How accurate are UFCalendar's MMA fight predictions?
How the model's pre-fight probabilities actually fared, graded against every decided fight in the database. Nothing is cherry-picked: these are the same numbers shown on bout pages before each fight, recomputed live.
UFCalendar's Power Index has correctly picked the winner in 62.9% of the 26659 MMA fights graded so far, with a Brier score of 0.235. It is well calibrated: when the model gives a fighter a 50%-55% chance, that favorite wins 55.2% of the time.
- Favorite accuracy
- 62.9%
- Fights graded
- 26659
- Brier score
- 0.235
When the model says 70%, does the favorite actually win about 70% of the time? Predicted vs. observed, by confidence bucket.
| Model says | Avg predicted | Favorite won | Fights |
|---|---|---|---|
| 50%–55% | 52.2% | 55.2% | 8957 |
| 55%–60% | 57.4% | 59.7% | 7133 |
| 60%–65% | 62.3% | 65.4% | 5167 |
| 65%–70% | 67.3% | 72.6% | 3193 |
| 70%–75% | 72.3% | 79.8% | 1869 |
| 75%–80% | 77.2% | 81.4% | 867 |
| 80%–100% | 83% | 81.8% | 352 |
| Year | Fights | Accuracy |
|---|---|---|
| 2026 | 1531 | 61.1% |
| 2025 | 2343 | 62.4% |
| 2024 | 2318 | 63% |
| 2023 | 2386 | 63.3% |
| 2022 | 1882 | 64.9% |
| 2021 | 1753 | 63.4% |
| 2020 | 1322 | 64.2% |
| 2019 | 1902 | 61.9% |
| 2018 | 1577 | 61% |
| 2017 | 1324 | 63.4% |
| 2016 | 1185 | 62.3% |
| 2015 | 959 | 61.9% |
| 2014 | 981 | 63.8% |
| 2013 | 740 | 64.6% |
| 2012 | 648 | 60.8% |
| 2011 | 668 | 61.8% |
| 2010 | 629 | 61.2% |
| 2009 | 470 | 59.6% |
| 2008 | 372 | 61.6% |
| 2007 | 319 | 64.6% |
| 2006 | 355 | 67.6% |
| 2005 | 211 | 71.6% |
| 2004 | 158 | 62.7% |
| 2003 | 100 | 64% |
| 2002 | 121 | 66.1% |
| 2001 | 90 | 64.4% |
| 2000 | 93 | 76.3% |
| 1999 | 66 | 66.7% |
| 1998 | 39 | 61.5% |
| 1997 | 35 | 57.1% |
| 1996 | 34 | 64.7% |
| 1995 | 27 | 70.4% |
| 1994 | 18 | 77.8% |
| 1993 | 3 | 66.7% |
Every number on this page is recomputed live from the stored pre-fight probabilities, the same ones printed on bout pages before each fight happens. Draws are excluded (no verdict to grade) and dead-even 50/50 prices grade no pick. Ratings and probabilities span every organization we track, back to 1993.