Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Brad vs Jean
Matches counted2,122
Win rate51.4%
Widest swing-3.6 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 | 54.1% | +2.7 | 0.425 | 196 | |
| Breakable half fence | 53.9% | +2.5 | 0.407 | 247 | |
| Half fence | 53.2% | +1.9 | 0.578 | 201 | |
| Rectangle | 52.6% | +1.2 | 0.694 | 232 | |
| Full fence | 52.2% | +0.8 | 0.831 | 161 | |
| Low fence | 50.9% | -0.5 | 0.871 | 232 | |
| Fence and open | 50.5% | -0.9 | 0.849 | 107 | |
| Octagon | 50.0% | -1.4 | 0.678 | 208 | |
| Single wall | 48.3% | -3.1 | 0.354 | 203 | |
| Open | 47.8% | -3.6 | 0.255 | 224 |
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 3.80 on 9 df, p 0.924
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 52.2%161 | -1.90.719 | -1.10.841 | -1.70.741 | +1.30.798 | +3.90.460 | +1.70.784 | +4.40.394 | -0.40.936 | +2.20.679 |
| Breakable full fence | +1.90.719 | 54.1%196 | +0.80.866 | +0.20.961 | +3.20.506 | +5.80.246 | +3.60.547 | +6.30.197 | +1.50.757 | +4.10.412 |
| Half fence | +1.10.841 | -0.80.866 | 53.2%201 | -0.60.897 | +2.40.622 | +5.00.319 | +2.80.643 | +5.50.260 | +0.60.893 | +3.20.513 |
| Breakable half fence | +1.70.741 | -0.20.961 | +0.60.897 | 53.9%247 | +3.00.513 | +5.60.239 | +3.40.559 | +6.10.188 | +1.30.782 | +3.90.413 |
| Low fence | -1.30.798 | -3.20.506 | -2.40.622 | -3.00.513 | 50.9%232 | +2.60.590 | +0.40.946 | +3.10.509 | -1.70.710 | +0.90.857 |
| Single wall | -3.90.460 | -5.80.246 | -5.00.319 | -5.60.239 | -2.60.590 | 48.3%203 | -2.20.714 | +0.50.916 | -4.30.370 | -1.70.727 |
| Fence and open | -1.70.784 | -3.60.547 | -2.80.643 | -3.40.559 | -0.40.946 | +2.20.714 | 50.5%107 | +2.70.646 | -2.10.717 | +0.50.937 |
| Open | -4.40.394 | -6.30.197 | -5.50.260 | -6.10.188 | -3.10.509 | -0.50.916 | -2.70.646 | 47.8%224 | -4.80.304 | -2.20.643 |
| Rectangle | +0.40.936 | -1.50.757 | -0.60.893 | -1.30.782 | +1.70.710 | +4.30.370 | +2.10.717 | +4.80.304 | 52.6%232 | +2.60.588 |
| Octagon | -2.20.679 | -4.10.412 | -3.20.513 | -3.90.413 | -0.90.857 | +1.70.727 | -0.50.937 | +2.20.643 | -2.60.588 | 50.0%208 |
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 counted2,015
Win rate51.6%
Widest swing-3.5 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 |
|---|---|---|---|---|---|
| Half fence | 54.2% | +2.6 | 0.448 | 192 | |
| Breakable full fence | 53.7% | +2.2 | 0.534 | 188 | |
| Rectangle | 53.6% | +2.0 | 0.524 | 224 | |
| Breakable half fence | 53.4% | +1.8 | 0.554 | 238 | |
| Full fence | 51.3% | -0.2 | 0.949 | 152 | |
| Octagon | 50.8% | -0.8 | 0.810 | 199 | |
| Fence and open | 50.0% | -1.6 | 0.743 | 104 | |
| Low fence | 50.0% | -1.6 | 0.619 | 224 | |
| Single wall | 49.4% | -2.1 | 0.552 | 178 | |
| Open | 48.1% | -3.5 | 0.288 | 210 |
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 3.25 on 9 df, p 0.953
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 51.3%152 | -2.40.658 | -2.90.599 | -2.00.693 | +1.30.802 | +1.90.734 | +1.30.836 | +3.20.545 | -2.20.667 | +0.60.917 |
| Breakable full fence | +2.40.658 | 53.7%188 | -0.50.931 | +0.40.941 | +3.70.451 | +4.30.412 | +3.70.542 | +5.60.262 | +0.10.975 | +3.00.559 |
| Half fence | +2.90.599 | +0.50.931 | 54.2%192 | +0.80.868 | +4.20.396 | +4.70.363 | +4.20.493 | +6.10.224 | +0.60.903 | +3.40.499 |
