Pick Pony Weekly Picks Recap — September 21, 2026

AI Picks Performance This Week

What a week for Pick Pony's AI engine! Our flagship AI Best Bets system delivered its strongest headline number of the week, with the top pick landing in the money an incredible 80.2% of the time across 318 settled races — meaning four out of every five Best Bet top picks finished win, place, or show. The win rate alone came in at 38.4%, comfortably clearing the morning-line chalk baseline of 34.8%, proving once again that our AI isn't just tracking the crowd — it's beating it. Over on the exotic side, the AI Exacta model covered 616 settled races and posted a solid 70.6% ITM rate, while racking up 48 straight exactas, 59 boxed exactas, and an impressive 65 boxed trifectas — giving players plenty of ways to cash tickets all week long. The experimental models also turned heads: Experimental Weight Set 3 topped the broader model field with a 35.2% win rate and 58 straight exacta hits, while the AI Ensemble (Algo 2) checked in at 33.6% wins and a 70.5% ITM rate, backed by 53 straight exactas and 59 boxed trifectas. With 14 pending races still to be settled across several models, those numbers have nowhere to go but up.

Standout Wins

The highlight reel this week is absolutely packed. On September 20 at Belmont, our AI Best Bets, AI Exacta, Algo 2, and Experimental Weight Set 3 models all converged on Long Pour (ML 4-1) — a true cross-system consensus that rewarded bettors in a big way. The longshot hunters were also well served: Algo 1 and the Experimental Weight Sets spotted CARDIFF BY THE SEA at 15-1 at Albuquerque on September 16, an outstanding overlay that the morning line completely underestimated. Not to be outdone, SENSATIONAL Z Z (ML 10-1) at Los Alamitos on September 18 was flagged by Algo 1, and GALATINA (ML 15-1) at CDX on September 17 was correctly identified by Experimental Weight Set 2 — two more examples of the AI finding genuine value where the public wasn't looking. Algo 3's Dignify (ML 6-1) at Belmont on September 20 and Carita Linda (ML 6-1) at GRP, also on September 20, rounded out a week where the AI repeatedly outpaced the chalk and delivered real, meaningful prices to players willing to trust the data.

Key Insights

A few clear themes emerged from this week's results. First, the AI models showed a distinct edge at mid-range overlays in the 4-1 to 6-1 range, where the win probability models identified horses the public was undervaluing but that weren't extreme longshots — the sweet spot for value betting. Second, the cross-model consensus picks — horses flagged by multiple algorithms simultaneously, like LONG POUR, DIVINE SEEKER, and CAUGHT OFF GUARD — posted an exceptional hit rate, reinforcing that when the AI systems agree, bettors should pay close attention. Third, Experimental Weight Set 3's trifecta performance (18 straight, 52 boxed) suggests the updated weighting scheme is developing a particularly sharp eye for race order, making it one to watch closely as it continues to mature. The morning-update versions of the models also showed meaningful, if incremental, improvements over their standard counterparts, confirming that the late-breaking data pipeline is adding genuine predictive value as post time approaches.

Looking Ahead

With several models still fine-tuning and the experimental weight sets showing real promise, next week is shaping up to be even more exciting — keep an eye on Experimental Weight Set 3 and the morning-update models as they continue to refine their edge. Stay locked in to Pick Pony's AI Picks, trust the data, and let the algorithms do the heavy lifting! 🏇

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 616 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	33.6%	616
Finished 2nd	20.9%	616
Finished 3rd	15.9%	616
In the money	70.5%	616

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	710
Top Pick Wins (1st)	207	33.6%
Top Pick Places (2nd)	129	20.9%
Top Pick Shows (3rd)	98	15.9%
Top Pick ITM	434	70.5%
Pending	26

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	Description
Exacta	53	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	55	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	14	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	59	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	710
Top Pick Wins (1st)	207	33.5%
Top Pick Places (2nd)	131	21.2%
Top Pick Shows (3rd)	98	15.9%
Top Pick ITM	436	70.6%
Pending	26

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	Description
Exacta	53	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	56	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	14	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	60	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	710
Top Pick Wins (1st)	179	29.0%
Top Pick Places (2nd)	133	21.6%
Top Pick Shows (3rd)	113	18.3%
Top Pick ITM	425	68.9%
Pending	26

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	Description
Exacta	43	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	46	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	15	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	58	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	710
Top Pick Wins (1st)	179	29.0%
Top Pick Places (2nd)	134	21.7%
Top Pick Shows (3rd)	113	18.3%
Top Pick ITM	426	68.9%
Pending	26

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	Description
Exacta	43	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	47	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	15	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	59	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	710
Top Pick Wins (1st)	200	32.1%
Top Pick Places (2nd)	126	20.2%
Top Pick Shows (3rd)	87	13.9%
Top Pick ITM	413	66.2%
Pending	27

