Saratoga & Del Mar · 2026 Meets · Model v0 · the anti-tout
Transparent model race-cards

Del Mar — Sun Jul 26, 2026

4 value plays today · 7 races we're passing
Edge of the Day
5COME ON OM
Race 5 · 5 furlongs turf
29%model5/2fair4/1boardWINpaid at the close
Our biggest edge on the card today (+13 pts over the board) — the crowd will likely bet it down, so expect a shorter number — size it smaller. Chosen by rule: the flag with the most value, graded like any other.
Public record11–35flags, W–L-24.7uflat-$2-26.9%flat-bet ROI, n=46every call hash-stamped before post →

We lose most single flags — that’s expected. The edge is price: when we’re right, the board paid more than fair. Our 30% picks win about 30% (see the calibration curve), and every call is graded against the closing odds — wins and losses.

No set price. On the tote you’re paid the closing odds, so the edge isn’t a line you beat early — it’s the gap between our fair number and where the crowd lands. We grade each flag against the actual close.

Our last miss: SAR R11 Tuthilltown, flagged at 12/1, didn’t win — on the record like every call.

Today at Del MarMostly Cloudy, 69°F, wind 0 to 5 mph · rain 1% — no off-track flagNWS forecast
How this card is made & how to verify it

Edge Card v0 is a transparent heuristic, not a trained model: Prime-Power softmax blended 65/35 with the de-vigged morning line, plus published rules-based pace and trainer-form adjustments (the trainer angle is used as a model input; the raw figure is never published). Constants on the methodology page. Structured analysis, not proven edge; tracked publicly either way.

It reads Brisnet figures, pace, and trainer form — not jockey, trip, or track bias yet; those arrive with the trained v1 model. The trainer angle is used as a model input only; we never publish the raw figure. Fair odds are 1 ÷ our win probability.

The hold/shorten read on each flag is an early signal from its committed board price — long-priced flags the crowd leaves alone tend to hold, short ones get bet down. It’s a heuristic on a small sample; every call is graded on the record.

Model v0-heuristic-1.4 · cfg aab788cb · code 3c797c7f · takeout (DMR) win 15.43% / exacta 22.68% · card SHA-256 ee2f7ccdc08a… · Scratches as of 12:03 AM ET (lock time — no scratches posted yet; first post 13h away). Late scratches void at scoring; the card is never edited.

Powered by Brisnet data
Flags 4 of 11 races
New here? How to read a flag
Model
Our estimated win chance for the horse.
Fair
The odds that chance implies — the price where a bet breaks even.
Board
The morning line, the track's early guess at the odds.
Win bet
Bet the horse to win. Pari-mutuel pays the closing price no matter when you bet, so you're backing the horse, not a fixed price.
Hold / bet down
Whether the price should stay long or get bet down by post — how much of the edge is likely to survive.
The rest of the card
Most races. We still show our top pick and a read on it, but there's no overlay worth a bet.

Odds note: 7/2 is the same as +350.

Race 4 · 1 mile · dirt · OClm 50000n1xFlag
4RABEEBA
Model
Fair
Board
22%
7/2
5/1
our win %
break-even
the morning line
We flag it because the board (5/1) pays more than our fair price (7/2). Same horse, longer price.
The market
13%
Edge Card
22% +8 pts
▸ WIN BET · #4 to win · our fair 7/2, paid at the close
Price may move A mid board price — it can hold or shorten into post. You are paid the closing price either way, so bet the horse and take the number you get.
Ranks #1 in our power figure blend. Even pace
Data · Brisnet
The model’s read ▾

We make RABEEBA a 22% chance in the 1 mile dirt; the line implies about 13%, and that 8-point gap over the board is the flag.

Our power-rating blend makes it the best of this field — which is why the board’s price looks a step generous.

To play it: a straight win bet on #4. Our fair is 7/2. On the tote you’re paid the closing price no matter when you bet, so you’re backing the horse, not a fixed price — the hold/shorten read above says how much of the edge is likely to survive to post.

Fair-value exotics ▾

Model-fair reference prices, not a +EV call. Exotics take ~20% off the top, so a pool is an overlay only when the tote's probable pays more than the fair return.

