Pick Pony Weekly Picks Recap — October 18, 2025

AI Picks Performance This Week

What a week to be a Pick Pony subscriber! Across more than 600 settled races, the AI Ensemble (Algo 2), AI Win Probability (Algo 3) and Experimental Weight Set 3 all beat the morning-line favorite's 35.0% win rate. Leading the charge on the overnight side, the AI Ensemble (Algo 2) won 37.5% with 200 top-pick victories, Experimental Weight Set 3 posted 37.4% with a remarkable 69.9% ITM, and Algo 3 hit 36.3%. The AI Best Bets model — our most selective tier — delivered an elite 39.6% win rate on 128 wins, with an eye-popping 73.4% ITM across 323 settled races. The morning updates added even more winners: Algo 2's morning update rang up 216 wins, the most of any model, and Algo 3's morning update hit 211. It was a strong week from top to bottom.

Standout Wins

The longshot alerts were firing on all cylinders this week, and the highlights reel is absolutely packed. Experimental Weight Set 2 deserves a standing ovation for flagging CHLOE'S BANKER at 15-1 (Oct 16, DEL R4) and PINEAPPLE MAN at 12-1 (Oct 17, BEL R11) — two massive overlays that rewarded believers with serious payouts. The Algo 3 morning update spotted EQUUS at 10-1 (Oct 15, DEL R5), and the Off-Track Ensemble uncovered HIGHER WISH at 10-1 (Oct 12, IND R4) while also nailing JUST TIPSY and CELESTIAL HEART both at 8-1 on October 11. Meanwhile, the AI Best Bets model delivered back-to-back 8-1 winners in SHIP THE MONEY (Oct 15, RPX R7) and RIZZ (Oct 11, MNR R2), proving that our most curated tier knows how to find value. DO THE RIGHT THING (Oct 16, LRL R4, 6-1) stands as the week's consensus hero — flagged as a top pick by virtually every model in the system, a true cross-algorithm conviction play that rewarded players who acted on it. On the exotic side, Algo 2's morning update led all models with 66 Exacta hits and 29 Trifecta hits, meaning multi-race ticket players had plenty to smile about this week.

Key Insights

A few clear themes emerged from this week's data. First, value spotting at mid-range odds (4-1 to 8-1) was the sweet spot across all models — the bulk of this week's notable wins clustered in that range, suggesting the AI is particularly sharp at identifying horses the market underestimates rather than burying at extreme longshot prices. Second, the morning update models consistently added wins over their overnight counterparts — Algo 2's update jumped from 200 to 216 wins, Algo 3 climbed from 193 to 211, and Experimental Weight Set 3 rose from 201 to 209 — demonstrating real, tangible value in reassessing each field after the official scratches. Each morning update found a new pick in 60 to 70 races where the overnight pick had been scratched (bets that would otherwise have been refunded), and between 11 and 18 of those replacements won. Finally, track diversity was strong, with wins spread across DEL, BEL, LRL, RPX, PRX, KEE, MNR, FLX, IND, DED, and more — this wasn't a one-track fluke. The AI is performing consistently across surfaces and circuits.

Looking Ahead

With 32 races still pending settlement across most models, this week's final numbers could climb even higher — so keep an eye on those results as they come in. Next week, watch for the Experimental Weight Set 3 and Algo 2 morning updates to keep pressing their edge, and if the AI flags another cross-model consensus play like DO THE RIGHT THING, you'll want to be ready to act early. The algorithms are sharp, they're consistent, and they're just getting started — it's a great time to be riding with Pick Pony! 🐴

Weekly Performance Summary

How each pick source's top selection finished across every graded race this week.

Where our AI Ensemble picks finished this week

All 533 graded races the Algo 2 top pick ran in.

The bottom bar adds the first three together.

Show the numbers

Group	Win rate	Races
Won the race	37.5%	533
Finished 2nd	20.6%	533
Finished 3rd	11.3%	533
In the money	69.4%	533

Pick Pony's AI Winner models rank every horse in each race using a weighted combination of speed figures, pace analysis, trainer/jockey statistics, track bias, and dozens of other handicapping factors. Each algorithm uses a different set of optimized weights to capture different angles on the same race data. Top Pick Wins measures how often the model's #1 ranked horse won the race outright. Places and Shows count 2nd and 3rd place finishes respectively. ITM (In The Money) is the combined total of Win + Place + Show. Rates are calculated against settled races only (pending results excluded). The Exotic Wager Hits table shows how often the model's top 3 picks finished in the correct order (Exacta/Trifecta) or in any order within the top positions (Boxed Exacta/Boxed Trifecta). Morning Update rows are the same picks re-ranked after the official scratches and surface changes were applied that morning.

Algo 2 (AI Ensemble)

Several independent AI models each rank the race; the horse they agree on most is the pick.

Algo 2 (AI Ensemble) Winner

The overnight top pick in every graded race, scored the night before from the official past performances.

Metric	Count	Rate
Total Races	645
Top Pick Wins (1st)	200	37.5%
Top Pick Places (2nd)	110	20.6%
Top Pick Shows (3rd)	60	11.3%
Top Pick ITM	370	69.4%
Pending	32

Exotic Wager Hits (Algo 2 (AI Ensemble) Winner)

How often the source's top three finished 1-2-3, counted as straight and boxed exactas and trifectas.

Wager Type	Hits (rate of playable races)	Description
Exacta	55 (13%)	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	37 (8%)	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	20 (5%)	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	40 (9%)	Picks 1, 2 & 3 all finished in top 3, any order

Algo 2 (AI Ensemble) Morning Update

The same picks re-ranked that morning after the official scratches and surface changes were applied.

Metric	Count	Rate
Total Races	645
Top Pick Wins (1st)	216	36.2%
Top Pick Places (2nd)	119	19.9%
Top Pick Shows (3rd)	72	12.1%
Top Pick ITM	407	68.2%
Replaced a scratched overnight pick	64 races, 16 won	25.0%
Pending	32

The morning update found a new pick in 64 races where the overnight pick was scratched, and 16 of them won. Without the morning update those 64 bets would simply have been refunded, so these are extra winners. Because those races are counted here but not in the overnight table (and our first choice was gone), this win rate can read slightly lower than the overnight rate even in a week when the morning update wins more races.

Exotic Wager Hits (Algo 2 (AI Ensemble) Morning Update)

How often the source's top three finished 1-2-3, counted as straight and boxed exactas and trifectas.

Wager Type	Hits (rate of playable races)	Description
Exacta	66 (12%)	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	43 (8%)	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	29 (5%)	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	55 (10%)	Picks 1, 2 & 3 all finished in top 3, any order

Algo 3 (AI Win Probability)

An AI estimate of each horse's chance of winning, blended with the morning line; the most likely winner is the pick.

Algo 3 (AI Win Probability) Winner

The overnight top pick in every graded race, scored the night before from the official past performances.

Metric	Count	Rate
Total Races	645
Top Pick Wins (1st)	193	36.3%
Top Pick Places (2nd)	115	21.7%
Top Pick Shows (3rd)	63	11.9%
Top Pick ITM	371	69.9%
Pending	32

Exotic Wager Hits (Algo 3 (AI Win Probability) Winner)

How often the source's top three finished 1-2-3, counted as straight and boxed exactas and trifectas.

Wager Type	Hits (rate of playable races)	Description
Exacta	45 (10%)	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	45 (10%)	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	17 (4%)	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	49 (11%)	Picks 1, 2 & 3 all finished in top 3, any order

Algo 3 (AI Win Probability) Morning Update

The same picks re-ranked that morning after the official scratches and surface changes were applied.