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	Description
Exacta	52	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	49	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	10	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	48	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	710
Top Pick Wins (1st)	200	32.1%
Top Pick Places (2nd)	126	20.2%
Top Pick Shows (3rd)	87	13.9%
Top Pick ITM	413	66.2%
Pending	27

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	Description
Exacta	53	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	49	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	11	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	48	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	710
Top Pick Wins (1st)	206	33.4%
Top Pick Places (2nd)	141	22.9%
Top Pick Shows (3rd)	88	14.3%
Top Pick ITM	435	70.6%
Pending	26

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	Description
Exacta	48	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	59	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	14	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	65	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	710
Top Pick Wins (1st)	191	30.9%
Top Pick Places (2nd)	132	21.4%
Top Pick Shows (3rd)	95	15.4%
Top Pick ITM	418	67.6%
Pending	27

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	Description
Exacta	48	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	50	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	9	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	63	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	710
Top Pick Wins (1st)	191	30.9%
Top Pick Places (2nd)	133	21.5%
Top Pick Shows (3rd)	95	15.3%
Top Pick ITM	419	67.7%
Pending	27

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	Description
Exacta	48	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	50	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	9	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	64	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	710
Top Pick Wins (1st)	218	35.0%
Top Pick Places (2nd)	125	20.1%
Top Pick Shows (3rd)	86	13.8%
Top Pick ITM	429	69.0%
Pending	27

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	Description
Exacta	57	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	45	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	17	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	52	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	710
Top Pick Wins (1st)	219	35.2%
Top Pick Places (2nd)	125	20.1%
Top Pick Shows (3rd)	86	13.8%
Top Pick ITM	430	69.0%
Pending	27

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	Description
Exacta	58	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	45	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	18	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	52	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	354
Top Pick Wins (1st)	122	38.4%
Top Pick Places (2nd)	80	25.2%
Top Pick Shows (3rd)	53	16.7%
Top Pick ITM	255	80.2%
Pending	14

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	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

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	147	58	35	28	39.5%
2 of 3 AI models + experts	93	34	26	15	36.6%
1 of 3 AI models + experts	66	22	17	9	33.3%
All Best Bets	306	114	78	52	37.3%
Pending	80

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	265
Races Covered	167
Wins (1st)	10	4.9%
Places (2nd)	11	5.4%
Shows (3rd)	20	9.8%
ITM	41	20.0%
Pending	14

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: 2565; wider 10/1-and-longer universe available to the edge rows: 14747, of which 12809 could be assigned a calibrated edge. Calibrator: out-of-sample tiered calibrator on the cross-race win probability (lgbm_win_prob_fwd), trained through 2026-07-30; edge rows replay only the 52 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 52 days (12809 runners), because everything before 2026-07-30 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	2565	142 (5.5%)	$5130.00	$3112.26
$2 PLACE — all longshots	2565	364 (14.2%)	$5130.00	$3486.76
$2 SHOW — all longshots	2565	595 (23.2%)	$5130.00	$3372.52
$2 WIN + $2 PLACE	2565	364 (14.2%)	$10260.00	$6599.02
$2 WIN — ML ≥ 15/1	1563	71 (4.5%)	$3126.00	$1920.58
$2 WIN — ML ≥ 20/1	1021	32 (3.1%)	$2042.00	$1042.36
$2 WIN — field ≥ 8	1741	94 (5.4%)	$3482.00	$2282.40
$2 WIN — edge ≥ 5%	7438	438 (5.9%)	$14876.00	$9575.56
$2 WIN — edge ≥ 10%	6256	379 (6.1%)	$12512.00	$8316.66
$2 WIN — edge ≥ 20%	5619	345 (6.1%)	$11238.00	$7442.90
$2 WIN — edge ≥ 30%	3798	268 (7.1%)	$7596.00	$4819.14
$2 WIN — edge ≥ 40%	2719	202 (7.4%)	$5438.00	$3457.64
$2 WIN — edge ≥ 50%	1084	83 (7.7%)	$2168.00	$1472.42
$2 WIN — edge ≥ 60%	11	2 (18.2%)	$22.00	$37.80
$2 WIN — edge ≥ 70%	0	—	$0.00	$0.00
$2 WIN — edge ≥ 80%	0	—	$0.00	$0.00
$2 WIN — edge ≥ 90%	0	—	$0.00	$0.00
$2 WIN — edge ≥ 100%	0	—	$0.00	$0.00
$2 WIN — edge ≥ 10% AND field ≥ 8	3611	211 (5.8%)	$7222.00	$5119.88

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	375
Trifectas hit	45 (12.0%)
Total staked	$1,407.00
Total returned	$1,011.80

300 race(s) skipped for scratches inside the top four; 35 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	491
Favorite Wins (1st)	171	34.8%
Favorite Places (2nd)	99	20.2%
Favorite Shows (3rd)	67	13.6%
Favorite ITM	337	68.6%

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	651
Top Pick Wins (1st)	183	32.8%
Top Pick Places (2nd)	135	24.2%
Top Pick Shows (3rd)	92	16.5%
Top Pick ITM	410	73.5%
Pending	93

