
Rafael DeversOver 0.5 Hits · vs NYM-170
Dustin HarrisOver 0.5 Hits · vs NYY-108
MLB
Sun, Sep 6times in ETGames
15 scheduled · 15 with a report · 14 with a supported read · 14 started or final
- Sun, Sep 6 · 10:10 PM ETpregameWSH @ LADLAD · UNDER 8 · WSH +1.5model forecast · simulation
| Start | Game | Status | Our read | Report |
|---|---|---|---|---|
| Sun, Sep 6 · 10:10 PM ET | WSH @ LAD | pregame | LAD · UNDER 8 · WSH +1.5model forecast · simulation | View report for WSH @ LAD |
Started or final
- Sun, Sep 6 · 6:20 PM ETstartedMIN @ CWSMIN · UNDER 8.5 · MIN -1.5model forecast · simulation
- Sun, Sep 6 · 4:10 PM ETstartedATH @ SEAATH · OVER 7 · SEA +1.5model forecast · simulation
- Sun, Sep 6 · 4:10 PM ETstartedNYY @ SDSD · OVER 7 · NYY +1.5model forecast · simulation
- Sun, Sep 6 · 3:10 PM ETstartedSTL @ COLCOL · UNDER 11 · STL +1.5model forecast · simulation
- Sun, Sep 6 · 2:35 PM ETstartedTB @ TEXTEX · UNDER 7.5 · TB +1.5model forecast · simulation
- Sun, Sep 6 · 2:10 PM ETstartedAZ @ HOUAZ · UNDER 8 · HOU +1.5model forecast · simulation
- Sun, Sep 6 · 2:10 PM ETstartedTOR @ KCTOR · UNDER 9.5 · KC +1.5model forecast · simulation
- Sun, Sep 6 · 1:40 PM ETstartedDET @ CLECLE · UNDER 7 · DET +1.5model forecast · simulation
- Sun, Sep 6 · 1:40 PM ETstartedSF @ NYMNYM · UNDER 8 · SF +1.5model forecast · simulation
- Sun, Sep 6 · 1:40 PM ETstartedCHC @ MIACHC · OVER 8 · CHC -1.5model forecast · simulation
- Sun, Sep 6 · 1:35 PM ETstartedBOS @ BALBOS · OVER 7 · BAL +1.5model forecast · simulation
- Sun, Sep 6 · 1:35 PM ETstartedLAA @ PITPIT · OVER 7 · LAA +1.5model forecast · simulation
- Sun, Sep 6 · 1:10 PM ETstartedATL @ PHIATL · UNDER 8 · PHI +1.5model forecast · simulation
- Sun, Sep 6 · 12:10 PM ETstarted or finalMIL @ CINNo supported read
| Start | Game | Status | Our read | Report |
|---|---|---|---|---|
| Sun, Sep 6 · 6:20 PM ET | MIN @ CWS | started | MIN · UNDER 8.5 · MIN -1.5model forecast · simulation | View record for MIN @ CWS |
| Sun, Sep 6 · 4:10 PM ET | ATH @ SEA | started | ATH · OVER 7 · SEA +1.5model forecast · simulation | View record for ATH @ SEA |
| Sun, Sep 6 · 4:10 PM ET | NYY @ SD | started | SD · OVER 7 · NYY +1.5model forecast · simulation | View record for NYY @ SD |
| Sun, Sep 6 · 3:10 PM ET | STL @ COL | started | COL · UNDER 11 · STL +1.5model forecast · simulation | View record for STL @ COL |
| Sun, Sep 6 · 2:35 PM ET | TB @ TEX | started | TEX · UNDER 7.5 · TB +1.5model forecast · simulation | View record for TB @ TEX |
| Sun, Sep 6 · 2:10 PM ET | AZ @ HOU | started | AZ · UNDER 8 · HOU +1.5model forecast · simulation | View record for AZ @ HOU |
| Sun, Sep 6 · 2:10 PM ET | TOR @ KC | started | TOR · UNDER 9.5 · KC +1.5model forecast · simulation | View record for TOR @ KC |
| Sun, Sep 6 · 1:40 PM ET | DET @ CLE | started | CLE · UNDER 7 · DET +1.5model forecast · simulation | View record for DET @ CLE |
| Sun, Sep 6 · 1:40 PM ET | SF @ NYM | started | NYM · UNDER 8 · SF +1.5model forecast · simulation | View record for SF @ NYM |
| Sun, Sep 6 · 1:40 PM ET | CHC @ MIA | started | CHC · OVER 8 · CHC -1.5model forecast · simulation | View record for CHC @ MIA |
| Sun, Sep 6 · 1:35 PM ET | BOS @ BAL | started | BOS · OVER 7 · BAL +1.5model forecast · simulation | View record for BOS @ BAL |
| Sun, Sep 6 · 1:35 PM ET | LAA @ PIT | started | PIT · OVER 7 · LAA +1.5model forecast · simulation | View record for LAA @ PIT |