Metric	Count	Rate
Total Races	645
Top Pick Wins (1st)	211	35.2%
Top Pick Places (2nd)	127	21.2%
Top Pick Shows (3rd)	73	12.2%
Top Pick ITM	411	68.6%
Replaced a scratched overnight pick	68 races, 18 won	26.5%
Pending	32

The morning update found a new pick in 68 races where the overnight pick was scratched, and 18 of them won. Without the morning update those 68 bets would simply have been refunded, so these are extra winners. Because those races are counted here but not in the overnight table (and our first choice was gone), this win rate can read slightly lower than the overnight rate even in a week when the morning update wins more races.

Exotic Wager Hits (Algo 3 (AI Win Probability) Morning Update)

How often the source's top three finished 1-2-3, counted as straight and boxed exactas and trifectas.

Wager Type	Hits (rate of playable races)	Description
Exacta	58 (10%)	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	53 (9%)	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	27 (5%)	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	67 (12%)	Picks 1, 2 & 3 all finished in top 3, any order

Algo 1

Our weighted rating: every horse is scored on speed, pace, class, form and connections, and the top score is the pick.

Algo 1 Winner

The overnight top pick in every graded race, scored the night before from the official past performances.

Metric	Count	Rate
Total Races	645
Top Pick Wins (1st)	181	34.0%
Top Pick Places (2nd)	107	20.1%
Top Pick Shows (3rd)	67	12.6%
Top Pick ITM	355	66.7%
Pending	32

Exotic Wager Hits (Algo 1 Winner)

How often the source's top three finished 1-2-3, counted as straight and boxed exactas and trifectas.

Wager Type	Hits (rate of playable races)	Description
Exacta	42 (10%)	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	36 (8%)	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	13 (3%)	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	38 (9%)	Picks 1, 2 & 3 all finished in top 3, any order

Algo 1 Morning Update

The same picks re-ranked that morning after the official scratches and surface changes were applied.

Metric	Count	Rate
Total Races	645
Top Pick Wins (1st)	197	32.7%
Top Pick Places (2nd)	122	20.3%
Top Pick Shows (3rd)	75	12.5%
Top Pick ITM	394	65.4%
Replaced a scratched overnight pick	70 races, 17 won	24.3%
Pending	32

The morning update found a new pick in 70 races where the overnight pick was scratched, and 17 of them won. Without the morning update those 70 bets would simply have been refunded, so these are extra winners. Because those races are counted here but not in the overnight table (and our first choice was gone), this win rate can read slightly lower than the overnight rate even in a week when the morning update wins more races.

Exotic Wager Hits (Algo 1 Morning Update)

How often the source's top three finished 1-2-3, counted as straight and boxed exactas and trifectas.

Wager Type	Hits (rate of playable races)	Description
Exacta	50 (9%)	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	48 (8%)	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	16 (3%)	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	59 (10%)	Picks 1, 2 & 3 all finished in top 3, any order

AI Exacta

The top two horses in our exotics ordering, played as a $1 straight exacta.

AI Exacta Winner

The overnight top pick in every graded race, scored the night before from the official past performances.

Metric	Count	Rate
Total Races	645
Top Pick Wins (1st)	196	37.1%
Top Pick Places (2nd)	114	21.6%
Top Pick Shows (3rd)	59	11.2%
Top Pick ITM	369	69.8%
Pending	32

Exotic Wager Hits (AI Exacta Winner)

How often the source's top three finished 1-2-3, counted as straight and boxed exactas and trifectas.

Wager Type	Hits (rate of playable races)	Description
Exacta	50 (11%)	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	37 (8%)	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	19 (4%)	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	41 (9%)	Picks 1, 2 & 3 all finished in top 3, any order

Experimental Weight Set 2

An experimental variant of the Algo 1 rating with a different weight profile, graded here to see whether it earns a place in the published ladder.

Experimental Weight Set 2 Winner

The overnight top pick in every graded race, scored the night before from the official past performances.

Metric	Count	Rate
Total Races	645
Top Pick Wins (1st)	198	36.9%
Top Pick Places (2nd)	105	19.6%
Top Pick Shows (3rd)	63	11.7%
Top Pick ITM	366	68.2%
Pending	32

Exotic Wager Hits (Experimental Weight Set 2 Winner)

How often the source's top three finished 1-2-3, counted as straight and boxed exactas and trifectas.

Wager Type	Hits (rate of playable races)	Description
Exacta	48 (11%)	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	28 (7%)	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	15 (3%)	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	35 (8%)	Picks 1, 2 & 3 all finished in top 3, any order

Experimental Weight Set 2 Morning Update

The same picks re-ranked that morning after the official scratches and surface changes were applied.

Metric	Count	Rate
Total Races	645
Top Pick Wins (1st)	203	34.0%
Top Pick Places (2nd)	125	20.9%
Top Pick Shows (3rd)	73	12.2%
Top Pick ITM	401	67.2%
Replaced a scratched overnight pick	60 races, 11 won	18.3%
Pending	32

The morning update found a new pick in 60 races where the overnight pick was scratched, and 11 of them won. Without the morning update those 60 bets would simply have been refunded, so these are extra winners. Because those races are counted here but not in the overnight table (and our first choice was gone), this win rate can read slightly lower than the overnight rate even in a week when the morning update wins more races.

Exotic Wager Hits (Experimental Weight Set 2 Morning Update)

How often the source's top three finished 1-2-3, counted as straight and boxed exactas and trifectas.

Wager Type	Hits (rate of playable races)	Description
Exacta	57 (10%)	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	43 (8%)	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	23 (4%)	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	53 (9%)	Picks 1, 2 & 3 all finished in top 3, any order

Experimental Weight Set 3

An experimental variant of the Algo 1 rating with a different weight profile, graded here to see whether it earns a place in the published ladder.

Experimental Weight Set 3 Winner

The overnight top pick in every graded race, scored the night before from the official past performances.

Metric	Count	Rate
Total Races	645
Top Pick Wins (1st)	201	37.4%
Top Pick Places (2nd)	115	21.4%
Top Pick Shows (3rd)	60	11.2%
Top Pick ITM	376	69.9%
Pending	32

Exotic Wager Hits (Experimental Weight Set 3 Winner)

How often the source's top three finished 1-2-3, counted as straight and boxed exactas and trifectas.

Wager Type	Hits (rate of playable races)	Description
Exacta	51 (12%)	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	34 (8%)	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	17 (4%)	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	44 (10%)	Picks 1, 2 & 3 all finished in top 3, any order

Experimental Weight Set 3 Morning Update

The same picks re-ranked that morning after the official scratches and surface changes were applied.

Metric	Count	Rate
Total Races	645
Top Pick Wins (1st)	209	34.8%
Top Pick Places (2nd)	134	22.3%
Top Pick Shows (3rd)	71	11.8%
Top Pick ITM	414	68.9%
Replaced a scratched overnight pick	63 races, 12 won	19.0%
Pending	32

The morning update found a new pick in 63 races where the overnight pick was scratched, and 12 of them won. Without the morning update those 63 bets would simply have been refunded, so these are extra winners. Because those races are counted here but not in the overnight table (and our first choice was gone), this win rate can read slightly lower than the overnight rate even in a week when the morning update wins more races.

Exotic Wager Hits (Experimental Weight Set 3 Morning Update)

How often the source's top three finished 1-2-3, counted as straight and boxed exactas and trifectas.

Wager Type	Hits (rate of playable races)	Description
Exacta	62 (11%)	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	45 (8%)	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	26 (5%)	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	66 (11%)	Picks 1, 2 & 3 all finished in top 3, any order

Ai Best Bets

Ai Best Bets Winner

The overnight top pick in every graded race, scored the night before from the official past performances.