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	Description
Exacta	47	Picks 1 & 2 finished 1st & 2nd in exact order
Boxed Exacta	42	Picks 1 & 2 both finished in top 2, reversed order
Trifecta	18	Picks 1, 2 & 3 finished 1st, 2nd & 3rd in exact order
Boxed Trifecta	42	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	710	207 (34%)	129 (21%)	98 (16%)	434 (70%)	53	55	14	59
Algo 3 Winner	710	179 (29%)	133 (22%)	113 (18%)	425 (69%)	43	46	15	58
Algo 1 Winner	710	200 (32%)	126 (20%)	87 (14%)	413 (66%)	52	49	10	48
Experimental Weight Set 2 Winner	710	191 (31%)	132 (21%)	95 (15%)	418 (68%)	48	50	9	63
Experimental Weight Set 3 Winner	710	218 (35%)	125 (20%)	86 (14%)	429 (69%)	57	45	17	52
AI Longshot	265	10 (5%)	11 (5%)	20 (10%)	41 (20%)	—	—	—	—

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	7	0 (—)	0 (—)	0 (—)	0 (—)	0	0	0	0

ALB

AI Picks posts graded here: Wed 9/16 · Thu 9/17 · Sat 9/19 · Sun 9/20

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	16	3 (20%)	3 (20%)	2 (13%)	8 (53%)	0	0	0	1
Algo 3 Winner	16	3 (21%)	2 (14%)	0 (0%)	5 (36%)	0	0	0	1
Algo 1 Winner	16	3 (19%)	6 (38%)	1 (6%)	10 (62%)	0	2	0	0
Experimental Weight Set 2 Winner	16	1 (7%)	5 (36%)	1 (7%)	7 (50%)	0	1	0	1
Experimental Weight Set 3 Winner	16	2 (13%)	4 (27%)	2 (13%)	8 (53%)	0	1	0	1
AI Longshot	6	1 (20%)	2 (40%)	0 (0%)	3 (60%)	—	—	—	—
Expert Consensus	48	8 (23%)	4 (11%)	4 (11%)	16 (46%)	1	0	0	2
ML Favorite (chalk)	16	4 (25%)	1 (6%)	2 (12%)	7 (44%)	—	—	—	—

ASD

AI Picks posts graded here: Mon 9/14 · Tue 9/15 · Wed 9/16

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	21	7 (35%)	3 (15%)	7 (35%)	17 (85%)	2	0	2	0
Algo 3 Winner	21	4 (20%)	2 (10%)	4 (20%)	10 (50%)	1	1	1	1
Algo 1 Winner	21	8 (38%)	3 (14%)	3 (14%)	14 (67%)	2	0	0	2
Experimental Weight Set 2 Winner	21	8 (38%)	3 (14%)	5 (24%)	16 (76%)	3	0	1	2
Experimental Weight Set 3 Winner	21	9 (43%)	3 (14%)	5 (24%)	17 (81%)	4	0	3	1
AI Longshot	6	1 (17%)	0 (0%)	2 (33%)	3 (50%)	—	—	—	—
Expert Consensus	21	8 (40%)	3 (15%)	5 (25%)	16 (80%)	2	1	1	0
ML Favorite (chalk)	21	7 (33%)	3 (14%)	5 (24%)	15 (71%)	—	—	—	—

BEL

AI Picks posts graded here: Fri 9/18 · Sat 9/19 · Sun 9/20

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	28	9 (39%)	5 (22%)	5 (22%)	19 (83%)	1	2	0	3
Algo 3 Winner	28	6 (29%)	4 (19%)	5 (24%)	15 (71%)	1	2	0	2
Algo 1 Winner	28	7 (27%)	5 (19%)	3 (12%)	15 (58%)	2	2	2	0
Experimental Weight Set 2 Winner	28	7 (27%)	4 (15%)	3 (12%)	14 (54%)	1	1	0	2
Experimental Weight Set 3 Winner	28	6 (22%)	5 (19%)	5 (19%)	16 (59%)	1	2	1	2
AI Longshot	34	1 (4%)	0 (0%)	2 (7%)	3 (11%)	—	—	—	—
Expert Consensus	25	8 (36%)	3 (14%)	3 (14%)	14 (64%)	0	0	0	0
ML Favorite (chalk)	28	7 (25%)	5 (18%)	9 (32%)	21 (75%)	—	—	—	—

BTP

AI Picks posts graded here: Wed 9/16 · Thu 9/17 · Fri 9/18 · Sat 9/19

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	32	17 (57%)	5 (17%)	3 (10%)	25 (83%)	5	3	1	4
Algo 3 Winner	32	12 (39%)	8 (26%)	4 (13%)	24 (77%)	3	3	2	5
Algo 1 Winner	32	18 (62%)	6 (21%)	2 (7%)	26 (90%)	8	3	2	2
Experimental Weight Set 2 Winner	32	14 (47%)	10 (33%)	2 (7%)	26 (87%)	4	6	0	4
Experimental Weight Set 3 Winner	32	19 (63%)	6 (20%)	2 (7%)	27 (90%)	9	3	3	2
AI Longshot	2	0 (0%)	0 (0%)	0 (0%)	0 (0%)	—	—	—	—
Expert Consensus	32	16 (50%)	8 (25%)	3 (9%)	27 (84%)	4	1	1	0
ML Favorite (chalk)	32	16 (50%)	8 (25%)	2 (6%)	26 (81%)	—	—	—	—