TicketCostHitFair returnAfter ~20%
Key exacta #4 / #5, #2 value$2.0011.6%$17.20$13.76
Keyed trifecta #4 / #5, #2 / #5, #2, #1, #6 value$3.009.9%$30.27$24.22
Full field ▾
#HorseModelFairBoard
4RABEEBA 22%7/25/1
5CIPRIANI22%7/25/2
2GOODNIGHT NELLIE20%4/14/1
1SHARED FUTURE14%6/17/2
6QUICK KATE14%6/14/1
3MEDJUGORJE8%11/15/1
Race 5 · 5 furlongs · turf · Md Sp WtFlag
5COME ON OM
Model
Fair
Board
29%
5/2
4/1
our win %
break-even
the morning line
We flag it because the board (4/1) pays more than our fair price (5/2). Same horse, longer price.
The market
16%
Edge Card
29% +13 pts
▸ WIN BET · #5 to win · our fair 5/2, paid at the close
Likely bet down A short board price the late money bets down. Still a win play, but expect a shorter number by post — pari-mutuel pays the closing price, so the edge is thinner here. Size it smaller.
Ranks #1 in our power figure blend. Even pace
Data · Brisnet
The model’s read ▾

This is the widest gap on today’s card. We make COME ON OM a 29% shot in the 5 furlongs turf, where the morning line — take stripped out — sits near 16%. When our number is 13 points clear of the board, that disagreement is the whole reason to be here.

It tops our power blend for the race; on the numbers it’s the most likely winner, whatever the odds say.

To play it: a straight win bet on #5. Our fair is 5/2. On the tote you’re paid the closing price no matter when you bet, so you’re backing the horse, not a fixed price — the hold/shorten read above says how much of the edge is likely to survive to post.

Fair-value exotics ▾

Model-fair reference prices, not a +EV call. Exotics take ~20% off the top, so a pool is an overlay only when the tote's probable pays more than the fair return.

TicketCostHitFair returnAfter ~20%
Key exacta #5 / #2, #7 value$2.0013.3%$15.08$12.06
Keyed trifecta #5 / #2, #7 / #2, #7, #9, #10 longshot$3.007.9%$38.06$30.45
Full field ▾
#HorseModelFairBoard
5COME ON OM 29%5/24/1
2VERENICE20%4/13/1
7ZUZU'S CLASSIC GAL13%13/27/2
9DANZING DAISY8%11/18/1
10DRULINER8%12/18/1
4MUSTANG KNICKY5%15/112/1
3RUNNING IRON5%15/18/1
1FIRST LIGHT5%20/112/1
8GIRL FIRE4%25/120/1
6HAYLEY AMBER3%30/120/1
Race 8 · 6 furlongs · dirt · Clm 16000n3lFlag
5EMMA G
Model
Fair
Board
14%
13/2
12/1
our win %
break-even
the morning line
We flag it because the board (12/1) pays more than our fair price (13/2). Same horse, longer price.
The market
6%
Edge Card
14% +8 pts
▸ WIN BET · #5 to win · our fair 13/2, paid at the close
Price should hold A long board price the late money tends to leave alone, so you should still get a strong number at post — the fullest version of the edge.
Ranks #2 in our power figure blend; closer in a contested-pace setup. Contested pace likely (5 early-speed types)
Data · Brisnet
The model’s read ▾

We make EMMA G a 14% chance in the 6 furlongs dirt; the line implies about 6%, and that 8-point gap over the board is the flag.

It sits second on our power blend, close enough to the top that the price still looks generous.

The race sets up with contested early pace (5 speed types), and this one profiles to come from off it — we pushed its number up for that (×1.1).

To play it: a straight win bet on #5. Our fair is 13/2. On the tote you’re paid the closing price no matter when you bet, so you’re backing the horse, not a fixed price — the hold/shorten read above says how much of the edge is likely to survive to post.

Fair-value exotics ▾

Model-fair reference prices, not a +EV call. Exotics take ~20% off the top, so a pool is an overlay only when the tote's probable pays more than the fair return.

