Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Brad vs Pai
Matches counted1,780
Win rate50.7%
Widest swing-9.9 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Brad's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Fence and open | 56.5% | +5.7 | 0.278 | 85 | |
| Single wall | 54.3% | +3.6 | 0.381 | 140 | |
| Breakable full fence | 51.9% | +1.2 | 0.736 | 183 | |
| Open | 51.7% | +1.0 | 0.769 | 207 | |
| Full fence | 51.1% | +0.4 | 0.919 | 184 | |
| Breakable half fence | 50.8% | +0.1 | 0.985 | 189 | |
| Rectangle | 50.8% | +0.0 | 0.996 | 201 | |
| Octagon | 50.7% | -0.1 | 0.989 | 148 | |
| Low fence | 50.3% | -0.5 | 0.890 | 193 | |
| Half fence | 40.8% | -9.9 | 0.012 | 147 |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Brad's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 7.81 on 9 df, p 0.553
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 51.1%184 | -0.80.874 | +10.30.063 | +0.30.955 | +0.80.872 | -3.20.568 | -5.40.411 | -0.60.905 | +0.30.947 | +0.40.941 |
| Breakable full fence | +0.80.874 | 51.9%183 | +11.10.045 | +1.10.829 | +1.60.749 | -2.40.672 | -4.60.486 | +0.20.965 | +1.20.819 | +1.20.823 |
| Half fence | -10.30.063 | -11.10.045 | 40.8%147 | -10.00.069 | -9.40.084 | -13.50.022 | -15.70.021 | -10.90.043 | -9.90.067 | -9.90.089 |
| Breakable half fence | -0.30.955 | -1.10.829 | +10.00.069 | 50.8%189 | +0.50.917 | -3.50.531 | -5.70.384 | -0.90.858 | +0.00.993 | +0.10.983 |
| Low fence | -0.80.872 | -1.60.749 | +9.40.084 | -0.50.917 | 50.3%193 | -4.00.468 | -6.20.339 | -1.40.775 | -0.50.923 | -0.40.939 |
| Single wall | +3.20.568 | +2.40.672 | +13.50.022 | +3.50.531 | +4.00.468 | 54.3%140 | -2.20.749 | +2.60.635 | +3.50.520 | +3.60.540 |
| Fence and open | +5.40.411 | +4.60.486 | +15.70.021 | +5.70.384 | +6.20.339 | +2.20.749 | 56.5%85 | +4.80.457 | +5.70.376 | +5.80.394 |
| Open | +0.60.905 | -0.20.965 | +10.90.043 | +0.90.858 | +1.40.775 | -2.60.635 | -4.80.457 | 51.7%207 | +0.90.849 | +1.00.850 |
| Rectangle | -0.30.947 | -1.20.819 | +9.90.067 | -0.00.993 | +0.50.923 | -3.50.520 | -5.70.376 | -0.90.849 | 50.8%201 | +0.10.990 |
| Octagon | -0.40.941 | -1.20.823 | +9.90.089 | -0.10.983 | +0.40.939 | -3.60.540 | -5.80.394 | -1.00.850 | -0.10.990 | 50.7%148 |
Better on the row's stage — deeper at 5 and 10 pointsBetter on the column's stagep < 0.05 on its ownStill there after correcting for how many were tested· fewer than 80 decided matches on one side of the comparison
How significance is decided
- Each gap is two win rates compared with a pooled two-proportion z test, over decided matches only.
- The 95% interval is Newcombe's hybrid score method, which keeps its shape near 0% and 100% where a symmetric interval does not.
- q is p corrected for how many tests were asked at once, by Benjamini–Hochberg at a 5% false discovery rate. A figure is called real on q, never on p alone.
- Standard errors are widened by a measured design effect, because one player appears in many matches and those matches are not independent of each other.
- Stages are assigned at random, so a gap between them is the stage's own effect and not a difference in who chose to play where.