CBY

AI Picks posts graded here: Wed 9/16 · Thu 9/17 · Sat 9/19

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	24	10 (50%)	5 (25%)	0 (0%)	15 (75%)	3	2	1	1
Algo 3 Winner	24	5 (26%)	4 (21%)	2 (11%)	11 (58%)	1	2	0	2
Algo 1 Winner	24	9 (45%)	5 (25%)	1 (5%)	15 (75%)	4	1	1	1
Experimental Weight Set 2 Winner	24	5 (24%)	6 (29%)	0 (0%)	11 (52%)	1	4	0	3
Experimental Weight Set 3 Winner	24	7 (35%)	5 (25%)	1 (5%)	13 (65%)	2	2	1	2
AI Longshot	2	0 (0%)	0 (0%)	0 (0%)	0 (0%)	—	—	—	—
Expert Consensus	24	8 (40%)	6 (30%)	1 (5%)	15 (75%)	2	4	2	2
ML Favorite (chalk)	24	8 (33%)	7 (29%)	0 (0%)	15 (62%)	—	—	—	—

CDX

AI Picks posts graded here: Wed 9/16 · Thu 9/17 · Fri 9/18 · Sat 9/19 · Sun 9/20

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	48	6 (18%)	11 (32%)	3 (9%)	20 (59%)	1	4	1	2
Algo 3 Winner	48	8 (19%)	14 (33%)	3 (7%)	25 (60%)	0	4	0	3
Algo 1 Winner	48	5 (12%)	9 (21%)	4 (10%)	18 (43%)	0	4	0	1
Experimental Weight Set 2 Winner	48	4 (10%)	11 (28%)	4 (10%)	19 (49%)	0	6	0	1
Experimental Weight Set 3 Winner	48	5 (13%)	10 (26%)	3 (8%)	18 (46%)	0	3	0	0
AI Longshot	51	2 (5%)	2 (5%)	5 (12%)	9 (21%)	—	—	—	—
Expert Consensus	48	9 (22%)	13 (32%)	4 (10%)	26 (63%)	3	3	1	3

CTD

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	12	8 (67%)	1 (8%)	0 (0%)	9 (75%)	1	0	0	1
Algo 3 Winner	12	5 (45%)	1 (9%)	2 (18%)	8 (73%)	0	1	0	2
Algo 1 Winner	12	6 (50%)	1 (8%)	0 (0%)	7 (58%)	0	0	0	0
Experimental Weight Set 2 Winner	12	5 (45%)	1 (9%)	1 (9%)	7 (64%)	1	0	0	1
Experimental Weight Set 3 Winner	12	7 (58%)	2 (17%)	0 (0%)	9 (75%)	0	0	0	0
AI Longshot	3	0 (0%)	0 (0%)	0 (0%)	0 (0%)	—	—	—	—
ML Favorite (chalk)	12	7 (58%)	1 (8%)	1 (8%)	9 (75%)	—	—	—	—

CTX

AI Picks posts graded here: Thu 9/17 · Fri 9/18 · Sat 9/19

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	24	6 (26%)	5 (22%)	7 (30%)	18 (78%)	0	1	0	3
Algo 3 Winner	24	8 (35%)	4 (17%)	7 (30%)	19 (83%)	0	1	0	2
Algo 1 Winner	24	6 (27%)	5 (23%)	6 (27%)	17 (77%)	0	1	0	5
Experimental Weight Set 2 Winner	24	8 (36%)	5 (23%)	6 (27%)	19 (86%)	1	2	0	3
Experimental Weight Set 3 Winner	24	6 (27%)	5 (23%)	7 (32%)	18 (82%)	0	1	0	3
AI Longshot	14	0 (0%)	0 (0%)	0 (0%)	0 (0%)	—	—	—	—
Expert Consensus	24	9 (41%)	5 (23%)	4 (18%)	18 (82%)	1	0	0	3

DEL

AI Picks posts graded here: Wed 9/16 · Thu 9/17 · Fri 9/18 · Sat 9/19

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	32	12 (44%)	4 (15%)	5 (19%)	21 (78%)	3	2	1	3
Algo 3 Winner	32	12 (41%)	3 (10%)	4 (14%)	19 (66%)	4	1	2	2
Algo 1 Winner	32	11 (42%)	5 (19%)	3 (12%)	19 (73%)	3	3	1	2
Experimental Weight Set 2 Winner	32	9 (33%)	3 (11%)	7 (26%)	19 (70%)	2	1	0	4
Experimental Weight Set 3 Winner	32	11 (42%)	6 (23%)	1 (4%)	18 (69%)	2	2	1	2
AI Longshot	7	1 (25%)	0 (0%)	0 (0%)	1 (25%)	—	—	—	—
ML Favorite (chalk)	32	10 (31%)	7 (22%)	7 (22%)	24 (75%)	—	—	—	—