Metric	Count	Rate
Total Races	375
Top Pick Wins (1st)	128	39.6%
Top Pick Places (2nd)	70	21.7%
Top Pick Shows (3rd)	39	12.1%
Top Pick ITM	237	73.4%
Pending	5

Exotic Wager Hits (Ai Best Bets Winner)

How often the source's top three finished 1-2-3, counted as straight and boxed exactas and trifectas.

Wager Type	Hits (rate of playable races)	Description
Exacta	0 (—)	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	0 (—)	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	0 (—)	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	0 (—)	Picks 1, 2 & 3 all finished in top 3, any order

Algorithm Offtrk Ens

Algorithm Offtrk Ens Winner

The overnight top pick in every graded race, scored the night before from the official past performances.

Metric	Count	Rate
Total Races	645
Top Pick Wins (1st)	190	36.2%
Top Pick Places (2nd)	108	20.6%
Top Pick Shows (3rd)	67	12.8%
Top Pick ITM	365	69.5%
Pending	32

Exotic Wager Hits (Algorithm Offtrk Ens Winner)

How often the source's top three finished 1-2-3, counted as straight and boxed exactas and trifectas.

Wager Type	Hits (rate of playable races)	Description
Exacta	51 (12%)	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	33 (8%)	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	20 (5%)	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	38 (9%)	Picks 1, 2 & 3 all finished in top 3, any order

Today’s Best Bets (AI × Expert Alignment)

The horses published in each day's Today's Best Bets post: races where the AI top pick and the expert consensus top pick were the same horse, split by how many AI models agreed.

Agreement	Races graded	Won	2nd	3rd	Win %
All 3 AI models + experts	177	80	44	13	45.2%
2 of 3 AI models + experts	80	23	16	15	28.7%
1 of 3 AI models + experts	60	21	9	11	35.0%
All Best Bets	317	124	69	39	39.1%
Pending	112

AI Longshot Picks (Kelly Edge Plays)

Longshot picks are individual horses flagged at publication time: their morning-line odds were 8-1 or greater — prices the betting public considers unlikely to win — and the model's calibrated win probability said the price overpaid. Unlike the winner models above, a longshot is not a race's top-ranked horse, so these tables count selections, not races: every flagged horse is one bet, graded on its own finish, and a single race can contribute more than one. (For the same reason there is no exotic-hits table here — an exacta or trifecta needs a ranked 1-2-3 ticket, which a set of longshot flags does not define.) There is also one longshot table rather than one per algorithm: the flag depends only on the horse's price and its calibrated edge, never on where an algorithm ranked it, so all three models publish exactly the same longshot list. Because longshots win far less frequently by definition, win rates in this section are expected to be substantially lower than the winner models above. That is normal and by design — even a modest longshot win rate of 5-10% can be highly profitable because the payoffs are dramatically larger. A $2 win bet on an 8-1 longshot returns $18. Focus on ITM rate and on the realised ROI in the Longshot Betting Strategy Simulator below rather than on raw win percentage when evaluating longshot model performance.

The horses listed in each day's Kelly Edge Plays section: 10-1 or higher on the morning line and rated a value play by our models; counted per horse, not per race.

Metric	Count	Rate
Longshot Selections	209
Races Covered	138
Wins (1st)	9	6.1%
Places (2nd)	14	9.5%
Shows (3rd)	16	10.8%
ITM	39	26.4%
Pending	16

Longshot Betting Strategy Simulator

What a flat win bet on every flagged longshot would have returned this week at each minimum-edge threshold.

Each strategy below replays the past 60 days of AI longshot picks as actual $2 mutuel bets and reports the realised return. A longer window than the rest of this report is used here on purpose: longshots are rare and extremely high-variance, so a single week's results are dominated by luck — only over a larger sample do the calibrated edge strategies separate from simply betting every longshot. Bets are deduplicated by (track, race, horse) so a horse picked by all three algorithms generates one bet, not three. Edge strategies use a calibrated win probability (from the longshot meta-learner) and bet only when P(win) × decimal odds − 1 exceeds the listed threshold — these target overlays rather than long prices for their own sake. Hit% is the share of tickets that cashed any leg. Published longshots graded: 1802; wider 10/1-and-longer universe available to the edge rows: 15119, of which 15119 could be assigned a calibrated edge. Calibrator: out-of-sample tiered calibrator on the cross-race win probability (lgbm_win_prob_fwd), trained through 2026-08-18; edge rows replay only the 60 days after that date, so no graded race was ever seen by the calibrator. The edge filters use only leak-free forward scores (lgbm_win_prob_fwd — captured before each race ran), so the ROIs are a genuine out-of-sample estimate — never the in-sample re-scored values that previously inflated this section. The two families are measured differently — read them separately. The raw-filter rows grade the longshots we actually published, over the full 60 days. The edge rows sweep a different population: every thoroughbred runner priced at 10/1 or longer, published or not. That matters, because being published as a longshot already requires passing an edge test — so re-applying an edge threshold to the published picks would just re-filter an already-filtered group and tell you nothing. The edge rows also cover only the most recent 60 days (15119 runners), because everything before 2026-08-18 was needed to fit the calibrator and grading it would be marking its own homework. That window widens on its own as forward scores accumulate.

Strategy	Bets	Tickets Cashed	Stake	Payout
$2 WIN — all longshots	1802	90 (5.0%)	$3604.00	$1982.60
$2 PLACE — all longshots	1802	235 (13.0%)	$3604.00	$2254.68
$2 SHOW — all longshots	1802	379 (21.0%)	$3604.00	$2170.74
$2 WIN + $2 PLACE	1802	235 (13.0%)	$7208.00	$4237.28
$2 WIN — ML ≥ 15/1	1472	63 (4.3%)	$2944.00	$1688.20
$2 WIN — ML ≥ 20/1	1131	34 (3.0%)	$2262.00	$1185.22
$2 WIN — field ≥ 8	1485	70 (4.7%)	$2970.00	$1729.30
$2 WIN — edge ≥ 5%	7881	450 (5.7%)	$15762.00	$10089.44
$2 WIN — edge ≥ 10%	4061	224 (5.5%)	$8122.00	$4998.92
$2 WIN — edge ≥ 20%	2673	103 (3.9%)	$5346.00	$2766.32
$2 WIN — edge ≥ 30%	1216	48 (3.9%)	$2432.00	$1067.34
$2 WIN — edge ≥ 40%	1129	45 (4.0%)	$2258.00	$898.74
$2 WIN — edge ≥ 50%	1049	44 (4.2%)	$2098.00	$845.94
$2 WIN — edge ≥ 60%	1005	44 (4.4%)	$2010.00	$845.94
$2 WIN — edge ≥ 70%	895	41 (4.6%)	$1790.00	$781.34
$2 WIN — edge ≥ 80%	851	39 (4.6%)	$1702.00	$729.54
$2 WIN — edge ≥ 90%	766	38 (5.0%)	$1532.00	$687.94
$2 WIN — edge ≥ 100%	647	33 (5.1%)	$1294.00	$539.24
$2 WIN — edge ≥ 10% AND field ≥ 8	2660	130 (4.9%)	$5320.00	$3498.98

Trifecta Structure Plays (AI Exotics)

The Trifecta line from each day's AI Exotics section: key the top pick to win over the next three horses (six combinations per race); the tag shows whether the race shape looked playable.

Each AI Predictions post suggests one trifecta structure per race: the Algo 3 top pick to win, with its next three ranked horses boxed for 2nd and 3rd (6 combinations). Races our race-shape model rates most favorable are tagged ⭐ Best Bet in the post. This table grades last week's published plays against the actual trifecta payoffs at each track's real wager minimum — no assumptions, no hindsight.

Plays graded	349
Trifectas hit	50 (14.3%)
Total staked	$1,390.80
Total returned	$1,500.19

272 race(s) skipped for scratches inside the top four; 24 skipped where the track's trifecta minimum wasn't recorded. Per-race wager minimums have been captured since July 4, 2026, so this ledger grows more complete each week.

