hit
COL @ STL10.0111.00.60Hit
LAD @ ARI9.964.00.50Hit
TOR @ PHI9.3133.70.61Hit
CLE @ CWS9.081.00.52Hit
DET @ SF8.544.50.50Hit
BAL @ TEX9.6155.40.52Miss
MIN @ MIL8.371.30.59Hit
CHC @ KC9.8122.20.38Hit
ATL @ NYY9.536.50.55Miss
CIN @ WSH10.082.00.46Miss

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