EQY

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

FEX

AI Picks posts graded here: Mon 9/14 · Tue 9/15

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	14	5 (38%)	2 (15%)	3 (23%)	10 (77%)	0	1	0	4
Algo 3 Winner	14	5 (36%)	1 (7%)	5 (36%)	11 (79%)	2	1	2	3
Algo 1 Winner	14	3 (21%)	2 (14%)	5 (36%)	10 (71%)	1	1	0	3
Experimental Weight Set 2 Winner	14	6 (46%)	2 (15%)	3 (23%)	11 (85%)	1	1	0	2
Experimental Weight Set 3 Winner	14	5 (38%)	1 (8%)	4 (31%)	10 (77%)	1	0	0	5
Expert Consensus	14	4 (33%)	1 (8%)	4 (33%)	9 (75%)	1	1	1	2

FLX

AI Picks posts graded here: Mon 9/14 · Tue 9/15 · Wed 9/16

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	25	9 (39%)	5 (22%)	7 (30%)	21 (91%)	2	3	0	6
Algo 3 Winner	25	6 (26%)	6 (26%)	7 (30%)	19 (83%)	1	2	0	5
Algo 1 Winner	25	9 (38%)	4 (17%)	6 (25%)	19 (79%)	3	1	0	6
Experimental Weight Set 2 Winner	25	7 (30%)	4 (17%)	9 (39%)	20 (87%)	2	1	1	5
Experimental Weight Set 3 Winner	25	7 (29%)	6 (25%)	7 (29%)	20 (83%)	1	3	0	8
AI Longshot	3	0 (0%)	0 (0%)	0 (0%)	0 (0%)	—	—	—	—
Expert Consensus	25	5 (21%)	8 (33%)	7 (29%)	20 (83%)	2	4	1	4

FPK

AI Picks posts graded here: Tue 9/15 · Sat 9/19

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	18	0 (—)	0 (—)	0 (—)	0 (—)	0	0	0	0
Algo 3 Winner	18	0 (—)	0 (—)	0 (—)	0 (—)	0	0	0	0
Algo 1 Winner	18	0 (—)	0 (—)	0 (—)	0 (—)	0	0	0	0
Experimental Weight Set 2 Winner	18	0 (—)	0 (—)	0 (—)	0 (—)	0	0	0	0
Experimental Weight Set 3 Winner	18	0 (—)	0 (—)	0 (—)	0 (—)	0	0	0	0
AI Longshot	12	0 (—)	0 (—)	0 (—)	0 (—)	—	—	—	—
Expert Consensus	18	0 (—)	0 (—)	0 (—)	0 (—)	0	0	0	0

GPX

AI Picks posts graded here: Fri 9/18 · Sat 9/19 · Sun 9/20

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	28	10 (38%)	4 (15%)	4 (15%)	18 (69%)	5	0	0	1
Algo 3 Winner	28	7 (26%)	9 (33%)	4 (15%)	20 (74%)	1	2	0	2
Algo 1 Winner	28	9 (38%)	3 (12%)	3 (12%)	15 (62%)	3	1	1	1
Experimental Weight Set 2 Winner	28	7 (27%)	4 (15%)	3 (12%)	14 (54%)	4	0	1	1
Experimental Weight Set 3 Winner	28	8 (31%)	4 (15%)	3 (12%)	15 (58%)	1	1	0	1
AI Longshot	2	0 (0%)	0 (0%)	1 (50%)	1 (50%)	—	—	—	—
Expert Consensus	38	9 (33%)	9 (33%)	4 (15%)	22 (81%)	3	2	2	2

GRP

AI Picks posts graded here: Mon 9/14 · Sun 9/20

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	12	2 (17%)	4 (33%)	0 (0%)	6 (50%)	1	2	0	0
Algo 3 Winner	12	3 (25%)	5 (42%)	1 (8%)	9 (75%)	1	2	1	2
Algo 1 Winner	12	3 (27%)	2 (18%)	1 (9%)	6 (55%)	1	1	0	0
Experimental Weight Set 2 Winner	12	2 (18%)	2 (18%)	0 (0%)	4 (36%)	2	0	1	0
Experimental Weight Set 3 Winner	12	2 (18%)	2 (18%)	1 (9%)	5 (45%)	2	0	0	0
AI Longshot	1	0 (—)	0 (—)	0 (—)	0 (—)	—	—	—	—
ML Favorite (chalk)	12	2 (17%)	4 (33%)	0 (0%)	6 (50%)	—	—	—	—