| Sun, Sep 6 · 1:10 PM ET | ATL @ PHI | started | ATL · UNDER 8 · PHI +1.5model forecast · simulation | View record for ATL @ PHI |
| Sun, Sep 6 · 12:10 PM ET | MIL @ CIN | started or final | No supported read | View record for MIL @ CIN |
MLB
Simulation CenterLive· 15 gamesMLB · 2026 seasonSlate · 2026-09-06MLB — today’s board
Home runs · batters · pitchers · teams · gamesMost likely to go deep today
The model's five highest home-run probabilities from 422 batter-vs-starter pairings. Each is its own number — this is not a card, and the five are not combined.
2 of these 5 face Aaron Nola — the model reads him as today's most homer-prone start, so the board clusters there on purpose.
- 1
Matt Olson
vs
ATL @ PHI · off Aaron Nola · Citizens Bank Park28.4%37 HR in 617 plate appearances (6.0% of trips, league 3.0%). Aaron Nola has been more homer-prone than average (32 allowed in 638 batters faced), lifting it to 28.4%.
- 2
Joc Pederson
vs
TB @ TEX · off Ian Seymour · Globe Life Field23.9%25 HR in 416 plate appearances (6.0% of trips, league 3.0%). Ian Seymour has been more homer-prone than average (20 allowed in 470 batters faced), lifting it to 23.9%.
- 3
Munetaka Murakami
vs
MIN @ CWS · off Bailey Ober · Rate Field23.6%30 HR in 468 plate appearances (6.4% of trips, league 3.0%). Bailey Ober has been more homer-prone than average (18 allowed in 477 batters faced), lifting it to 23.7%.
- 4
Kyle Schwarber
vs
ATL @ PHI · off Tyler Mahle · Citizens Bank Park23.3%41 HR in 610 plate appearances (6.7% of trips, league 3.0%). Tyler Mahle sits near league average for homers allowed (17 in 521), so the matchup barely moves it to 23.2%.
- 5
Michael Harris II
vs
ATL @ PHI · off Aaron Nola · Citizens Bank Park22.4%24 HR in 542 plate appearances (4.4% of trips, league 3.0%). Aaron Nola has been more homer-prone than average (32 allowed in 638 batters faced), lifting it to 22.4%.
How these are calculated, and what they leave out
Season HR per plate appearance, regressed to the league rate, scaled by the opposing probable starter's regressed HR-allowed rate, over a league-average number of trips to the plate.
League baseline is 3.0% of plate appearances, over 4.21 trips per lineup slot. A batter needs 120 plate appearances to be ranked at all, and every rate is pulled toward the league mean so a hot fortnight cannot top the board on its own.
Not in the model: park factor, weather and wind, batter/pitcher handedness split, batting-order slot (trips to the plate are a league average, not this batter's lineup spot), bullpen faced after the starter leaves.
Settled from official box scores: 13 of 88 graded picks homered against 21.5 expected. No accuracy claim is made at this sample size, and no home-run market price is fetched, so it makes no claim to beat a sportsbook. It is the model's own read, published so it can be measured.
Batter props
Hits · total bases · hits+runs+RBIs, filterable.Pitcher props
Strikeouts · outs recorded · earned runs, same filters.Team markets
Win probability, run line and total for every game — de-vigged.De-vigged sportsbook prices · the market’s read, not a model pick
Where the sportsbook is most confident
Shortest prices on the slate, de-vigged. This is the market's ranking, not ours — our model's read is the Homer Nukes board above.- 1