TicketCostHitFair returnAfter ~20%
Key exacta #5 / #7, #3 longshot$2.006%$33.50$26.80
Keyed trifecta #5 / #7, #3 / #7, #3, #6, #8 longshot$3.004%$74.20$59.36
Full field ▾
#HorseModelFairBoard
7DANZING FLYER21%7/27/2
3SPOTTED HAZE16%5/15/2
6DONTTELLOURWIVES16%5/15/1
5EMMA G 14%13/212/1
8BEAR'S BOARD11%8/14/1
1HOW LOVELY9%10/15/1
4LOVELY MEDAGLIA8%11/112/1
2CAN YOU DREAM5%20/115/1
Race 9 · 1 1/8 miles · turf · EdRead-G2Flag
5GOLD PHOENIX
Model
Fair
Board
29%
5/2
3/1
our win %
break-even
the morning line
We flag it because the board (3/1) pays more than our fair price (5/2). Same horse, longer price.
The market
20%
Edge Card
29% +9 pts
▸ WIN BET · #5 to win · our fair 5/2, paid at the close
Likely bet down A short board price the late money bets down. Still a win play, but expect a shorter number by post — pari-mutuel pays the closing price, so the edge is thinner here. Size it smaller.
Ranks #2 in our power figure blend. Even pace
Data · Brisnet
The model’s read ▾

GOLD PHOENIX is one of the more likely winners we flag today — a 29% chance in the 1 1/8 miles turf the board still prices like a longer shot (about 20% once you strip the take). The gap is smaller in points (9) but it’s on a horse we genuinely rate to win.

Our figures put it just behind the field’s best — near enough that the board is leaving value on it.

To play it: a straight win bet on #5. Our fair is 5/2. On the tote you’re paid the closing price no matter when you bet, so you’re backing the horse, not a fixed price — the hold/shorten read above says how much of the edge is likely to survive to post.

Fair-value exotics ▾

Model-fair reference prices, not a +EV call. Exotics take ~20% off the top, so a pool is an overlay only when the tote's probable pays more than the fair return.

TicketCostHitFair returnAfter ~20%
Key exacta #5 / #8, #4 value$2.0016.8%$11.91$9.53
Keyed trifecta #5 / #8, #4 / #8, #4, #2, #7 value$3.0010.4%$28.75$23.00
Full field ▾
#HorseModelFairBoard
8FORMIDABLE MAN34%2/17/5
5GOLD PHOENIX 29%5/23/1
4ALMENDARES8%11/18/1
2MONDEGO7%12/18/1
7SEAL TEAM7%15/18/1
6STAY HOT6%15/110/1
9MI HERMANO RAMON4%25/120/1
3CABO SPIRIT4%25/112/1
1ASTRONOMER2%50/120/1
Multi-race tickets the whole card, keyed on our reads
Late Pick 4 (R8–R11)
BuildCostHitFair returnAfter ~20%
Conviction$1.000.23%$443.76$355.01
R8 #5 · R9 #5 · R10 #10, #4 · R11 #5
Coverage$4.000.71%$563.74$450.99
R8 #5 · R9 #5 · R10 #10, #4, #6, #8 · R11 #5, #2
Late Pick 5 (R7–R11)
BuildCostHitFair returnAfter ~20%
Conviction$1.000.04%$2472.19$1977.75
R7 #2 · R8 #5 · R9 #5 · R10 #10, #4 · R11 #5
Coverage$8.000.22%$3654.72$2923.78
R7 #2, #1 · R8 #5 · R9 #5 · R10 #10, #4, #6, #8 · R11 #5, #2
Early Pick 5 (R1–R5)
BuildCostHitFair returnAfter ~20%
Conviction$0.500.09%$540.26$432.21
R1 #7 · R2 #2 · R3 #6 · R4 #4 · R5 #5
Coverage$4.000.54%$746.45$597.16
R1 #7, #1 · R2 #2, #5 · R3 #6, #1 · R4 #4 · R5 #5
Pick 6 (R6–R11)
BuildCostHitFair returnAfter ~20%
Conviction$0.800.01%$6540.20$5232.16
R6 #5, #1 · R7 #2 · R8 #5 · R9 #5 · R10 #10, #4 · R11 #5
Coverage$12.800.12%$11129.73$8903.78
R6 #5, #1, #3, #11 · R7 #2, #1 · R8 #5 · R9 #5 · R10 #10, #4, #6, #8 · R11 #5, #2
Rolling Pick 3 (R3–R5)
BuildCostHitFair returnAfter ~20%
Conviction$0.501.67%$30.00$24.00
R3 #6 · R4 #4 · R5 #5
Coverage$1.002.9%$34.51$27.61
R3 #6, #1 · R4 #4 · R5 #5
Rolling Pick 3 (R2–R4)
BuildCostHitFair returnAfter ~20%
Conviction$0.501.34%$37.35$29.88
R2 #2 · R3 #6 · R4 #4
Coverage$2.004.58%$43.67$34.94
R2 #2, #5 · R3 #6, #1 · R4 #4

Whole-card tickets keyed on our reads — a tight conviction build and a wider coverage build, singling the flags and spreading the open races. Reference construction, not a +EV call: the hit % assumes the legs are independent (v0 doesn’t model pace or scratches across races), and only the flagged legs are graded bets.