Benchmark: The Morning-Line Favorite

What betting the morning-line favorite in every race would have returned: the baseline every pick source has to beat.

The simplest possible strategy is to always bet the morning-line favorite — the "chalk." This table shows how that baseline performed across the same thoroughbred races this week, so you can judge the AI's win rates against what the public's top choice delivered. Beating the chalk consistently is the real test of any handicapping model.

Metric	Count	Rate
Settled Races	655
Favorite Wins (1st)	229	35.0%
Favorite Places (2nd)	134	20.5%
Favorite Shows (3rd)	81	12.4%
Favorite ITM	444	67.8%

Consensus Expert Picks

Picks from more than twenty-five published handicappers, weighted into one consensus selection per race.

Consensus Expert Picks are derived from multiple independent handicapping sources. Each source submits their top picks per race, and the consensus ranking is built by scoring each horse: 4 points for a 1st-place pick, 3 for 2nd, 2 for 3rd, and 1 for 4th. The horse with the highest total score becomes the consensus top pick. Agreement % measures what share of experts included a horse in their picks — higher agreement signals stronger conviction across sources. The Win/Place/Show/ITM and Exotic stats below measure how the consensus top pick actually performed on race day.

Metric	Count	Rate
Total Races	735
Top Pick Wins (1st)	175	31.6%
Top Pick Places (2nd)	114	20.6%
Top Pick Shows (3rd)	88	15.9%
Top Pick ITM	377	68.1%
Pending	181

Exotic Wager Hits (Consensus Top 3 Picks)

How often the source's top three finished 1-2-3, counted as straight and boxed exactas and trifectas.

Wager Type	Hits (rate of playable races)	Description
Exacta	36 (8%)	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	34 (8%)	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	9 (2%)	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	36 (8%)	Picks 1, 2 & 3 all finished in top 3, any order

Performance by Breed

The same results split by thoroughbred and quarter horse races, which are handicapped differently.

Top-pick win rates vary dramatically by breed. Thoroughbred (TB) racing is the most form-driven and predictable, while Quarter Horse (QH) and Arabian (AR) sprints are decided in a few hundred yards and are far more chaotic — they naturally produce lower win rates. Because the summary above blends all breeds together, this table separates them so each breed's true performance is visible. W/P/S are wins, places (2nd), and shows (3rd), with the percentage of settled races in parentheses. ITM is the In-The-Money total (Win + Place + Show). EX/BEX/TRI/BTRI are exacta, boxed-exacta, trifecta, and boxed-trifecta hits on the top picks. Longshot rows count individual flagged selections rather than races (a race can contribute more than one), and show dashes for the exotic columns because those wagers need a ranked 1-2-3 ticket.

Thoroughbred

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	645	200 (38%)	110 (21%)	60 (11%)	370 (69%)	55 (13%)	37 (8%)	20 (5%)	40 (9%)
Algo 3 Winner	645	193 (36%)	115 (22%)	63 (12%)	371 (70%)	45 (10%)	45 (10%)	17 (4%)	49 (11%)
Algo 1 Winner	645	181 (34%)	107 (20%)	67 (13%)	355 (67%)	42 (10%)	36 (8%)	13 (3%)	38 (9%)
Experimental Weight Set 2 Winner	645	198 (37%)	105 (20%)	63 (12%)	366 (68%)	48 (11%)	28 (7%)	15 (3%)	35 (8%)
Experimental Weight Set 3 Winner	645	201 (37%)	115 (21%)	60 (11%)	376 (70%)	51 (12%)	34 (8%)	17 (4%)	44 (10%)
AI Longshot	209	9 (6%)	14 (9%)	16 (11%)	39 (26%)	—	—	—	—

Performance by Track

The same results split by track, to show where each source is strongest and weakest.

The tables below break down each pick source's performance at individual tracks. W/P/S show the number of wins, places (2nd), and shows (3rd) with the percentage of settled races in parentheses. ITM is the combined In The Money total (Win + Place + Show). EX (Exacta) counts races where the top 2 picks finished 1st and 2nd in exact order. BEX (Boxed Exacta) counts races where the top 2 picks both finished in the top 2 in either order. TRI (Trifecta) and BTRI (Boxed Trifecta) apply the same logic to the top 3 picks finishing in the top 3 positions. Longshot rows count individual flagged selections rather than races (a race can contribute more than one) and show dashes in the exotic columns, because those wagers need a ranked 1-2-3 ticket that a per-horse longshot flag does not define. Algo 1 is the weighted rating, Algo 2 the AI Ensemble and Algo 3 the AI Win Probability model — ordered by measured performance, so a higher number should be the stronger source; the Weight Set rows are experimental profiles graded as shadows. Comparing sources at a specific track helps identify which is strongest for that venue. The ML Favorite (chalk) row shows how the morning-line favorite performed in that track's thoroughbred races — the baseline any pick source needs to beat to be adding value at that venue.

AJX

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Expert Consensus	8	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)

ALB

AI Picks posts graded here: Sun 10/11 · Wed 10/14

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	13	5 (38%)	3 (23%)	2 (15%)	10 (77%)	2 (18%)	2 (18%)	1 (9%)	2 (18%)
Algo 3 Winner	13	5 (38%)	3 (23%)	4 (31%)	12 (92%)	0 (0%)	2 (18%)	0 (0%)	2 (18%)
Algo 1 Winner	13	3 (25%)	2 (17%)	4 (33%)	9 (75%)	1 (8%)	1 (8%)	0 (0%)	2 (17%)
Experimental Weight Set 2 Winner	13	5 (42%)	1 (8%)	3 (25%)	9 (75%)	1 (9%)	1 (9%)	0 (0%)	3 (27%)
Experimental Weight Set 3 Winner	13	5 (42%)	1 (8%)	3 (25%)	9 (75%)	1 (9%)	0 (0%)	0 (0%)	3 (27%)
AI Longshot	2	0 (0%)	0 (0%)	0 (0%)	0 (0%)	—	—	—	—
Expert Consensus	37	6 (18%)	4 (12%)	10 (29%)	20 (59%)	1 (3%)	0 (0%)	0 (0%)	2 (6%)
ML Favorite (chalk)	13	5 (38%)	2 (15%)	2 (15%)	9 (69%)	—	—	—	—

BEL

AI Picks posts graded here: Sun 10/11 · Wed 10/14 · Thu 10/15 · Fri 10/16 · Sat 10/17

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	45	13 (32%)	9 (22%)	5 (12%)	27 (66%)	1 (3%)	2 (6%)	0 (0%)	1 (3%)
Algo 3 Winner	45	13 (32%)	8 (20%)	5 (12%)	26 (65%)	0 (0%)	3 (9%)	0 (0%)	1 (3%)
Algo 1 Winner	45	12 (28%)	8 (19%)	5 (12%)	25 (58%)	0 (0%)	2 (6%)	0 (0%)	1 (3%)
Experimental Weight Set 2 Winner	45	15 (37%)	11 (27%)	5 (12%)	31 (76%)	0 (0%)	2 (6%)	0 (0%)	4 (11%)
Experimental Weight Set 3 Winner	45	12 (29%)	10 (24%)	5 (12%)	27 (64%)	1 (3%)	1 (3%)	0 (0%)	2 (6%)
AI Longshot	16	0 (0%)	0 (0%)	0 (0%)	0 (0%)	—	—	—	—
Expert Consensus	45	10 (24%)	9 (21%)	10 (24%)	29 (69%)	3 (7%)	1 (2%)	1 (2%)	2 (5%)
ML Favorite (chalk)	45	11 (24%)	10 (22%)	7 (16%)	28 (62%)	—	—	—	—