IND

AI Picks posts graded here: Mon 9/14 · Tue 9/15 · Wed 9/16 · Thu 9/17

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	32	9 (31%)	4 (14%)	2 (7%)	15 (52%)	4	1	1	2
Algo 3 Winner	32	4 (15%)	2 (8%)	8 (31%)	14 (54%)	1	1	0	1
Algo 1 Winner	32	9 (31%)	3 (10%)	5 (17%)	17 (59%)	2	2	0	3
Experimental Weight Set 2 Winner	32	9 (29%)	5 (16%)	5 (16%)	19 (61%)	2	2	1	2
Experimental Weight Set 3 Winner	32	13 (43%)	3 (10%)	5 (17%)	21 (70%)	3	1	1	1
AI Longshot	13	0 (0%)	1 (10%)	1 (10%)	2 (20%)	—	—	—	—
Expert Consensus	38	11 (30%)	7 (19%)	7 (19%)	25 (68%)	3	0	2	1
ML Favorite (chalk)	32	11 (34%)	4 (12%)	3 (9%)	18 (56%)	—	—	—	—

LAD

AI Picks posts graded here: Mon 9/14 · Tue 9/15 · Wed 9/16 · Sat 9/19

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	29	8 (29%)	4 (14%)	7 (25%)	19 (68%)	4	3	2	4
Algo 3 Winner	29	4 (15%)	10 (37%)	7 (26%)	21 (78%)	0	6	0	6
Algo 1 Winner	29	7 (26%)	6 (22%)	5 (19%)	18 (67%)	3	5	1	3
Experimental Weight Set 2 Winner	29	9 (35%)	6 (23%)	4 (15%)	19 (73%)	4	3	0	6
Experimental Weight Set 3 Winner	29	8 (30%)	5 (19%)	5 (19%)	18 (67%)	4	4	1	3
AI Longshot	25	1 (4%)	1 (4%)	1 (4%)	3 (12%)	—	—	—	—
Expert Consensus	29	8 (29%)	4 (14%)	8 (29%)	20 (71%)	3	2	1	6
ML Favorite (chalk)	29	9 (31%)	5 (17%)	5 (17%)	19 (66%)	—	—	—	—

LAX

AI Picks posts graded here: Sat 9/19 · Sun 9/20

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	6	2 (33%)	3 (50%)	0 (0%)	5 (83%)	0	2	0	0
Algo 3 Winner	6	1 (20%)	1 (20%)	0 (0%)	2 (40%)	1	0	1	0
Algo 1 Winner	6	2 (33%)	3 (50%)	0 (0%)	5 (83%)	0	1	0	0
Experimental Weight Set 2 Winner	6	2 (33%)	1 (17%)	0 (0%)	3 (50%)	0	0	0	0
Experimental Weight Set 3 Winner	6	2 (33%)	2 (33%)	0 (0%)	4 (67%)	0	1	0	0

LBG

AI Picks posts graded here: Sat 9/19 · Sun 9/20

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	7	1 (14%)	1 (14%)	1 (14%)	3 (43%)	1	1	0	0
Algo 3 Winner	7	3 (43%)	1 (14%)	0 (0%)	4 (57%)	0	0	0	1
Algo 1 Winner	7	0 (0%)	3 (50%)	2 (33%)	5 (83%)	0	1	0	0
Experimental Weight Set 2 Winner	7	3 (50%)	0 (0%)	1 (17%)	4 (67%)	2	0	0	0
Experimental Weight Set 3 Winner	7	2 (33%)	1 (17%)	1 (17%)	4 (67%)	1	1	0	0
ML Favorite (chalk)	7	3 (43%)	1 (14%)	1 (14%)	5 (71%)	—	—	—	—

LRC

AI Picks posts graded here: Fri 9/18 · Sat 9/19 · Sun 9/20

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	26	9 (38%)	2 (8%)	5 (21%)	16 (67%)	3	0	1	3
Algo 3 Winner	26	6 (25%)	4 (17%)	9 (38%)	19 (79%)	2	3	0	2
Algo 1 Winner	26	6 (25%)	3 (12%)	5 (21%)	14 (58%)	4	2	0	1
Experimental Weight Set 2 Winner	26	11 (48%)	3 (13%)	3 (13%)	17 (74%)	5	0	0	2
Experimental Weight Set 3 Winner	26	11 (46%)	2 (8%)	3 (12%)	16 (67%)	3	1	1	2
AI Longshot	8	0 (0%)	0 (0%)	0 (0%)	0 (0%)	—	—	—	—
ML Favorite (chalk)	26	10 (38%)	3 (12%)	5 (19%)	18 (69%)	—	—	—	—

