MLB · model accountability
Every prediction we've made on MLB games, with every result. Pre-game probabilities are frozen at the moment of prediction — the backtest never reads from a future rating.
Hit rate
55.1%
1650 / 2996 games
Home-always baseline
53.5%
Naive: pick home every time
Edge over naive
+1.6pp
What the model adds
Calibration gap
0pp
Avg pred 53.5% vs actual 53.5%
By confidence bucket
Buckets defined by edge from 50%: tossup < 4pp, lean 4–8pp, edge 8–15pp, lock ≥ 15pp.
| Bucket | Games | Wins | Hit rate |
|---|---|---|---|
| tossup | 1152 | 608 | 52.8% |
| lean | 899 | 483 | 53.7% |
| edge | 741 | 420 | 56.7% |
| ★ Lock | 204 | 139 | 68.1% |
Best calls
Highest-confidence games where the model was right. The receipts.
Worst misses
Highest-confidence games where the model was wrong. Honest accounting.
Recent results
TOR pick 57%
TOR 7 – 3 MIN
May 2, 26 · vs MIN
LAD pick 56%
LAD 2 – 7 STL
May 2, 26 · vs STL
ATL pick 65%
ATL 8 – 6 COL
May 2, 26 · vs COL
LAA pick 52%
NYM 4 – 3 LAA
May 2, 26 · vs NYM
SD pick 64%
CHW 8 – 2 SD
May 2, 26 · vs CHW
ATH pick 54%
CLE 8 – 5 ATH
May 2, 26 · vs CLE
SEA pick 60%
KC 7 – 6 SEA
May 2, 26 · vs KC
CHC pick 61%
ARI 5 – 6 CHC
May 1, 26 · vs ARI
DET pick 52%
TEX 5 – 4 DET
May 1, 26 · vs TEX
PIT pick 50%
CIN 1 – 9 PIT
May 1, 26 · vs CIN
MIL pick 58%
MIL 6 – 1 WSH
May 1, 26 · vs WSH
NYY pick 66%
BAL 2 – 7 NYY
May 1, 26 · vs BAL
How we report this
Every row above carries the probability we'd have shown you before first pitch — never a backfilled rating. A game counted as "model right" if the team we favored won, regardless of margin. Hit rate is total wins divided by total finals. No selection bias, no excluded results.
← Tonight's slate