Bo BichetteHits 0.5 · San Francisco Giants @ New York Mets-29575% mkt - 2

Luis ArraezHits 0.5 · Atlanta Braves @ Philadelphia Phillies-27874% mkt - 3

TJ RumfieldHits 0.5 · St. Louis Cardinals @ Colorado Rockies-27573% mkt - 4

Chandler SimpsonHits 0.5 · Tampa Bay Rays @ Texas Rangers-26573% mkt - 5

Yordan AlvarezHits 0.5 · Arizona Diamondbacks @ Houston Astros-26573% mkt - 6

Cole CarriggHits 0.5 · St. Louis Cardinals @ Colorado Rockies-26072% mkt
Game Explorer
Every game on the slate — tap a card for first pitch, featured props & pitchers on the board.Open a game's full distribution
Every game on the slate simulated pitch by pitch from the posted lineups — win probability, the run-total distribution, the likeliest final scores, the run line and a simulated box score. These are the model's own numbers and are not compared against any sportsbook price.
MIL at CIN
even in the simulation
batting order not posted yet · refreshes hourly
Open the simulation →
ATL at PHI
ATL 51.1% · median 7 runs
likeliest 2–3 at 3.9%
batting order not posted yet · refreshes hourly
Open the simulation →
BOS at BAL
BOS 54.1% · median 7 runs
likeliest 3–4 at 3.8%
Open the simulation →
LAA at PIT
PIT 60.7% · median 7 runs
likeliest 2–3 at 4.0%
Open the simulation →
DET at CLE
CLE 52.3% · median 6 runs
likeliest 1–2 at 4.7%
Open the simulation →
SF at NYM
NYM 50.7% · median 7 runs
likeliest 2–3 at 4.2%
Open the simulation →
CHC at MIA
CHC 69.8% · median 9 runs
likeliest 3–4 at 2.5%
Open the simulation →
AZ at HOU
AZ 53.3% · median 7 runs
likeliest 2–3 at 4.0%
Open the simulation →
TOR at KC
TOR 57.2% · median 7 runs
likeliest 1–2 at 3.4%
Open the simulation →
TB at TEX
TEX 53.7% · median 7 runs
likeliest 2–3 at 4.2%
Open the simulation →
STL at COL
COL 59.8% · median 7 runs
likeliest 2–3 at 4.0%
Open the simulation →
ATH at SEA
ATH 56.6% · median 8 runs
likeliest 2–3 at 3.4%
batting order not posted yet · refreshes hourly
Open the simulation →
NYY at SD
SD 50.9% · median 7 runs
likeliest 3–4 at 3.7%
Open the simulation →
MIN at CWS
MIN 65.7% · median 8 runs
likeliest 2–3 at 3.0%
Open the simulation →
WSH at LAD
LAD 52.1% · median 7 runs
likeliest 2–3 at 4.4%
batting order not posted yet · refreshes hourly
Open the simulation →
11 of 15 are built on both confirmed batting orders; the rest use the batters who have posted lines so far and refresh as the orders arrive.
How the model's picks actually turned out
Player-prop projections: the model's over/under lean against the book's line, graded from the official box score.
38519 graded picks. A hit rate is still not proof a model beats a price — that requires a preregistered comparison against the closing line, which is tracked separately per sport.
A model-performance record, independent of the paper bankroll. It shares no row with the settled money record on /results.
| Date | Event | Model said | What happened | Result |
|---|---|---|---|---|
| 2026-09-05 | Ryan Gusto · MIA v CHC | Under 3.5 · 66.5% | 5 | MISS |
| 2026-09-05 | Javier Assad · CHC v MIA | Under 3.5 · 84.1% | 3 | HIT |
| 2026-09-05 | Pete Crow-Armstrong · CHC v MIA | Over 1.5 · 37.9% | 1 | MISS |
| 2026-09-05 | Nico Hoerner · CHC v MIA | Over 0.5 · 72.2% | 3 | HIT |
| 2026-09-05 | Otto Lopez · MIA v CHC | Over 0.5 · 72.1% | 1 | HIT |
| 2026-09-05 | Alex Bregman · CHC v MIA | Over 0.5 · 77.8% | 0 | MISS |
Showing the 6 most recent of 38,519 graded.
Card at each risk level · 2026-09-06
The model’s highest-scoring card in each price band, one per tier, tracked separately from every money product here. The live record restarted when the selection rules changed; what the previous policy did is shown above rather than carried forward.