BTP

AI Picks posts graded here: Mon 10/12

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	8	3 (50%)	0 (0%)	2 (33%)	5 (83%)	0 (0%)	0 (0%)	0 (0%)	2 (40%)
Algo 3 Winner	8	4 (67%)	0 (0%)	2 (33%)	6 (100%)	0 (0%)	0 (0%)	0 (0%)	2 (40%)
Algo 1 Winner	8	3 (50%)	0 (0%)	3 (50%)	6 (100%)	0 (0%)	0 (0%)	0 (0%)	2 (33%)
Experimental Weight Set 2 Winner	8	2 (33%)	0 (0%)	3 (50%)	5 (83%)	0 (0%)	0 (0%)	0 (0%)	1 (17%)
Experimental Weight Set 3 Winner	8	4 (67%)	0 (0%)	2 (33%)	6 (100%)	0 (0%)	0 (0%)	0 (0%)	2 (40%)
AI Longshot	1	0 (0%)	0 (0%)	0 (0%)	0 (0%)	—	—	—	—
Expert Consensus	8	4 (80%)	0 (0%)	1 (20%)	5 (100%)	0 (0%)	0 (0%)	0 (0%)	2 (40%)
ML Favorite (chalk)	8	5 (62%)	0 (0%)	2 (25%)	7 (88%)	—	—	—	—

CTD

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	16	5 (33%)	5 (33%)	2 (13%)	12 (80%)	4 (29%)	3 (21%)	0 (0%)	2 (14%)
Algo 3 Winner	16	4 (27%)	5 (33%)	2 (13%)	11 (73%)	3 (21%)	2 (14%)	0 (0%)	2 (14%)
Algo 1 Winner	16	5 (33%)	1 (7%)	2 (13%)	8 (53%)	4 (29%)	1 (7%)	1 (7%)	1 (7%)
Experimental Weight Set 2 Winner	16	7 (47%)	1 (7%)	3 (20%)	11 (73%)	5 (33%)	0 (0%)	2 (13%)	1 (7%)
Experimental Weight Set 3 Winner	16	6 (40%)	2 (13%)	1 (7%)	9 (60%)	4 (29%)	1 (7%)	1 (7%)	2 (14%)
ML Favorite (chalk)	16	7 (44%)	2 (12%)	2 (12%)	11 (69%)	—	—	—	—

CTM

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Expert Consensus	18	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)

CTX

AI Picks posts graded here: Wed 10/14 · Thu 10/15 · Fri 10/16 · Sat 10/17

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	32	10 (32%)	7 (23%)	3 (10%)	20 (65%)	3 (11%)	2 (7%)	1 (4%)	3 (11%)
Algo 3 Winner	32	8 (26%)	10 (32%)	4 (13%)	22 (71%)	2 (7%)	4 (14%)	0 (0%)	4 (14%)
Algo 1 Winner	32	8 (26%)	8 (26%)	4 (13%)	20 (65%)	2 (7%)	4 (14%)	1 (3%)	2 (7%)
Experimental Weight Set 2 Winner	32	11 (37%)	6 (20%)	3 (10%)	20 (67%)	2 (7%)	1 (4%)	0 (0%)	4 (14%)
Experimental Weight Set 3 Winner	32	9 (30%)	7 (23%)	3 (10%)	19 (63%)	2 (7%)	3 (10%)	0 (0%)	3 (10%)
Expert Consensus	32	11 (35%)	6 (19%)	5 (16%)	22 (71%)	2 (6%)	3 (10%)	0 (0%)	4 (13%)
ML Favorite (chalk)	32	8 (25%)	11 (34%)	3 (9%)	22 (69%)	—	—	—	—

DED

AI Picks posts graded here: Wed 10/14 · Thu 10/15 · Fri 10/16 · Sat 10/17

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	35	10 (30%)	3 (9%)	5 (15%)	18 (55%)	2 (7%)	1 (3%)	0 (0%)	0 (0%)
Algo 3 Winner	35	11 (33%)	2 (6%)	6 (18%)	19 (58%)	4 (14%)	1 (3%)	1 (3%)	2 (7%)
Algo 1 Winner	35	5 (16%)	3 (9%)	5 (16%)	13 (41%)	3 (11%)	1 (4%)	0 (0%)	2 (7%)
Experimental Weight Set 2 Winner	35	4 (12%)	3 (9%)	5 (15%)	12 (36%)	1 (4%)	0 (0%)	0 (0%)	1 (4%)
Experimental Weight Set 3 Winner	35	10 (30%)	4 (12%)	6 (18%)	20 (61%)	2 (8%)	2 (8%)	0 (0%)	1 (4%)
AI Longshot	14	1 (11%)	1 (11%)	0 (0%)	2 (22%)	—	—	—	—
Expert Consensus	10	3 (33%)	3 (33%)	1 (11%)	7 (78%)	1 (11%)	1 (11%)	0 (0%)	0 (0%)
ML Favorite (chalk)	35	10 (29%)	3 (9%)	3 (9%)	16 (46%)	—	—	—	—

DEL

AI Picks posts graded here: Wed 10/14 · Thu 10/15 · Fri 10/16 · Sat 10/17

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	35	12 (44%)	6 (22%)	2 (7%)	20 (74%)	4 (24%)	3 (18%)	1 (6%)	2 (12%)
Algo 3 Winner	35	14 (52%)	5 (19%)	0 (0%)	19 (70%)	5 (29%)	1 (6%)	3 (18%)	2 (12%)
Algo 1 Winner	35	11 (46%)	8 (33%)	1 (4%)	20 (83%)	1 (6%)	2 (12%)	0 (0%)	2 (12%)
Experimental Weight Set 2 Winner	35	14 (54%)	5 (19%)	2 (8%)	21 (81%)	5 (29%)	3 (18%)	3 (18%)	1 (6%)
Experimental Weight Set 3 Winner	35	11 (44%)	6 (24%)	2 (8%)	19 (76%)	3 (18%)	4 (24%)	2 (12%)	1 (6%)
AI Longshot	8	1 (14%)	4 (57%)	1 (14%)	6 (86%)	—	—	—	—
Expert Consensus	35	10 (42%)	4 (17%)	3 (12%)	17 (71%)	2 (8%)	2 (8%)	0 (0%)	3 (12%)
ML Favorite (chalk)	35	17 (49%)	4 (11%)	4 (11%)	25 (71%)	—	—	—	—

EQB

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	3	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
Algo 3 Winner	3	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
Algo 1 Winner	3	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
Experimental Weight Set 2 Winner	3	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
Experimental Weight Set 3 Winner	3	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)

EQK

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	5	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
Algo 3 Winner	5	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
Algo 1 Winner	5	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
Experimental Weight Set 2 Winner	5	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
Experimental Weight Set 3 Winner	5	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
AI Longshot	3	0 (—)	0 (—)	0 (—)	0 (—)	—	—	—	—

EUR

AI Picks posts graded here: Sat 10/17

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	4	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
Algo 3 Winner	4	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
Algo 1 Winner	4	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
Experimental Weight Set 2 Winner	4	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
Experimental Weight Set 3 Winner	4	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
AI Longshot	1	0 (—)	0 (—)	0 (—)	0 (—)	—	—	—	—
Expert Consensus	10	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)

EVD

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Expert Consensus	28	7 (26%)	5 (19%)	4 (15%)	16 (59%)	2 (7%)	0 (0%)	0 (0%)	1 (4%)

