Supercomputer Predicts 2026 Grand National Winner

2X3JANG Winning trainer Willie Mullins poses with the Champion Trainer trophy after Minella Cocooner won the bet365 Gold Cup Handicap Chase on bet365 Jump Finale day at Sandown Park Racecourse, Esher. Picture date: Saturday April 27, 2024.

The time for the most valuable jumps race in all of Europe is here, with the 2026 Grand National set to be run on 11th April. Will 2024 winner I Am Maximus improve on last year’s second place finish and reclaim his crown? Or will Jagwar extend his fine form from Cheltenham and ride to Grand National glory?

We at GrandNational.org.uk fired up our supercomputer to answer that and determine which of this year’s Grand National runners have the best chance of winning it all at Aintree this year.

Tight battle projected for top spot

Our supercomputer’s simulations point to an extremely tight battle for first place between Grangeclare West and I Am Maximus. Grangeclare West is our supercomputer’s projected winner with an 11.42% chance of winning, compared to I Am Maximus’ 11.36%. Both horses, trained by Willie Mullins, are hard to separate at the top because their traits, trainer and market confidence signals are very similar to that of past Grand National champions, thus setting up a classic fight for the crown.

Jagwar, who impressed at Cheltenham earlier this year, is the supercomputer’s third favourite, followed by Panic Attack with winning probabilities of 10.03% and 9.42% respectively.

Captain Cody is a horse whose winning chance (according to our supercomputer simulations) doesn’t reflect in the bookmaker odds. The Irish horse has been given an 8.65% winning chance, making it our supercomputer’s fifth-favourite, while bookmaker odds place it as the eighth favourite at the time of writing.

The Algorithm Driving The Supercomputer

Our data experts formulated a complex and industry leading algorithm to best assess the chances of the competing horses.

The algorithm processed the following steps before running the simulations and generating the winning probabilities for all competing horses.

1. Data Collection & Extraction
The project utilised extensive data sourced internally, consisting of two primary groups:

Historical Winners: Data on past victors of the Grand National to establish “success profiles.”Current Contenders: The 2026 entries for whom we calculated winning probabilities.

2. Machine Learning Methodology

The model utilises a ‘Relative Profile Matching’ approach based on ‘Cosine Similarity’ and ‘Softmax Normalisation’.

A. Feature Vectorisation
We combined numerical features (Age, Betting Position, Odds, Weight) with categorical features (Breeding and Trainer countries).

Standardisation: Using StandardScaler, we normalized all features to a mean of 0 and a standard deviation of 1, preventing high-value features (like odds) from dominating the calculation.

B. Weighted Nearest Neighbours
Rather than comparing a horse to an “average” winner, we used a ‘Nearest Neighbours’ approach.

Max Similarity Score: Each horse was assigned a score based on its “closest” historical match. This acknowledges that there is more than one way to win a race (e.g., a “Young Improver” profile vs. a “Veteran” profile).

Feature Weighting: We applied manual weights to emphasize the most predictive variables, specifically giving the highest priority to Betting Position (0.9) and Distance Fitness (0.5).

C. Intra-Race Probability
To turn similarity scores into a “Chance of Winning,” we applied a Softmax function localised to each specific race name.

This ensures that the total probability for all horses in a single race sums to 100%.

This approach accounts for the “strength of the field”; a horse might be an elite match for history, but if it is racing against five other “elite” matches, its individual chance of winning is lower.

3. Final Output

The final model produced a ‘Winning Chance Score’ (1-100) for all the competing horses at the 2026 Grand National.