How good are these forecasts?
Every forecast scored on seasons the model never saw while its settings were chosen.
Held-back seasons
| Forecast | Forecasts | Log loss | Favourite won |
|---|---|---|---|
| The model | 45 | 0.622 | 73% |
| Base rate | 45 | 0.740 | 64% |
| Recent form | 45 | 0.699 | 64% |
Ratings use every game in the related competitions (see Sources); only Six Nations games are scored in the track record.
The simulated table adds bonus points the union way: four for a win, two for a draw, one for losing by seven or less, one for four tries (at each side's usual rate).
Injuries and selection are not in the model; the Grand Slam and Triple Crown are not simulated separately.
Questions and answers
How accurate are PodiumOracle's Six Nations predictions?
On 45 games from held-back seasons (2024 to 2026), which the model never saw while it was tuned, the side it favoured won 73% of the time. Its log loss was 0.622, against 0.740 for the base rate and 0.699 for recent form.