FEX

AI Picks posts graded here: Mon 10/12 · Tue 10/13

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	13	5 (38%)	3 (23%)	3 (23%)	11 (85%)	2 (17%)	1 (8%)	1 (8%)	0 (0%)
Algo 3 Winner	13	5 (42%)	1 (8%)	2 (17%)	8 (67%)	1 (8%)	0 (0%)	1 (8%)	0 (0%)
Algo 1 Winner	13	6 (46%)	1 (8%)	1 (8%)	8 (62%)	1 (8%)	0 (0%)	0 (0%)	1 (8%)
Experimental Weight Set 2 Winner	13	7 (54%)	1 (8%)	2 (15%)	10 (77%)	2 (17%)	1 (8%)	0 (0%)	0 (0%)
Experimental Weight Set 3 Winner	13	5 (42%)	0 (0%)	1 (8%)	6 (50%)	1 (8%)	0 (0%)	0 (0%)	1 (8%)
Expert Consensus	13	4 (33%)	0 (0%)	5 (42%)	9 (75%)	0 (0%)	0 (0%)	0 (0%)	1 (8%)
ML Favorite (chalk)	13	4 (31%)	3 (23%)	4 (31%)	11 (85%)	—	—	—	—

FHX

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	6	0 (0%)	0 (0%)	1 (100%)	1 (100%)	0 (—)	0 (—)	0 (—)	0 (—)
Algo 3 Winner	6	0 (0%)	0 (0%)	1 (100%)	1 (100%)	0 (—)	0 (—)	0 (—)	0 (—)
Algo 1 Winner	6	0 (0%)	0 (0%)	0 (0%)	0 (0%)	0 (—)	0 (—)	0 (—)	0 (—)
Experimental Weight Set 2 Winner	6	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
Experimental Weight Set 3 Winner	6	0 (0%)	0 (0%)	0 (0%)	0 (0%)	0 (—)	0 (—)	0 (—)	0 (—)
AI Longshot	5	0 (—)	0 (—)	0 (—)	0 (—)	—	—	—	—
ML Favorite (chalk)	1	1 (100%)	0 (0%)	0 (0%)	1 (100%)	—	—	—	—

FLX

AI Picks posts graded here: Mon 10/12 · Tue 10/13 · Wed 10/14

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	26	11 (44%)	4 (16%)	5 (20%)	20 (80%)	7 (32%)	1 (5%)	2 (9%)	3 (14%)
Algo 3 Winner	26	11 (44%)	5 (20%)	4 (16%)	20 (80%)	5 (22%)	4 (17%)	2 (9%)	4 (17%)
Algo 1 Winner	26	9 (39%)	6 (26%)	3 (13%)	18 (78%)	2 (10%)	4 (19%)	2 (10%)	1 (5%)
Experimental Weight Set 2 Winner	26	6 (27%)	5 (23%)	3 (14%)	14 (64%)	2 (10%)	1 (5%)	1 (5%)	1 (5%)
Experimental Weight Set 3 Winner	26	12 (50%)	5 (21%)	3 (12%)	20 (83%)	5 (23%)	2 (9%)	1 (5%)	2 (9%)
AI Longshot	4	0 (0%)	1 (25%)	0 (0%)	1 (25%)	—	—	—	—
Expert Consensus	26	13 (52%)	3 (12%)	4 (16%)	20 (80%)	5 (20%)	1 (4%)	2 (8%)	3 (12%)
ML Favorite (chalk)	26	10 (38%)	6 (23%)	4 (15%)	20 (77%)	—	—	—	—

FPK

AI Picks posts graded here: Tue 10/13 · Sat 10/17

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	16	8 (50%)	5 (31%)	0 (0%)	13 (81%)	1 (7%)	1 (7%)	1 (7%)	3 (21%)
Algo 3 Winner	16	7 (44%)	4 (25%)	1 (6%)	12 (75%)	1 (7%)	1 (7%)	1 (7%)	3 (20%)
Algo 1 Winner	16	7 (44%)	3 (19%)	1 (6%)	11 (69%)	2 (14%)	1 (7%)	2 (14%)	1 (7%)
Experimental Weight Set 2 Winner	16	7 (44%)	4 (25%)	2 (12%)	13 (81%)	2 (13%)	1 (7%)	2 (13%)	2 (13%)
Experimental Weight Set 3 Winner	16	6 (38%)	4 (25%)	2 (12%)	12 (75%)	2 (14%)	0 (0%)	2 (14%)	0 (0%)
AI Longshot	6	0 (0%)	0 (0%)	0 (0%)	0 (0%)	—	—	—	—
Expert Consensus	16	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
ML Favorite (chalk)	16	7 (44%)	5 (31%)	0 (0%)	12 (75%)	—	—	—	—

GPX

AI Picks posts graded here: Sun 10/11 · Fri 10/16 · Sat 10/17

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	28	8 (38%)	3 (14%)	4 (19%)	15 (71%)	2 (14%)	2 (14%)	0 (0%)	0 (0%)
Algo 3 Winner	28	8 (35%)	4 (17%)	4 (17%)	16 (70%)	1 (6%)	3 (18%)	0 (0%)	0 (0%)
Algo 1 Winner	28	7 (32%)	4 (18%)	5 (23%)	16 (73%)	1 (7%)	2 (13%)	0 (0%)	1 (7%)
Experimental Weight Set 2 Winner	28	11 (48%)	4 (17%)	3 (13%)	18 (78%)	3 (18%)	2 (12%)	0 (0%)	0 (0%)
Experimental Weight Set 3 Winner	28	9 (39%)	5 (22%)	3 (13%)	17 (74%)	1 (6%)	3 (17%)	0 (0%)	1 (6%)
AI Longshot	3	0 (0%)	0 (0%)	0 (0%)	0 (0%)	—	—	—	—
Expert Consensus	42	8 (35%)	4 (17%)	3 (13%)	15 (65%)	2 (9%)	3 (13%)	0 (0%)	2 (9%)
ML Favorite (chalk)	28	13 (46%)	3 (11%)	4 (14%)	20 (71%)	—	—	—	—

GRP

AI Picks posts graded here: Sun 10/11 · Mon 10/12

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	14	5 (38%)	2 (15%)	0 (0%)	7 (54%)	2 (20%)	0 (0%)	2 (20%)	0 (0%)
Algo 3 Winner	14	4 (29%)	3 (21%)	0 (0%)	7 (50%)	1 (9%)	1 (9%)	1 (9%)	1 (9%)
Algo 1 Winner	14	4 (33%)	3 (25%)	0 (0%)	7 (58%)	1 (9%)	1 (9%)	0 (0%)	1 (9%)
Experimental Weight Set 2 Winner	14	5 (38%)	2 (15%)	0 (0%)	7 (54%)	1 (10%)	1 (10%)	0 (0%)	1 (10%)
Experimental Weight Set 3 Winner	14	3 (25%)	3 (25%)	0 (0%)	6 (50%)	1 (10%)	1 (10%)	0 (0%)	0 (0%)
AI Longshot	2	0 (0%)	0 (0%)	0 (0%)	0 (0%)	—	—	—	—
ML Favorite (chalk)	14	5 (36%)	2 (14%)	1 (7%)	8 (57%)	—	—	—	—

IND

AI Picks posts graded here: Mon 10/12 · Tue 10/13 · Wed 10/14 · Thu 10/15

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	32	10 (45%)	3 (14%)	3 (14%)	16 (73%)	3 (17%)	0 (0%)	0 (0%)	1 (6%)
Algo 3 Winner	32	12 (52%)	2 (9%)	4 (17%)	18 (78%)	3 (19%)	0 (0%)	0 (0%)	0 (0%)
Algo 1 Winner	32	9 (38%)	1 (4%)	5 (21%)	15 (62%)	2 (11%)	0 (0%)	0 (0%)	2 (11%)
Experimental Weight Set 2 Winner	32	8 (32%)	5 (20%)	3 (12%)	16 (64%)	1 (6%)	1 (6%)	0 (0%)	1 (6%)
Experimental Weight Set 3 Winner	32	8 (32%)	4 (16%)	3 (12%)	15 (60%)	2 (11%)	0 (0%)	0 (0%)	2 (11%)
AI Longshot	23	3 (17%)	1 (6%)	1 (6%)	5 (28%)	—	—	—	—
Expert Consensus	36	8 (30%)	6 (22%)	5 (19%)	19 (70%)	1 (4%)	2 (7%)	0 (0%)	3 (11%)
ML Favorite (chalk)	32	11 (34%)	8 (25%)	4 (12%)	23 (72%)	—	—	—	—

