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

MLB projections vs. the market

Week of Sep 7 to 13, 2026 (2026-W37) · model clean_v2 · generated Sep 14, 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, Sep 7 to 13, 2026 · reports, not picks
Games graded
88
2026-W37
Moneyline record
57-31
64.8% higher-prob side
our >50% side won
Moneyline Brier
0.232
better than 0.250 coin flip
lower is better
Totals avg miss
3.57
runs |proj − actual|
88 games
Totals vs market
-0.03
leads market (3.57 vs 3.60)
88 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 team45–2166
Model's side was the road team10–818
Model's side was the market favorite39–2160
Model's side was the market underdog15–1025
Coin-flip calls (50-55%)38–2664
Moderate calls (55-65%)16–521
Strongest calls (65%+)not scored: below the n=5 floor (n=3)
Games with a total under 8.531–1243
Games with a total 8.5-9.526–1945
Games with a total above 9.5not scored: no opening total captured for these games (n=0)
Totals splitOur avg missMarket'sn
Projection sat above the line3.693.7283
Projection sat below the line1.571.55
Lines under 8.53.643.743
Lines 8.5-9.53.53.545
Lines above 9.5not scored: no opening total captured for these games (n=0)
Confidence bucketWe saidIt happenedn
Coin-flip calls (50-55%)52.2%59.4%64
Moderate calls (55-65%)58.3%76.2%21
Strongest calls (65%+)not scored: below the n=5 floor (n=3)

League base rates for the same games: home teams went 55–33 (n=88); market favorites went 49–36 (57.6%, n=85); overs went 50–34 against the line (n=88). Every model result above sits inside that backdrop.

The three largest totals misses account for 13.7% of the week's total absolute totals error (43.0 of 314.1 runs across 88 games).

Strongest call that landed

COL @ NYY (Sep 8): we had the home side at 72%; the home side won.

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

HOU @ PHI (Sep 10): we had the home side at 60%; the away side won. It stays in the record.

Final HOU 2, PHI 1; opening price on that side -175; total 8.5; 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 7 to 13, 2026

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

GameProjectedActualOff by
NYM @ MIA8.72920.3
CIN @ MIL9.92212.1
CIN @ MIL9.42010.6

Every graded game

Projected total vs. actual, and whether our higher-probability moneyline side won · 88 games
GameProj totalActualMissHome win%ML side
CHC @ MIL9.272.20.50Miss
CLE @ BAL8.9101.10.54Hit
LAA @ BOS9.272.20.52Hit
NYM @ MIA8.9134.00.53Miss
WSH @ SD8.953.90.54Hit
TOR @ OAK9.9111.10.53Hit
STL @ SF9.290.20.55Hit
MIN @ DET9.190.10.50Miss
CIN @ LAD9.690.60.50Miss
ARI @ KC8.590.50.50Miss
ATL @ PHI8.517.50.60Hit
MIN @ DET9.254.20.47Hit
LAA @ BOS8.371.30.51Miss
WSH @ SD9.990.90.57Hit
CLE @ BAL9.4144.60.52Miss
NYM @ MIA9.0123.00.50Hit
STL @ SF8.635.60.53Hit
CHC @ MIL9.172.10.56Hit
TEX @ SEA9.3155.70.51Miss
HOU @ PHI8.8112.20.56Miss
COL @ NYY9.381.30.72Hit
TOR @ OAK10.664.60.50Miss
TB @ ATL8.880.80.48Hit
ARI @ KC8.580.50.50Miss
CIN @ LAD9.154.10.61Hit
PIT @ CWS9.4122.60.50Miss
ARI @ KC8.471.40.50Hit
COL @ NYY10.073.00.67Hit
TOR @ OAK10.328.30.52Hit
CIN @ LAD9.0156.00.60Hit
WSH @ SD9.8111.20.57Hit
MIN @ DET10.091.00.46Miss
STL @ SF8.7134.30.52Hit
NYM @ MIA8.72920.30.50Hit
PIT @ CWS9.063.00.50Hit
LAA @ BOS8.8101.20.54Miss
TB @ ATL9.590.50.48Hit
CLE @ BAL9.4144.60.54Hit
CHC @ MIL8.9145.10.57Hit
TEX @ SEA9.754.70.52Hit
HOU @ PHI8.3189.70.60Hit
HOU @ PHI8.935.90.59Miss
TEX @ SEA9.072.00.53Hit
TB @ ATL9.245.20.49Miss
PIT @ CWS8.826.80.45Hit
COL @ NYY9.3133.70.67Hit
CIN @ MIL9.42010.60.55Hit
CLE @ MIN9.272.20.54Miss
HOU @ TB8.544.50.60Hit
LAA @ WSH8.571.50.57Hit
SD @ SF8.9123.10.47Hit
KC @ BOS8.853.80.55Miss
NYM @ NYY8.8101.20.54Hit
BAL @ TOR8.6112.50.54Miss
CWS @ STL9.4100.60.52Hit
PHI @ ATL8.2112.80.51Hit
SEA @ OAK10.3110.70.51Hit
COL @ DET8.980.90.60Hit
CIN @ MIL9.92212.10.54Hit
SD @ SF8.6134.40.46Hit
CWS @ STL9.5111.50.50Miss
PIT @ CHC9.672.60.52Hit
SEA @ OAK9.82010.20.51Miss
HOU @ TB8.553.50.55Hit
CLE @ MIN9.272.20.57Hit
PHI @ ATL8.6145.40.55Hit
LAD @ MIA8.471.40.44Miss
BAL @ TOR8.5101.50.50Hit
TEX @ ARI9.881.80.53Miss
COL @ DET9.7188.30.56Hit
LAA @ WSH9.4111.60.52Hit
KC @ BOS9.063.00.51Hit
NYM @ NYY9.0145.00.59Miss
PIT @ CHC9.672.60.52Miss
KC @ BOS8.253.20.52Hit
CIN @ MIL9.472.40.59Miss
SEA @ OAK10.4154.60.54Hit
NYM @ NYY8.426.40.59Hit
LAA @ WSH9.6111.40.50Hit
SD @ SF8.5101.50.49Hit
PHI @ ATL8.7134.30.50Miss
COL @ DET10.291.10.60Hit
CLE @ MIN9.3111.70.53Miss
LAD @ MIA8.5101.50.45Miss
CWS @ STL9.145.10.50Miss
HOU @ TB8.7189.30.54Hit
TEX @ ARI8.8134.20.53Miss
BAL @ TOR8.390.70.54Hit

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: Mean absolute error (MAE)

A rotating look at how we grade ourselves

Our totals number is graded on average miss: |projected runs − actual runs|. In our held-out research backtest the model's MAE is 3.52 runs versus the market's 3.46: we trail by 0.06. We say so plainly.

Keep reading

The full record and the live board