Lawrence ButlerOver 1.5 Hits + Runs + RBIs · vs SEA+121
Pete Crow-ArmstrongOver 1.5 Total Bases · vs MIA-109
Alex BregmanOver 1.5 Hits + Runs + RBIs · vs MIA-119
Wilyer AbreuOver 1.5 Total Bases · vs BAL+140
Riley GreeneOver 0.5 Hits + Runs + RBIs · vs CLE-164
Paper stream with its own ledger · never part of the Bank Builder / Moonshot bankroll or the settled product record
How the MLB simulation works
market-anchored + 10,000-run player-prop sim- · Team markets (moneyline / run line / total) are the de-vigged sportsbook lines — a market-anchored read, settled from the official box score.
- · Player props (strikeouts / hits / total bases) use a 10,000-run simulation from MLB Stats API game logs where the artifact exists; otherwise a projection vs the line.
- · There is no independent full-game score model yet — full-game outcomes are market-implied and labelled experimental. Team totals stay out of product cards until settlement is proven.
Market-by-market coverage below
What we simulate — and what we don’t (yet)
Every market we cover, plus the ones we don’t — with the exact reason (provider feed, settlement, or validation). We never show a market we can’t back with real data.
De-vigged sportsbook moneyline. Settled from the official box score.
De-vigged run line. Settled from the official final score.
De-vigged total. Settled from the official final score.
Strikeouts / hits / total bases projected from game logs vs the line; a 10,000-run prop sim is shown only where the artifact exists. Settled from the official box score.
Full-game outcomes are currently MARKET-IMPLIED (from the de-vigged lines), not an independent score simulation. An independent, backtested sim is on the roadmap — not claimed until validated.
Team totals can be read from odds but are not yet settlement-validated, so they stay out of product cards until grading is proven.
Settlement: pending · needs: Odds API team-total lines, team-total settlement source
First-5-innings markets are planned; they need the F5 line feed and inning-level settlement.
Settlement: pending · needs: Odds API F5 lines, F5 settlement (linescore innings 1-5)
9 supported · 5 need a provider/build · settlement-blocked + experimental markets are never in Bank Builder / Moonshot.
What the model is most confident about today
What each simulation is most confident about today, ranked by the model's own probability — not by any gap against a sportsbook price. A watchlist, not a bet.
mlb — Its modelled markets were measured against the sportsbook and demoted to market context — the simulation is published, not claimed to beat a price.
NFL — not listed: the model does not currently tell these teams apart — its team-strength term was measured and found not to be statistically significant, so it produces near-identical reads for every game.
Paper-only and educational. Nothing here is a pick or a recommendation to wager, and no stake is filled in anywhere on this site.
