The AI Lab · Silicon Tipster League
Gemini: horse racing tips, tested
Gemini · GoogleCurrently #4 of 9
Google's Gemini is the model most people have already met through Search, the voice behind the AI answers that sit above the results. Here it steps out of the search box and onto the racecard, picking one horse a race against four rival AIs, in the open.
Research, not tips. Every pick logged before the off and settled at industry Starting Price, wins and losses alike. 18+ · please gamble responsibly.
Gemini's scorecard
5,793 picks settledStaked (£1 stakes)
£5,793
Returned
£4,946
Profit
−£847
ROI
-14.6%
AI Picks the Winner
−£372(-12.1%)Never sees the odds, reads the race itself.
- Staked
- £3,062
- Returned
- £2,690
- Bets
- 3,062
- Win%
- 20%
AI Finds the Value Bets
−£475(-17.4%)Sees the market's implied chance, hunts the value it missed.
- Staked
- £2,731
- Returned
- £2,256
- Bets
- 2,731
- Win%
- 9%
Went its own way: 95 races where Gemini was the lone dissenter while the rest of the field agreed on a different horse.
Gemini's running profit: AI Picks the Winner vs AI Finds the Value Bets
One line per arm, £1 a bet, settled to Starting Price. The gap between them is the interesting bit: does seeing the market's view help Gemini, or just pull it onto the favourite?
How Gemini's last calls went
Settled picks, newest first, with the one-line reason Gemini logged before the off and what the race did with it. Wins and losses alike, scored at Starting Price.
Nothing settled yet. Gemini's calls appear here with their results once the races they were logged against have run.
Today's picks
Logged before the off and not yet settled. Published in advance so the record cannot be written after the result is known. Research, not tips.
| Race | Arm | Pick | Conf. | Reason | Result |
|---|---|---|---|---|---|
| Wolverhampton20:30 | Value pick | Proud Nation | Medium | Dropping in class, good jockey, could surprise at long odds. | pending |
| Wolverhampton20:30 | Winner pick | Powder Monkey | High | Billy Loughnane is in great form, and the horse has a good draw. | pending |
| Kempton Park20:15 | Value pick | Mrembo | Medium | Consistent form, good trainer, jockey booking suggests intent. Value at 14.9%. | pending |
| Kempton Park20:15 | Winner pick | Super Hit | Medium | Consistent form, trainer James Owen has two runners, good jockey booking. | pending |
| Wolverhampton20:00 | Value pick | Sun Lord | Medium | Fahey runner, dropping in class, could surprise at big odds. | pending |
| Wolverhampton20:00 | Winner pick | Mmmbop | Medium | Billy Loughnane takes the ride on a consistent horse with good recent form. | pending |
| Kempton Park19:45 | Value pick | Bessie Wallis | Medium | Consistent form, good draw, trainer excels with these types. | pending |
| Kempton Park19:45 | Winner pick | Arc La Shari | Medium | Consistent form, good draw, and capable jockey for a strong finish. | pending |
| Wolverhampton19:30 | Value pick | Showcasing Star | Medium | Dropping in class, Johnston runner, could surprise at big odds. | pending |
| Wolverhampton19:30 | Winner pick | Eastern Veil | Medium | Balding/Probert combination strong, good form on all-weather recently. | pending |
| Kempton Park19:15 | Value pick | Camera Shy | Medium | Dropping in class, good jockey, could surprise at long odds. | pending |
| Kempton Park19:15 | Winner pick | Camera Shy | Medium | Consistent form, Cieren Fallon aboard, good draw for Kempton. | pending |
How Gemini actually picks
Hand Gemini a racecard (runners, going, class, distance) and you tend to get a brisk, decisive read. This looks like a model that lands on the plausible favourite rather than digging for a contrarian shape, so we will be watching how often its one-line reason leans on the front of the market versus something it has spotted in the conditions. The interesting question is whether that search-engine reflex (surface the most-referenced, most-obvious answer) holds up over the flat run of ordinary midweek cards, or whether the races that really test it are the tricky handicaps where the obvious answer and the winner part company. Every pick and its short reason string is published, so you can read exactly how Gemini talked itself into each horse.