Matches counted1,611
Win rate51.3%
Widest swing-10.6 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Brad's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Breakable full fence | 55.5% | +4.2 | 0.262 | 164 | |
| Fence and open | 54.7% | +3.3 | 0.554 | 75 · | |
| Rectangle | 53.8% | +2.4 | 0.481 | 186 | |
| Octagon | 52.3% | +1.0 | 0.812 | 128 | |
| Breakable half fence | 52.1% | +0.8 | 0.831 | 165 | |
| Single wall | 51.5% | +0.2 | 0.961 | 130 | |
| Open | 51.5% | +0.1 | 0.975 | 173 | |
| Full fence | 51.1% | -0.2 | 0.959 | 174 | |
| Low fence | 49.5% | -1.9 | 0.587 | 186 | |
| Half fence | 40.8% | -10.6 | 0.012 | 130 |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Brad's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 8.07 on 9 df, p 0.527
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 51.1%174 | -4.30.424 | +10.40.073 | -1.00.858 | +1.70.749 | -0.40.946 | -3.50.610 | -0.30.956 | -2.60.620 | -1.20.837 |
| Breakable full fence | +4.30.424 | 55.5%164 | +14.70.012 | +3.40.540 | +6.00.260 | +4.00.500 | +0.80.906 | +4.00.457 | +1.70.746 | +3.10.593 |
| Half fence | -10.40.073 | -14.70.012 | 40.8%130 | -11.30.052 | -8.70.127 | -10.80.082 | -13.90.054 | -10.70.065 | -13.00.023 | -11.60.062 |
| Breakable half fence | +1.00.858 | -3.40.540 | +11.30.052 | 52.1%165 | +2.70.619 | +0.60.921 | -2.50.714 | +0.70.901 | -1.60.758 | -0.20.970 |
| Low fence | -1.70.749 | -6.00.260 | +8.70.127 | -2.70.619 | 49.5%186 | -2.10.716 | -5.20.447 | -2.00.707 | -4.30.407 | -2.90.616 |
| Single wall | +0.40.946 | -4.00.500 | +10.80.082 | -0.60.921 | +2.10.716 | 51.5%130 | -3.10.666 | +0.10.987 | -2.20.697 | -0.80.897 |
| Fence and open | +3.50.610 | -0.80.906 | +13.90.054 | +2.50.714 | +5.20.447 | +3.10.666 | 54.7%75 | +3.20.641 | +0.90.895 | +2.30.749 |
| Open | +0.30.956 | -4.00.457 | +10.70.065 | -0.70.901 | +2.00.707 | -0.10.987 | -3.20.641 | 51.5%173 | -2.30.660 | -0.90.877 |
| Rectangle | +2.60.620 | -1.70.746 | +13.00.023 | +1.60.758 | +4.30.407 | +2.20.697 | -0.90.895 | +2.30.660 | 53.8%186 | +1.40.804 |
| Octagon | +1.20.837 | -3.10.593 | +11.60.062 | +0.20.970 | +2.90.616 | +0.80.897 | -2.30.749 | +0.90.877 | -1.40.804 | 52.3%128 |
Better on the row's stage — deeper at 5 and 10 pointsBetter on the column's stagep < 0.05 on its ownStill there after correcting for how many were tested· fewer than 80 decided matches on one side of the comparison
How significance is decided
- Each gap is two win rates compared with a pooled two-proportion z test, over decided matches only.
- The 95% interval is Newcombe's hybrid score method, which keeps its shape near 0% and 100% where a symmetric interval does not.
- q is p corrected for how many tests were asked at once, by Benjamini–Hochberg at a 5% false discovery rate. A figure is called real on q, never on p alone.
- Standard errors are widened by a measured design effect, because one player appears in many matches and those matches are not independent of each other.
- Stages are assigned at random, so a gap between them is the stage's own effect and not a difference in who chose to play where.