KEE

AI Picks posts graded here: Sun 10/11 · Wed 10/14 · Thu 10/15 · Fri 10/16 · Sat 10/17

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	46	13 (41%)	7 (22%)	1 (3%)	21 (66%)	1 (5%)	2 (10%)	0 (0%)	0 (0%)
Algo 3 Winner	46	14 (44%)	6 (19%)	1 (3%)	21 (66%)	1 (5%)	1 (5%)	0 (0%)	1 (5%)
Algo 1 Winner	46	14 (42%)	3 (9%)	1 (3%)	18 (55%)	2 (10%)	0 (0%)	0 (0%)	0 (0%)
Experimental Weight Set 2 Winner	46	12 (35%)	8 (24%)	1 (3%)	21 (62%)	1 (5%)	2 (10%)	1 (5%)	0 (0%)
Experimental Weight Set 3 Winner	46	15 (45%)	5 (15%)	1 (3%)	21 (64%)	1 (5%)	0 (0%)	1 (5%)	0 (0%)
AI Longshot	49	2 (5%)	1 (3%)	6 (15%)	9 (23%)	—	—	—	—
Expert Consensus	46	11 (33%)	8 (24%)	5 (15%)	24 (73%)	1 (3%)	2 (6%)	0 (0%)	1 (3%)
ML Favorite (chalk)	46	14 (30%)	7 (15%)	6 (13%)	27 (59%)	—	—	—	—

LAX

AI Picks posts graded here: Sun 10/11 · Sat 10/17

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	3	3 (100%)	0 (0%)	0 (0%)	3 (100%)	0 (0%)	0 (0%)	0 (0%)	1 (100%)
Algo 3 Winner	3	2 (100%)	0 (0%)	0 (0%)	2 (100%)	0 (0%)	0 (0%)	0 (0%)	1 (100%)
Algo 1 Winner	3	3 (100%)	0 (0%)	0 (0%)	3 (100%)	0 (0%)	0 (0%)	0 (0%)	1 (100%)
Experimental Weight Set 2 Winner	3	3 (100%)	0 (0%)	0 (0%)	3 (100%)	0 (0%)	0 (0%)	0 (0%)	0 (0%)
Experimental Weight Set 3 Winner	3	3 (100%)	0 (0%)	0 (0%)	3 (100%)	0 (0%)	0 (0%)	0 (0%)	1 (100%)
ML Favorite (chalk)	3	3 (100%)	0 (0%)	0 (0%)	3 (100%)	—	—	—	—

LBG

AI Picks posts graded here: Sun 10/11 · Mon 10/12

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	13	3 (25%)	5 (42%)	1 (8%)	9 (75%)	1 (12%)	3 (38%)	1 (12%)	1 (12%)
Algo 3 Winner	13	3 (27%)	5 (45%)	2 (18%)	10 (91%)	1 (12%)	3 (38%)	1 (12%)	1 (12%)
Algo 1 Winner	13	3 (27%)	5 (45%)	0 (0%)	8 (73%)	0 (0%)	1 (14%)	0 (0%)	1 (14%)
Experimental Weight Set 2 Winner	13	5 (42%)	4 (33%)	1 (8%)	10 (83%)	4 (50%)	2 (25%)	0 (0%)	1 (12%)
Experimental Weight Set 3 Winner	13	4 (33%)	4 (33%)	2 (17%)	10 (83%)	3 (43%)	1 (14%)	1 (14%)	2 (29%)
ML Favorite (chalk)	13	4 (31%)	5 (38%)	2 (15%)	11 (85%)	—	—	—	—

LRL

AI Picks posts graded here: Sun 10/11 · Thu 10/15 · Fri 10/16 · Sat 10/17

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	35	8 (42%)	6 (32%)	2 (11%)	16 (84%)	1 (8%)	0 (0%)	1 (8%)	2 (17%)
Algo 3 Winner	35	7 (37%)	6 (32%)	3 (16%)	16 (84%)	1 (8%)	1 (8%)	1 (8%)	1 (8%)
Algo 1 Winner	35	5 (25%)	6 (30%)	5 (25%)	16 (80%)	1 (8%)	1 (8%)	0 (0%)	2 (17%)
Experimental Weight Set 2 Winner	35	5 (25%)	8 (40%)	2 (10%)	15 (75%)	0 (0%)	1 (10%)	0 (0%)	1 (10%)
Experimental Weight Set 3 Winner	35	6 (32%)	7 (37%)	3 (16%)	16 (84%)	2 (20%)	0 (0%)	1 (10%)	2 (20%)
AI Longshot	22	0 (0%)	1 (17%)	2 (33%)	3 (50%)	—	—	—	—
Expert Consensus	55	5 (28%)	6 (33%)	2 (11%)	13 (72%)	2 (11%)	2 (11%)	0 (0%)	3 (17%)
ML Favorite (chalk)	26	8 (31%)	9 (35%)	3 (12%)	20 (77%)	—	—	—	—

LSX

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Expert Consensus	29	6 (26%)	5 (22%)	6 (26%)	17 (74%)	2 (9%)	1 (4%)	0 (0%)	1 (4%)

MED

AI Picks posts graded here: Fri 10/16

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	6	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
Algo 3 Winner	6	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
Algo 1 Winner	6	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
Experimental Weight Set 2 Winner	6	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)
Experimental Weight Set 3 Winner	6	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)	0 (—)

MNR

AI Picks posts graded here: Sun 10/11 · Mon 10/12 · Tue 10/13

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	24	6 (35%)	6 (35%)	3 (18%)	15 (88%)	1 (10%)	3 (30%)	0 (0%)	3 (30%)
Algo 3 Winner	24	8 (53%)	5 (33%)	2 (13%)	15 (100%)	1 (11%)	1 (11%)	0 (0%)	2 (22%)
Algo 1 Winner	24	7 (44%)	6 (38%)	3 (19%)	16 (100%)	2 (25%)	4 (50%)	1 (12%)	2 (25%)
Experimental Weight Set 2 Winner	24	8 (42%)	6 (32%)	2 (11%)	16 (84%)	2 (22%)	1 (11%)	1 (11%)	2 (22%)
Experimental Weight Set 3 Winner	24	9 (47%)	8 (42%)	1 (5%)	18 (95%)	1 (11%)	4 (44%)	0 (0%)	3 (33%)
AI Longshot	6	0 (0%)	0 (0%)	1 (20%)	1 (20%)	—	—	—	—
Expert Consensus	24	8 (44%)	6 (33%)	1 (6%)	15 (83%)	3 (17%)	3 (17%)	1 (6%)	1 (6%)
ML Favorite (chalk)	24	8 (33%)	6 (25%)	2 (8%)	16 (67%)	—	—	—	—