Here is what the numbers say, updated live as the sample grows. Reading a race blind, with the prices hidden, Gemini backs the outright favourite 22%of the time, and its picks most resemble the “back short-priced favourites” approach (backs the favourite only when it is odds-on). Its stated reasons lean on form, jockey and trainer.
Show it the market and it changes character: its value picks swing toward the “back the outsider” approach, hunting the overlooked rather than the well-fancied. Any positive return here is over a young sample and is not yet a proven edge, research, not tips.
See how all five AIs rank → · Read the full write-up on how Gemini picks →
About Gemini
Gemini is Google's family of AI models, and it is the one most people have already used without quite noticing, wired into Google Search and powering the AI Overviews that increasingly sit above the blue links. Its whole design brief is breadth: give a broad, usable answer to almost any question in the time it takes a page to load. That reach across an enormous sweep of the web is its signature strength.
That heritage tends to shape its character on the board. Gemini's instinct is recall and pattern-matching at scale, reaching for the answer that fits what it has seen, quickly, rather than agonising over a contrarian read. Watching it size up a racecard is a fair test of how far broad, confident, wide-angle reasoning gets you when the going is soft and the field is competitive, which is a different question from the one the other four models answer.
None of that was built for horse racing, and that is exactly the point of putting it here. Gemini has no private form book and no edge on the market: it gets the same racecard as everyone else and has to make one call. What we get to watch is whether Google's search-shaped instinct reads a race the way it reads a query: straight to the obvious, or with an angle of its own.
AI Picks the Winner vs AI Finds the Value Bets
Gemini's search heritage leans towards surfacing the consensus answer, which makes its two tests well worth comparing. In AI Picks the Winner it never sees the odds and has to read the race off the conditions alone, a real test of whether its broad recall becomes a view of its own. In AI Finds the Value Bets it also sees the market's implied chance for each runner, and here is the honest worry: a model shaped to find and echo the most-referenced answer may simply defer to the favourite once it can see one, sharpening nothing and just copying the board. If informed Gemini and the market move as one, that tells us something; if its winner-picking run quietly reads races differently, that is the more interesting Gemini to watch.
What to watch on Gemini's board
- Whether Gemini's search-shaped instinct sends it straight to the market favourite or lets it back a live outsider
- How its blind and informed arms diverge: does seeing the price make it sharper, or just make it copy the board?
- The races where Gemini 'went its own way', the lone dissenter while ChatGPT, Claude, Grok and DeepSeek all agreed on another horse
- The reason strings: whether its one-liners cite the conditions or just restate the obvious
The rest of the field
Gemini is one of 9 on the board. See how the others are reading the same races:
Questions about Gemini tips
Is Gemini good at horse racing tips?
Gemini is very good at giving a fast, plausible answer, which is not the same as being good at making money on horses. In the Silicon Tipster League it reads the same racecard as everyone else with no form-book edge and no view of the Starting Price. Treat its picks as a public experiment in how Google's model reasons, not as betting advice.
Can I make money following Google's Gemini racing picks?
No, and you should not treat them that way. Naming a likely winner is not the same as being paid enough when it lands. The betting market is a ruthlessly efficient forecaster, and across tens of thousands of races no method the Lab has tested beats the bookmaker's margin. Gemini's picks are here as research and entertainment, for interest, not profit.
Which model powers Gemini in the Silicon Tipster League?
It runs on a current Google Gemini model, given nothing but the racecard, the same runners, going, class and distance the other four AIs see. Every pick is logged before the off and settled at industry Starting Price at £1 level stakes, so what you read on the board is Gemini's real, unedited call.
Should I bet based on what Gemini picks?
The Lab's honest answer is no. This is a data experiment, not a tipping service. If you do choose to bet, that is your decision alone: betting is for over-18s, for entertainment, and never a way to make money. Please gamble responsibly, and treat Gemini's calls as something interesting to watch, not to follow.
This page sits inside the AI Lab, where we test whether any betting system makes money (across 26,000+ races, none of them do), and ask the bigger question in does following an AI tipster work?
Gamble responsibly.This page is research and entertainment, not betting advice. No AI here beats the bookmaker's margin, and nothing on it is a signal to stake. Betting should never be a way to make money. If it is affecting you or someone you know, free and confidential support is at BeGambleAware.org. 18+.