Choose a race or paste its card URL. GAMELIN runs the available field through its formulas, shows the projected winner, tests the price, and returns BET or PASS. Every read is free; research spans 5.7M+ starter-level records spanning 1990–2026.
The horse most likely to win is not always a good bet. GAMELIN shows you two separate things: who is most likely to win, and whether the price is worth betting. If the favorite pays too little, the honest answer can be PASS.
New to horse betting? Here is the one idea that matters. Picking the horse most likely to win is not the same as making a good bet. GAMELIN runs the race and shows you both. First, the projected winner. Second, the price. If that horse is a heavy favorite, the payout may be too small for the risk. So the answer might be pass. Or use him only as one piece of an exacta, paired with a longer shot. If the price is attractive, GAMELIN says bet, and shows you why. Either way, you see the reasoning, not just a name. Pick a race, or paste its link, and read it free. No signup. No wagers taken here. GAMELIN is information only. Please play within your limits.
Narration is synthetic voice (ElevenLabs). Information only; no wagers are taken on GAMELIN.
The 60-second beginner guide → What win, place and show mean → What an exacta is →
1 · Bring a real cardChoose an upcoming race above or paste its exact TVG/FanDuel URL. GAMELIN checks the race and available runners.
2 · Read the evidenceSee the field ranking, market and model probabilities, price edge, and the data-coverage label. More data can change the kind of read.
3 · Decide with the gateThe projected winner is the most likely runner under this read. A BET needs a qualifying price and evidence; PASS is a complete outcome.
Next scheduled stakes as of 2026-10-27. A scheduled race is not a posted field, model pick or result. Run GAMELIN’s formulas on the exact supported card and compare its price gate.
1990–2026 partial · multiple datasets across the US, UK/Ireland, Europe, Hong Kong, and Singapore.
Starter-level records analyzed across multiple research datasets. This is not a count of unique horses and these rows are not loaded into every live race read.
A full-year US validation set, not the entire GAMELIN research corpus.
Historical portfolio backtests. The +10.6% result belongs to the top-50% conviction subset across repeated races; it is not a single-race promise or a guarantee of future returns.