Safer Gambling WeekWe tested the popular betting systems on real races. See what they madeSet a deposit limit before your next bet. Here is howNo licence means no protection. Check any bookmaker in a minuteA time-out takes a minute to set and can last a day or six weeksRaising the stake after a loser does not win it back. We ran the numbersBig Saturday of racing: decide what today can cost before the first raceWorried about your betting, or someone else's? Free help is a call away

StableBet
Professor Furlong and Pascal at the AI Lab
THE AI LAB
THE AI LAB DAILY · THE CARD FOR WEDNESDAY, 18 NOVEMBER 2026

Wednesday 18 November 2026 racing: the card at Hexham, Dundalk and two more

← Every day·The market on Friday, 20 November 2026·The day so far on Saturday, 21 November 2026·Yesterday's results

This is the card for Wednesday, 18 November 2026, kept as an archive. The latest cards are here.

The card for Wednesday 18 November 2026 runs to four meetings and 31 races: Dundalk in Ireland, and Hexham, Ffos Las and Kempton Park in Britain. The first race is at Hexham at 12:33 and the last is at Kempton Park at 20:30. Kempton Park hosts the longest card of the day, with racing in Britain and Ireland, both Flat and jumps, spread across the afternoon and evening. The feature is the QuinnBet Open NH Flat Race at Hexham, due off at 15:38, and it has the next section to itself. Every runner, with the model's estimated chance beside the market's price, is on the racecards page, and the model's view of the whole day is on the day's predictions; the card was written before the first race, so nothing on it is a result.

The feature: the QuinnBet Open NH Flat Race at Hexham

Stablebet model (pre-race estimated win chances)

Hexham 15:38 · QuinnBet Open NH Flat Race · Class 4 · 2m48y

Latest output →

Pre-race estimate. Published 18 November 2026, before the off. This is what the model made of the race beforehand, kept as a record. It was never published as a tip.

The model rated Browney Bank its most likely winner at 32%, ahead of Rio Blue (20%) and Jimmy The Jet (16%). It read as a clear first choice, but beatable.

HorseSPModel chanceMarketvs Market
Browney Bank
Danny McMenamin / Mrs A Hamilton
11.00
31.8%
7.9%Market 23.9pp longer
Rio Blue
Tristan Durrell / D Skelton
3.00
20.0%
28.9%Market 8.9pp shorter
Jimmy The Jet
Sean Quinlan / Lizzie Quinlan
17.00
15.8%
5.1%Market 10.7pp longer
Yorgunnarock
D R Fox / W Coltherd
17.00
11.5%
5.1%Market 6.3pp longer
Mortgage Man
Craig Nichol / Ewan Whillans
21.00
10.9%
4.1%Market 6.8pp longer
Max Potential
Rian Corcoran / D Pipe
1.91
5.1%
45.5%Market 40.4pp shorter
Angela's Rose
Nathan Moscrop / S Corbett
26.00
4.9%
3.3%Market 1.6pp longer

These were the model's estimated win chances going into the race, not tips. The model is calibrated to real results (when it says 25%, about 25% win) but it does not beat the market, so read it as an independent second opinion on the race. See how accurate it is →

Model: ensemble-v1.1 · Generated Wed, 18 Nov 2026The LabMethodology

The model and the market prefer different horses in the feature, with Browney Bank the model's most likely winner and Max Potential the market's shortest price. The card above sets the model's estimated chance for each runner beside the chance implied by the market, and the gap between the two columns is the only thing the Lab claims to measure; it says which horse the model rates highest and nothing about what to do with that. The race is run over 2m48y, on ground declared as Good (Good to Soft in places), with seven priced runners. The course itself is covered in the Hexham guide.

Where the model disagrees with the market

The widest gap between the model's estimate and the market's price on this card is in the Dandara Maiden Hurdle (GBB Race) (Div 1) at Ffos Las (12:48), where the model gives No Walkover a smaller chance than the price implies. The race was chosen by the size of that gap and by nothing else.

Stablebet model (pre-race estimated win chances)

Ffos Las 12:48 · Dandara Maiden Hurdle (GBB Race) (Div 1) · Class 4 · 1m7f182y

Latest output →

Pre-race estimate. Published 18 November 2026, before the off. This is what the model made of the race beforehand, kept as a record. It was never published as a tip.

The model rated Bob Bishop its most likely winner at 37%, ahead of Blinded By Grace (20%) and Nuptown Girl (11%). It read as a clear first choice, but beatable.

HorseSPModel chanceMarketvs Market
Bob Bishop
Freddie Gingell / J Tizzard
3.75
36.7%
22.2%Market 14.5pp longer
Blinded By Grace
S Bowen / M Bowen
5.00
20.4%
16.7%Market 3.8pp longer
Nuptown Girl
Lee Edwards / B J Llewellyn
67.00
10.8%
1.2%Market 9.6pp longer
Jevon
C J Todd / D Skelton
5.50
9.5%
15.1%Market 5.7pp shorter
No Walkover
Jack Tudor / D Pipe
2.38
8.8%
35.0%Market 26.2pp shorter
Fozzy Osbourne
Joe Anderson / G Harris
34.00
7.0%
2.5%Market 4.5pp longer
Mac Gayveur
Jack Stenhouse / Claire Hitch
26.00
3.2%
3.2%In line with market
Short Sell
Liam Harrison / D Skelton
34.00
2.2%
2.5%In line with market
Petit Galet
James Best / R Mitford-Slade
101.00
0.7%
0.8%In line with market
El Dorado
Conor Ring / Sheila Lewis
101.00
0.7%
0.8%In line with market

These were the model's estimated win chances going into the race, not tips. The model is calibrated to real results (when it says 25%, about 25% win) but it does not beat the market, so read it as an independent second opinion on the race. See how accurate it is →

Model: ensemble-v1.1 · Generated Wed, 18 Nov 2026The LabMethodology

A gap is a difference of opinion, and a difference of opinion is all it is: the wide ones tend to fall on runners the model has the least evidence about, as often as on a horse the market has overlooked. The left column is the model's estimated chance, the right is the chance the price implies, and the track record shows how often the model's side of the argument has been right once every pick is settled at starting price.