Matches counted169
Win rate45.0%
Widest swing45.0 pts
Survive correction2
Period2026/03/26 – 2026/09/23
Where it was fought
Brad's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Single wall | 90.0% | +45.0 | 0.003 | 10 · | |
| Low fence | 71.4% | +26.5 | 0.151 | 7 · | |
| Fence and open | 70.0% | +25.0 | 0.101 | 10 · | |
| Open | 52.9% | +8.0 | 0.296 | 34 · | |
| Full fence | 50.0% | +5.0 | 0.742 | 10 · | |
| Breakable half fence | 41.7% | -3.3 | 0.725 | 24 · | |
| Half fence | 41.2% | -3.8 | 0.740 | 17 · | |
| Octagon | 40.0% | -5.0 | 0.634 | 20 · | |
| Breakable full fence | 21.1% | -23.9 | 0.026 | 19 · | |
| Rectangle | 13.3% | -31.6 | 0.010 | 15 · |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Brad's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 24.52 on 9 df, p 0.004
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 50.0%10 | +28.90.109 | +8.80.656 | +8.30.656 | -21.40.377 | -40.00.051 | -20.00.361 | -2.90.870 | +36.70.045 | +10.00.602 |
| Breakable full fence | -28.90.109 | 21.1%19 | -20.10.191 | -20.60.152 | -50.40.017 | -69.0<0.001 | -49.00.010 | -31.90.024 | +7.70.558 | -18.90.200 |
| Half fence | -8.80.656 | +20.10.191 | 41.2%17 | -0.50.975 | -30.20.178 | -48.80.013 | -28.80.148 | -11.80.428 | +27.90.080 | +1.20.942 |
| Breakable half fence | -8.30.656 | +20.60.152 | +0.50.975 | 41.7%24 | -29.80.166 | -48.30.010 | -28.30.132 | -11.30.397 | +28.30.062 | +1.70.911 |
| Low fence | +21.40.377 | +50.40.017 | +30.20.178 | +29.80.166 | 71.4%7 | -18.60.323 | +1.40.949 | +18.50.369 | +58.10.006 | +31.40.152 |
| Single wall | +40.00.051 | +69.0<0.001 | +48.80.013 | +48.30.010 | +18.60.323 | 90.0%10 | +20.00.264 | +37.10.034 | +76.7<0.001 | +50.00.009 |
| Fence and open | +20.00.361 | +49.00.010 | +28.80.148 | +28.30.132 | -1.40.949 | -20.00.264 | 70.0%10 | +17.10.338 | +56.70.004 | +30.00.121 |
| Open | +2.90.870 | +31.90.024 | +11.80.428 | +11.30.397 | -18.50.369 | -37.10.034 | -17.10.338 | 52.9%34 | +39.60.009 | +12.90.358 |
| Rectangle | -36.70.045 | -7.70.558 | -27.90.080 | -28.30.062 | -58.10.006 | -76.7<0.001 | -56.70.004 | -39.60.009 | 13.3%15 | -26.70.084 |
| Octagon | -10.00.602 | +18.90.200 | -1.20.942 | -1.70.911 | -31.40.152 | -50.00.009 | -30.00.121 | -12.90.358 | +26.70.084 | 40.0%20 |
Better on the row's stage — deeper at 5 and 10 pointsBetter on the column's stagep < 0.05 on its ownStill there after correcting for how many were tested· fewer than 80 decided matches on one side of the comparison
How significance is decided
- Each gap is two win rates compared with a pooled two-proportion z test, over decided matches only.
- The 95% interval is Newcombe's hybrid score method, which keeps its shape near 0% and 100% where a symmetric interval does not.
- q is p corrected for how many tests were asked at once, by Benjamini–Hochberg at a 5% false discovery rate. A figure is called real on q, never on p alone.
- Standard errors are widened by a measured design effect, because one player appears in many matches and those matches are not independent of each other.
- Stages are assigned at random, so a gap between them is the stage's own effect and not a difference in who chose to play where.