LRL

AI Picks posts graded here: Fri 9/18 · Sat 9/19 · Sun 9/20

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	30	9 (32%)	7 (25%)	3 (11%)	19 (68%)	1	4	0	3
Algo 3 Winner	30	9 (33%)	5 (19%)	5 (19%)	19 (70%)	3	2	2	2
Algo 1 Winner	30	7 (24%)	7 (24%)	4 (14%)	18 (62%)	1	4	1	3
Experimental Weight Set 2 Winner	30	8 (28%)	7 (24%)	3 (10%)	18 (62%)	1	3	1	3
Experimental Weight Set 3 Winner	30	8 (28%)	7 (24%)	4 (14%)	19 (66%)	3	5	0	3
AI Longshot	31	0 (0%)	1 (5%)	3 (14%)	4 (18%)	—	—	—	—
Expert Consensus	35	8 (28%)	6 (21%)	6 (21%)	20 (69%)	2	3	0	1
ML Favorite (chalk)	30	12 (40%)	5 (17%)	4 (13%)	21 (70%)	—	—	—	—

LSX

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Expert Consensus	30	10 (33%)	12 (40%)	3 (10%)	25 (83%)	0	2	0	2

MED

AI Picks posts graded here: Fri 9/18 · Sat 9/19

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	12	5 (56%)	2 (22%)	0 (0%)	7 (78%)	3	0	0	2
Algo 3 Winner	12	3 (38%)	4 (50%)	0 (0%)	7 (88%)	1	1	0	1
Algo 1 Winner	12	6 (60%)	2 (20%)	0 (0%)	8 (80%)	2	0	0	0
Experimental Weight Set 2 Winner	12	5 (62%)	1 (12%)	1 (12%)	7 (88%)	1	0	0	0
Experimental Weight Set 3 Winner	12	5 (56%)	2 (22%)	0 (0%)	7 (78%)	2	0	0	0
ML Favorite (chalk)	12	4 (33%)	4 (33%)	3 (25%)	11 (92%)	—	—	—	—

MNR

AI Picks posts graded here: Mon 9/14 · Tue 9/15 · Wed 9/16 · Sun 9/20

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	32	5 (20%)	4 (16%)	8 (32%)	17 (68%)	2	1	1	1
Algo 3 Winner	32	2 (8%)	4 (17%)	6 (25%)	12 (50%)	1	1	0	2
Algo 1 Winner	32	6 (25%)	8 (33%)	5 (21%)	19 (79%)	0	3	0	1
Experimental Weight Set 2 Winner	32	4 (16%)	6 (24%)	9 (36%)	19 (76%)	0	1	0	2
Experimental Weight Set 3 Winner	32	9 (35%)	6 (23%)	5 (19%)	20 (77%)	3	2	1	3
AI Longshot	10	1 (17%)	1 (17%)	3 (50%)	5 (83%)	—	—	—	—
Expert Consensus	32	14 (52%)	4 (15%)	5 (19%)	23 (85%)	3	1	2	3
ML Favorite (chalk)	32	11 (34%)	6 (19%)	7 (22%)	24 (75%)	—	—	—	—

PID

AI Picks posts graded here: Mon 9/14 · Fri 9/18

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	18	5 (31%)	2 (12%)	2 (12%)	9 (56%)	0	0	0	0
Algo 3 Winner	18	5 (28%)	2 (11%)	3 (17%)	10 (56%)	1	0	0	1
Algo 1 Winner	18	4 (25%)	2 (12%)	2 (12%)	8 (50%)	1	1	0	0
Experimental Weight Set 2 Winner	18	7 (41%)	5 (29%)	0 (0%)	12 (71%)	0	2	0	2
Experimental Weight Set 3 Winner	18	8 (50%)	3 (19%)	1 (6%)	12 (75%)	1	1	0	0
ML Favorite (chalk)	18	5 (28%)	3 (17%)	2 (11%)	10 (56%)	—	—	—	—

PRM

AI Picks posts graded here: Fri 9/18 · Sat 9/19 · Sun 9/20

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	20	10 (59%)	4 (24%)	2 (12%)	16 (94%)	1	2	0	3
Algo 3 Winner	20	10 (59%)	3 (18%)	2 (12%)	15 (88%)	2	1	1	0
Algo 1 Winner	20	10 (56%)	4 (22%)	2 (11%)	16 (89%)	1	1	0	2
Experimental Weight Set 2 Winner	20	7 (44%)	4 (25%)	2 (12%)	13 (81%)	2	1	0	3
Experimental Weight Set 3 Winner	20	7 (47%)	4 (27%)	1 (7%)	12 (80%)	2	1	0	3
AI Longshot	4	0 (0%)	0 (0%)	1 (33%)	1 (33%)	—	—	—	—
Expert Consensus	32	12 (43%)	4 (14%)	4 (14%)	20 (71%)	2	1	1	1
ML Favorite (chalk)	20	9 (45%)	5 (25%)	2 (10%)	16 (80%)	—	—	—	—