PEN

AI Picks posts graded here: Wed 10/14 · Thu 10/15 · Fri 10/16

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	21	11 (58%)	4 (21%)	1 (5%)	16 (84%)	4 (24%)	1 (6%)	3 (18%)	2 (12%)
Algo 3 Winner	21	9 (45%)	6 (30%)	1 (5%)	16 (80%)	3 (18%)	4 (24%)	1 (6%)	6 (35%)
Algo 1 Winner	21	11 (55%)	3 (15%)	2 (10%)	16 (80%)	5 (31%)	3 (19%)	2 (12%)	2 (12%)
Experimental Weight Set 2 Winner	21	10 (50%)	3 (15%)	4 (20%)	17 (85%)	2 (13%)	2 (13%)	0 (0%)	4 (27%)
Experimental Weight Set 3 Winner	21	11 (55%)	4 (20%)	3 (15%)	18 (90%)	1 (6%)	3 (18%)	0 (0%)	6 (35%)
Expert Consensus	21	9 (45%)	5 (25%)	3 (15%)	17 (85%)	3 (15%)	0 (0%)	2 (10%)	1 (5%)
ML Favorite (chalk)	21	10 (48%)	4 (19%)	3 (14%)	17 (81%)	—	—	—	—

PID

AI Picks posts graded here: Mon 10/12 · Tue 10/13 · Wed 10/14

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	24	8 (36%)	3 (14%)	4 (18%)	15 (68%)	2 (11%)	2 (11%)	1 (5%)	1 (5%)
Algo 3 Winner	24	5 (24%)	4 (19%)	3 (14%)	12 (57%)	1 (5%)	3 (16%)	1 (5%)	1 (5%)
Algo 1 Winner	24	6 (29%)	4 (19%)	3 (14%)	13 (62%)	1 (5%)	1 (5%)	1 (5%)	0 (0%)
Experimental Weight Set 2 Winner	24	8 (35%)	2 (9%)	2 (9%)	12 (52%)	1 (6%)	0 (0%)	1 (6%)	0 (0%)
Experimental Weight Set 3 Winner	24	7 (30%)	4 (17%)	2 (9%)	13 (57%)	2 (11%)	1 (6%)	1 (6%)	0 (0%)
AI Longshot	1	0 (—)	0 (—)	0 (—)	0 (—)	—	—	—	—
Expert Consensus	24	7 (33%)	5 (24%)	3 (14%)	15 (71%)	1 (5%)	3 (14%)	0 (0%)	2 (10%)
ML Favorite (chalk)	24	9 (38%)	3 (12%)	3 (12%)	15 (62%)	—	—	—	—

PRX

AI Picks posts graded here: Mon 10/12 · Tue 10/13 · Wed 10/14

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	30	7 (24%)	6 (21%)	4 (14%)	17 (59%)	3 (11%)	2 (7%)	0 (0%)	5 (19%)
Algo 3 Winner	30	7 (24%)	10 (34%)	2 (7%)	19 (66%)	3 (11%)	4 (15%)	0 (0%)	7 (26%)
Algo 1 Winner	30	10 (36%)	8 (29%)	3 (11%)	21 (75%)	4 (14%)	3 (11%)	1 (4%)	5 (18%)
Experimental Weight Set 2 Winner	30	10 (36%)	7 (25%)	2 (7%)	19 (68%)	4 (16%)	2 (8%)	1 (4%)	1 (4%)
Experimental Weight Set 3 Winner	30	9 (31%)	7 (24%)	4 (14%)	20 (69%)	5 (19%)	2 (7%)	2 (7%)	4 (15%)
Expert Consensus	30	7 (23%)	12 (40%)	3 (10%)	22 (73%)	1 (3%)	2 (7%)	0 (0%)	2 (7%)
ML Favorite (chalk)	30	7 (23%)	8 (27%)	6 (20%)	21 (70%)	—	—	—	—

RPX

AI Picks posts graded here: Wed 10/14 · Thu 10/15 · Fri 10/16 · Sat 10/17

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	37	12 (38%)	7 (22%)	3 (9%)	22 (69%)	4 (14%)	2 (7%)	2 (7%)	4 (14%)
Algo 3 Winner	37	11 (35%)	9 (29%)	2 (6%)	22 (71%)	3 (10%)	1 (3%)	1 (3%)	5 (17%)
Algo 1 Winner	37	14 (39%)	10 (28%)	3 (8%)	27 (75%)	4 (14%)	2 (7%)	1 (4%)	3 (11%)
Experimental Weight Set 2 Winner	37	13 (39%)	6 (18%)	5 (15%)	24 (73%)	4 (14%)	0 (0%)	1 (3%)	3 (10%)
Experimental Weight Set 3 Winner	37	14 (40%)	10 (29%)	4 (11%)	28 (80%)	6 (21%)	2 (7%)	4 (14%)	2 (7%)
AI Longshot	10	1 (14%)	1 (14%)	1 (14%)	3 (43%)	—	—	—	—
Expert Consensus	37	9 (27%)	7 (21%)	5 (15%)	21 (64%)	2 (6%)	0 (0%)	1 (3%)	0 (0%)
ML Favorite (chalk)	37	15 (41%)	9 (24%)	2 (5%)	26 (70%)	—	—	—	—

SAX

AI Picks posts graded here: Sun 10/11 · Mon 10/12 · Fri 10/16 · Sat 10/17

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	38	16 (43%)	4 (11%)	3 (8%)	23 (62%)	4 (12%)	3 (9%)	2 (6%)	1 (3%)
Algo 3 Winner	38	13 (35%)	4 (11%)	6 (16%)	23 (62%)	4 (12%)	2 (6%)	2 (6%)	1 (3%)
Algo 1 Winner	38	11 (31%)	9 (26%)	5 (14%)	25 (71%)	1 (3%)	2 (6%)	0 (0%)	3 (9%)
Experimental Weight Set 2 Winner	38	13 (37%)	7 (20%)	4 (11%)	24 (69%)	4 (12%)	2 (6%)	2 (6%)	1 (3%)
Experimental Weight Set 3 Winner	38	15 (43%)	6 (17%)	3 (9%)	24 (69%)	3 (9%)	2 (6%)	0 (0%)	3 (9%)
AI Longshot	27	0 (0%)	3 (12%)	4 (17%)	7 (29%)	—	—	—	—
Expert Consensus	38	10 (27%)	4 (11%)	4 (11%)	18 (49%)	2 (5%)	3 (8%)	2 (5%)	1 (3%)
ML Favorite (chalk)	38	15 (39%)	5 (13%)	4 (11%)	24 (63%)	—	—	—	—

WOX

AI Picks posts graded here: Sun 10/11 · Thu 10/15 · Fri 10/16 · Sat 10/17

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	37	8 (24%)	9 (26%)	1 (3%)	18 (53%)	1 (3%)	1 (3%)	1 (3%)	1 (3%)
Algo 3 Winner	37	8 (23%)	8 (23%)	2 (6%)	18 (51%)	1 (3%)	3 (9%)	1 (3%)	0 (0%)
Algo 1 Winner	37	8 (23%)	5 (14%)	3 (9%)	16 (46%)	2 (6%)	0 (0%)	1 (3%)	0 (0%)
Experimental Weight Set 2 Winner	37	9 (26%)	6 (17%)	3 (9%)	18 (51%)	1 (3%)	2 (6%)	0 (0%)	2 (6%)
Experimental Weight Set 3 Winner	37	8 (24%)	9 (26%)	3 (9%)	20 (59%)	2 (6%)	2 (6%)	1 (3%)	1 (3%)
AI Longshot	6	1 (17%)	1 (17%)	0 (0%)	2 (33%)	—	—	—	—
Expert Consensus	37	9 (26%)	7 (20%)	2 (6%)	18 (51%)	0 (0%)	3 (9%)	0 (0%)	0 (0%)
ML Favorite (chalk)	37	7 (19%)	11 (30%)	2 (5%)	20 (54%)	—	—	—	—

WRD

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Expert Consensus	30	10 (37%)	5 (19%)	3 (11%)	18 (67%)	0 (0%)	2 (7%)	0 (0%)	1 (4%)