What the card costs

Every price on the card carries the bookmaker's margin: add up the chances the prices imply and the total comes to more than a whole field, and the excess is what the book keeps whichever horse wins. The table below is the latest published margin for each book the Lab tracks. It is compiled from the previous evening's prices, so it describes the card as it was sold then rather than the morning's board, and the order of the table is a measurement, never a recommendation.

BookmakerRacesOverroundTakeout
1 SmarketsSBK225915.04%13.08%
2 BetTom207123.52%19.04%
= Bet365281423.61%19.10%
4 Virgin Bet shared feed209223.90%19.29%
= LiveScore Bet shared feed186123.96%19.33%
6 William Hill291225.55%20.35%
7 Unibet285726.13%20.72%
8 7Bet224926.61%21.02%
= Betfred277826.63%21.03%
= Quinn Bet288926.67%21.06%
= Hollywood Bets291426.73%21.09%
= Paddy Power295626.96%21.23%
13 Star Sports298027.54%21.60%
= 10 Bet269627.58%21.61%
15 Midnite291628.29%22.05%
16 Coral shared feed296728.63%22.26%
= Ladbrokes shared feed296828.64%22.26%
= Boyle Sports296628.76%22.33%
19 Bet Victor shared feed213629.63%22.85%
= Betano shared feed213529.70%22.90%
= Betfair Sportsbook295629.83%22.98%
22 Dragon Bet299030.59%23.42%
= BetWright299030.61%23.43%
24 BresBet21732.04%24.27%
25 BetMGM299233.68%25.20%

First pre-race book of each day, 2026-08-27 to 2026-11-21, across 2994 races every listed book priced in full. Exchanges and spread firms are excluded: they do not quote comparable win odds. Overround is how far past a fair book the prices sit; takeout is the share of stakes the book keeps. On 85 days of data, books marked = are level with the one above rather than behind it. Books marked "shared feed" are one half of a pair that does not price independently, so there are fewer independent books here than rows.

The margin is the reason the Lab's tested strategies lose over time even when a pick is sound; what betting costs has the working, and the Tipster League shows what it does to the AI tipsters over a season.

Elsewhere in the Lab: What the AI Tipsters Got Right and Wrong: 9 November to 15 November 2026.

Common questions

Which meetings race on Wednesday 18 November 2026?

Dundalk in Ireland, and Hexham, Ffos Las and Kempton Park in Britain. Every card is on the racecards page with the model's estimated chance beside each runner, and the first race is at Hexham at 12:33.

When are the model's estimates published?

Each morning before the first race, from the declared runners, and they are not changed after the off. A card labels itself a pre-race estimate once its race has run.

What does the model's chance mean?

The model's own estimate of how likely each runner is to win, set beside the chance the market price implies. It is an opinion with a published record, not a tip, and the track record is where that record lives.

Why is a horse missing from a card?

Either it was withdrawn after the estimates were made, or the race was one the model did not price. The horse tracker follows any runner on the card to its next entry.

How are the AI tipsters doing?

The Tipster League settles every AI pick at starting price and publishes the running total, losses included.

A word on all of this

None of the above is a tip, and no system the Lab has tested has made money over the whole record. Bet only what you can afford to lose. If gambling has stopped being fun, BeGambleAware has free, confidential help.

Every figure on this page renders live from our published feeds and nothing here is a tip. For whether the model holds any edge, see our track record. 18+, please bet responsibly.

Previous cards

Tuesday, 17 November 2026
Tuesday 17 November 2026 racing: the card at Southwell, Limerick and Carlisle
Three meetings on 17 November 2026, the model's estimated chance beside every runner, and the margin the card is sold at.
Monday, 16 November 2026
Monday 16 November 2026 racing: the card at Wolverhampton and Plumpton
Two meetings on 16 November 2026, the model's estimated chance beside every runner, and the margin the card is sold at.
Sunday, 15 November 2026
Sunday 15 November 2026 racing: the card at Navan, Fontwell and Cheltenham
Three meetings on 15 November 2026, the model's estimated chance beside every runner, and the margin the card is sold at.
Saturday, 14 November 2026
Saturday 14 November 2026 racing: the card at Navan, Uttoxeter and three more
Five meetings on 14 November 2026, the model's estimated chance beside every runner, and the margin the card is sold at.
Friday, 13 November 2026
Friday 13 November 2026 racing: the card at Sedgefield, Dundalk and two more
Four meetings on 13 November 2026, the model's estimated chance beside every runner, and the margin the card is sold at.
Thursday, 12 November 2026
Thursday 12 November 2026 racing: the card at Hereford, Thurles and Market Rasen
Three meetings on 12 November 2026, the model's estimated chance beside every runner, and the margin the card is sold at.
Wednesday, 11 November 2026
Wednesday 11 November 2026 racing: the card at Bangor-on-Dee, Dundalk and two more
Four meetings on 11 November 2026, the model's estimated chance beside every runner, and the margin the card is sold at.