PRX

AI Picks posts graded here: Mon 9/14 · Tue 9/15 · Fri 9/18 · Sat 9/19

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	45	6 (15%)	18 (44%)	6 (15%)	30 (73%)	1	10	0	2
Algo 3 Winner	45	8 (20%)	14 (34%)	5 (12%)	27 (66%)	2	3	0	3
Algo 1 Winner	45	8 (19%)	11 (26%)	5 (12%)	24 (57%)	2	4	1	3
Experimental Weight Set 2 Winner	45	7 (17%)	14 (33%)	4 (10%)	25 (60%)	1	6	1	3
Experimental Weight Set 3 Winner	45	9 (22%)	9 (22%)	6 (15%)	24 (60%)	5	3	3	1
AI Longshot	15	1 (9%)	1 (9%)	0 (0%)	2 (18%)	—	—	—	—
Expert Consensus	45	9 (21%)	12 (29%)	9 (21%)	30 (71%)	5	5	1	2
ML Favorite (chalk)	45	9 (20%)	18 (40%)	5 (11%)	32 (71%)	—	—	—	—

RPX

AI Picks posts graded here: Thu 9/17 · Fri 9/18 · Sat 9/19

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	31	9 (31%)	5 (17%)	5 (17%)	19 (66%)	1	3	0	1
Algo 3 Winner	31	11 (37%)	4 (13%)	7 (23%)	22 (73%)	2	1	0	1
Algo 1 Winner	31	6 (20%)	4 (13%)	4 (13%)	14 (47%)	1	0	0	1
Experimental Weight Set 2 Winner	31	9 (30%)	2 (7%)	6 (20%)	17 (57%)	2	1	1	3
Experimental Weight Set 3 Winner	31	10 (32%)	5 (16%)	5 (16%)	20 (65%)	1	2	0	2
AI Longshot	3	0 (0%)	2 (67%)	0 (0%)	2 (67%)	—	—	—	—

SWA

AI Picks posts graded here: Wed 9/16 · Thu 9/17

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
AI Longshot	2	0 (—)	0 (—)	0 (—)	0 (—)	—	—	—	—

SWF

AI Picks posts graded here: Sat 9/19 · Sun 9/20

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	13	2 (15%)	0 (0%)	1 (8%)	3 (23%)	0	0	0	1
Algo 3 Winner	13	4 (31%)	1 (8%)	1 (8%)	6 (46%)	0	0	0	0
Algo 1 Winner	13	4 (31%)	1 (8%)	1 (8%)	6 (46%)	0	0	0	0
Experimental Weight Set 2 Winner	13	5 (38%)	1 (8%)	2 (15%)	8 (62%)	0	0	0	0
Experimental Weight Set 3 Winner	13	7 (54%)	0 (0%)	1 (8%)	8 (62%)	0	0	0	1
AI Longshot	2	0 (0%)	0 (0%)	0 (0%)	0 (0%)	—	—	—	—
ML Favorite (chalk)	13	4 (31%)	1 (8%)	1 (8%)	6 (46%)	—	—	—	—

TDN

AI Picks posts graded here: Mon 9/14 · Tue 9/15 · Wed 9/16 · Thu 9/17

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	32	13 (42%)	9 (29%)	1 (3%)	23 (74%)	5	7	1	3
Algo 3 Winner	32	13 (43%)	7 (23%)	2 (7%)	22 (73%)	10	4	2	3
Algo 1 Winner	32	16 (55%)	5 (17%)	1 (3%)	22 (76%)	7	3	0	3
Experimental Weight Set 2 Winner	32	14 (48%)	6 (21%)	3 (10%)	23 (79%)	6	4	1	4
Experimental Weight Set 3 Winner	32	16 (53%)	7 (23%)	1 (3%)	24 (80%)	6	3	1	1
AI Longshot	5	0 (0%)	0 (0%)	1 (20%)	1 (20%)	—	—	—	—
Expert Consensus	32	12 (39%)	12 (39%)	2 (6%)	26 (84%)	5	9	1	3
ML Favorite (chalk)	32	13 (41%)	7 (22%)	1 (3%)	21 (66%)	—	—	—	—

WOX

AI Picks posts graded here: Thu 9/17 · Fri 9/18 · Sat 9/19 · Sun 9/20

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Algo 2 Winner	35	10 (29%)	7 (20%)	9 (26%)	26 (74%)	3	1	2	5
Algo 3 Winner	35	12 (35%)	8 (24%)	10 (29%)	30 (88%)	2	1	1	3
Algo 1 Winner	35	12 (35%)	8 (24%)	8 (24%)	28 (82%)	1	2	0	5
Experimental Weight Set 2 Winner	35	8 (24%)	11 (33%)	8 (24%)	27 (82%)	0	4	0	4
Experimental Weight Set 3 Winner	35	9 (26%)	10 (29%)	7 (21%)	26 (76%)	0	2	0	5
AI Longshot	4	1 (25%)	0 (0%)	0 (0%)	1 (25%)	—	—	—	—
Expert Consensus	35	11 (34%)	7 (22%)	8 (25%)	26 (81%)	5	2	1	5

WRD

Source	Races	W	P	S	ITM	EX	BEX	TRI	BTRI
Expert Consensus	19	4 (21%)	7 (37%)	1 (5%)	12 (63%)	0	1	0	0