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 | 1663 | 0.668 | 60% |
| Base rate | 1663 | 0.693 | 45% |
| Recent form | 1663 | 0.674 | 59% |
Against the betting markets
Each market's price before the start, scored on the same finished games as the model. A negative figure means the market was more accurate.
| Market | Since | Priced | Model log loss | Market log loss | Model vs market |
|---|---|---|---|---|---|
| Bookmakers (Pinnacle, DraftKings, bet365) | 24 Jan 2026 | 508 | 0.666 | 0.596 | −11.7% |
| Polymarket | 22 Sep 2026 | 106 | 0.688 | 0.630 | −9.0% |
| Kalshi | 11 May 2025 | 667 | 0.665 | 0.592 | −12.5% |
Fighters move between promotions, so every rating also counts their Bellator and PFL fights; only UFC fights are forecast and scored in the track record.
A fight is a win or a loss for the rating, however it ended; a draw counts half each and a no contest not at all.
Ratings carry from one fight to the next with no pull back to average: fighters don't have seasons.
There is no weather here: cards are indoors.
Weight changes, layoffs, age and camp changes are not in the model.
Betting lines aren't in the source, so there is no market comparison.
Questions and answers
How accurate are PodiumOracle's UFC predictions?
On 1,663 games from held-back seasons (2024 to 2026), which the model never saw while it was tuned, the side it favoured won 60% of the time. Its log loss was 0.668, against 0.693 for the base rate and 0.674 for recent form. Against the betting markets on the same finished games, its log loss was 0.666 against the bookmakers' 0.596 over 508 games, 0.688 against Polymarket's 0.630 over 106 games and 0.665 against Kalshi's 0.592 over 667 games (lower is better).