| Breakable half fence | +2.00.693 | -0.40.941 | -0.80.868 | 53.4%238 | +3.40.470 | +3.90.428 | +3.40.567 | +5.30.266 | -0.20.964 | +2.60.587 |
| Low fence | -1.30.802 | -3.70.451 | -4.20.396 | -3.40.470 | 50.0%224 | +0.60.911 | +0.01.000 | +1.90.692 | -3.60.449 | -0.80.877 |
| Single wall | -1.90.734 | -4.30.412 | -4.70.363 | -3.90.428 | -0.60.911 | 49.4%178 | -0.60.927 | +1.30.792 | -4.10.410 | -1.30.799 |
| Fence and open | -1.30.836 | -3.70.542 | -4.20.493 | -3.40.567 | -0.01.000 | +0.60.927 | 50.0%104 | +1.90.751 | -3.60.547 | -0.80.901 |
| Open | -3.20.545 | -5.60.262 | -6.10.224 | -5.30.266 | -1.90.692 | -1.30.792 | -1.90.751 | 48.1%210 | -5.50.254 | -2.60.591 |
| Rectangle | +2.20.667 | -0.10.975 | -0.60.903 | +0.20.964 | +3.60.449 | +4.10.410 | +3.60.547 | +5.50.254 | 53.6%224 | +2.80.563 |
| Octagon | -0.60.917 | -3.00.559 | -3.40.499 | -2.60.587 | +0.80.877 | +1.30.799 | +0.80.901 | +2.60.591 | -2.80.563 | 50.8%199 |
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 counted107
Win rate47.7%
Widest swing27.3 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 |
|---|---|---|---|---|---|
| Low fence | 75.0% | +27.3 | 0.108 | 8 · | |
| Breakable half fence | 66.7% | +19.0 | 0.233 | 9 · | |
| Full fence | 66.7% | +19.0 | 0.233 | 9 · | |
| Fence and open | 66.7% | +19.0 | 0.504 | 3 · | |
| Breakable full fence | 62.5% | +14.8 | 0.382 | 8 · | |
| Open | 42.9% | -4.8 | 0.699 | 14 · | |
| Single wall | 40.0% | -7.7 | 0.381 | 25 · | |
| Half fence | 33.3% | -14.3 | 0.368 | 9 · | |
| Octagon | 33.3% | -14.3 | 0.368 | 9 · | |
| Rectangle | 25.0% | -22.7 | 0.182 | 8 · |
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 9.98 on 9 df, p 0.352
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 66.7%9 | +4.20.858 | +33.30.157 | +0.01.000 | -8.30.707 | +26.70.169 | +0.01.000 | +23.80.265 | +41.70.086 | +33.30.157 |
| Breakable full fence | -4.20.858 | 62.5%8 | +29.20.229 | -4.20.858 | -12.50.590 | +22.50.266 | -4.20.898 | +19.60.375 | +37.50.131 | +29.20.229 |
| Half fence | -33.30.157 | -29.20.229 | 33.3%9 | -33.30.157 | -41.70.086 | -6.70.724 | -33.30.310 | -9.50.648 | +8.30.707 | +0.01.000 |
| Breakable half fence | -0.01.000 | +4.20.858 | +33.30.157 | 66.7%9 | -8.30.707 | +26.70.169 | +0.01.000 | +23.80.265 | +41.70.086 | +33.30.157 |
| Low fence | +8.30.707 | +12.50.590 | +41.70.086 | +8.30.707 | 75.0%8 | +35.00.085 | +8.30.782 | +32.10.145 | +50.00.046 | +41.70.086 |
| Single wall | -26.70.169 | -22.50.266 | +6.70.724 | -26.70.169 | -35.00.085 | 40.0%25 | -26.70.378 | -2.90.862 | +15.00.443 | +6.70.724 |
| Fence and open | -0.01.000 | +4.20.898 | +33.30.310 | -0.01.000 | -8.30.782 | +26.70.378 | 66.7%3 | +23.80.453 | +41.70.201 | +33.30.310 |
| Open | -23.80.265 | -19.60.375 | +9.50.648 | -23.80.265 | -32.10.145 | +2.90.862 | -23.80.453 | 42.9%14 | +17.90.402 | +9.50.648 |
| Rectangle | -41.70.086 | -37.50.131 | -8.30.707 | -41.70.086 | -50.00.046 | -15.00.443 | -41.70.201 | -17.90.402 | 25.0%8 | -8.30.707 |
| Octagon | -33.30.157 | -29.20.229 | -0.01.000 | -33.30.157 | -41.70.086 | -6.70.724 | -33.30.310 | -9.50.648 | +8.30.707 | 33.3%9 |
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.