The rest of the card our read on every race — analysis, not a bet
R1Chalk7SAREEHA24%3/15/2
No edge on our top pick — the market has it priced about right.
Full field ▾
#HorseModelFairBoard
7SAREEHA24%3/15/2
1CANDY BAR17%5/17/2
4SHOCKING GREY15%11/26/1
6CAMERON SLOUGH13%13/24/1
8CORPORAL VIOLETTE9%10/16/1
5LUBIE'S MUSIC8%11/112/1
2MARS MAGIC7%15/115/1
3IMA JOKER7%15/18/1
R2Chalk2VAN GOGH STYLE23%7/22/1
No edge on our top pick — the market has it priced about right.
Full field ▾
#HorseModelFairBoard
2VAN GOGH STYLE23%7/22/1
5ZAKIEL22%7/25/2
4DE FACTO20%4/15/1
3MICKEY16%5/13/1
6PRACTICAL BLAME11%8/16/1
1BELLO ROSSO8%12/115/1
R3Lean6LET HER FLY27%3/15/2
Our top-rated horse. A small edge, under our bet line.
Full field ▾
#HorseModelFairBoard
6LET HER FLY27%3/15/2
1DREAM SEEKER20%4/13/1
3AUTOMATIC PRESS16%5/14/1
8WILDCATTER11%8/16/1
7SUPER SPIKE9%10/18/1
5SAUDI RUNNER7%12/110/1
2DEE SNOOK6%15/18/1
4OSCAR STORM4%25/120/1
R6Scramble5PERFECT SMILE17%5/17/2
Wide-open heat; no separation we'd trust.
Full field ▾
#HorseModelFairBoard
5PERFECT SMILE17%5/17/2
1COTTA RIDE13%13/24/1
3HOW IT IS11%8/112/1
11MY BABYCAKES11%8/13/1
4SPY IN DISGUISE10%9/120/1
2SALTY SISS9%10/16/1
12SURPRISE D' ORO7%12/112/1
8CINDYS BEACH HOUSE6%15/112/1
9QUEEN OF BANTRY5%20/115/1
7BORACAY MISS4%20/120/1
6CHAMPAGNIA4%25/120/1
10SHEDUNIT2%50/130/1
R7Chalk2PRIVATE GEM18%9/24/1
No edge on our top pick — the market has it priced about right.
Full field ▾
#HorseModelFairBoard
2PRIVATE GEM18%9/24/1
1ROGUE LEGEND13%13/28/1
3MESCALERO11%8/18/1
4POSEIDON'S LAW11%8/13/1
7VALIANT SON10%9/110/1
8LEGAL HEIR10%9/18/1
9YACOWLEF10%9/16/1
6SIR ROCKET9%11/112/1
10RE ARMED JON6%15/112/1
5DR. MY EYES3%30/112/1
R10Scramble10MONGOLIAN MAX16%11/27/2
Wide-open heat; no separation we'd trust.
Full field ▾
#HorseModelFairBoard
10MONGOLIAN MAX16%11/27/2
4ROYAL 'N RANDO14%6/13/1
6SHORTMAN13%13/212/1
8MICI'S EXPRESS11%8/14/1
3OOBUBBAKAKAYO10%9/110/1
2CUPID'S CRUSADER9%10/18/1
9CATHAL8%11/112/1
1BIG JUANITO8%12/18/1
5SUNSET STORM5%20/115/1
7LEVON5%20/120/1
R11Chalk5GOJE19%9/27/2
No edge on our top pick — the market has it priced about right.
Full field ▾
#HorseModelFairBoard
5GOJE19%9/27/2
2RYAN'S GIRL15%6/15/1
4FIBONACCIS RIDE12%7/18/1
11WILD WEST COAST10%9/18/1
10HELLO KID O KID O10%9/112/1
8NEWPORT DREAMZ8%11/18/1
7EIGHTIES7%12/14/1
1IT'S A FAIRLIFE6%15/112/1
3MPERFECTION5%20/110/1
6KOOL MARIAH4%25/120/1
9WHOPPER FACTOR4%25/120/1