Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Brad vs Vanessa
Matches counted1,560
Win rate52.2%
Widest swing-10.9 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 |
|---|---|---|---|---|---|
| Open | 59.9% | +7.7 | 0.029 | 177 | |
| Fence and open | 57.4% | +5.2 | 0.383 | 68 · | |
| Full fence | 57.1% | +5.0 | 0.231 | 133 | |
| Rectangle | 54.1% | +1.9 | 0.592 | 170 | |
| Breakable half fence | 52.5% | +0.3 | 0.946 | 143 | |
| Low fence | 52.3% | +0.1 | 0.971 | 151 | |
| Octagon | 50.3% | -1.9 | 0.583 | 183 | |
| Breakable full fence | 49.0% | -3.1 | 0.409 | 155 | |
| Single wall | 47.6% | -4.6 | 0.210 | 168 | |
| Half fence | 41.3% | -10.9 | 0.007 | 138 |
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 15.30 on 9 df, p 0.083
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 57.1%133 | +8.10.169 | +15.80.009 | +4.70.434 | +4.80.415 | +9.50.101 | -0.20.977 | -2.80.627 | +3.00.599 | +6.90.227 |
| Breakable full fence | -8.10.169 | 49.0%155 | +7.70.185 | -3.40.556 | -3.30.565 | +1.40.800 | -8.30.252 | -10.90.047 | -5.10.359 | -1.20.820 |
| Half fence | -15.80.009 | -7.70.185 | 41.3%138 | -11.20.061 | -11.00.061 | -6.30.269 | -16.10.030 | -18.60.001 | -12.80.025 | -9.00.111 |
| Breakable half fence | -4.70.434 | +3.40.556 | +11.20.061 | 52.5%143 | +0.10.982 | +4.80.396 | -4.90.504 | -7.40.182 | -1.70.768 | +2.20.697 |
| Low fence | -4.80.415 | +3.30.565 | +11.00.061 | -0.10.982 | 52.3%151 | +4.70.402 | -5.00.489 | -7.60.168 | -1.80.747 | +2.00.710 |
| Single wall | -9.50.101 | -1.40.800 | +6.30.269 | -4.80.396 | -4.70.402 | 47.6%168 | -9.70.176 | -12.30.022 | -6.50.232 | -2.60.619 |
| Fence and open | +0.20.977 | +8.30.252 | +16.10.030 | +4.90.504 | +5.00.489 | +9.70.176 | 57.4%68 | -2.50.718 | +3.20.650 | +7.10.318 |
| Open | +2.80.627 | +10.90.047 | +18.60.001 | +7.40.182 | +7.60.168 | +12.30.022 | +2.50.718 | 59.9%177 | +5.80.278 | +9.60.067 |
| Rectangle | -3.00.599 | +5.10.359 | +12.80.025 | +1.70.768 | +1.80.747 | +6.50.232 | -3.20.650 | -5.80.278 | 54.1%170 | +3.90.470 |
| Octagon | -6.90.227 | +1.20.820 | +9.00.111 | -2.20.697 | -2.00.710 | +2.60.619 | -7.10.318 | -9.60.067 | -3.90.470 | 50.3%183 |
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 counted1,196
Win rate51.8%
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 |
|---|---|---|---|---|---|
| Open | 57.6% | +5.9 | 0.132 | 144 | |
| Rectangle | 56.4% | +4.7 | 0.239 | 140 | |
| Low fence | 54.4% | +2.6 | 0.555 | 114 | |
| Full fence | 52.7% | +0.9 | 0.851 | 93 | |
| Fence and open | 52.2% | +0.4 | 0.954 | 46 · | |
| Breakable half fence | 51.0% | -0.8 | 0.865 | 104 | |
| Octagon | 50.4% | -1.4 | 0.723 | 141 | |
| Breakable full fence | 48.8% | -3.0 | 0.486 | 123 | |
| Single wall | 48.0% | -3.8 | 0.375 | 125 | |
| Half fence | 41.1% | -10.6 | 0.021 | 107 |
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 9.65 on 9 df, p 0.379
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 52.7%93 | +3.90.570 | +11.60.102 | +1.70.809 | -1.70.808 | +4.70.494 | +0.50.954 | -5.00.454 | -3.70.574 | +2.30.727 |
| Breakable full fence | -3.90.570 | 48.8%123 | +7.70.244 | -2.20.743 | -5.60.388 | +0.80.902 | -3.40.695 | -8.90.148 | -7.70.215 | -1.60.799 |
| Half fence | -11.60.102 | -7.70.244 | 41.1%107 | -9.80.152 | -13.30.049 | -6.90.294 | -11.10.207 | -16.50.010 | -15.30.017 | -9.20.149 |
| Breakable half fence | -1.70.809 | +2.20.743 | +9.80.152 | 51.0%104 | -3.40.613 | +3.00.655 | -1.20.891 | -6.70.297 | -5.50.397 | +0.60.925 |
| Low fence | +1.70.808 | +5.60.388 | +13.30.049 | +3.40.613 | 54.4%114 | +6.40.324 | +2.20.800 | -3.20.601 | -2.00.745 | +4.00.522 |
| Single wall | -4.70.494 | -0.80.902 | +6.90.294 | -3.00.655 | -6.40.324 | 48.0%125 | -4.20.628 | -9.60.114 | -8.40.170 | -2.40.701 |
| Fence and open | -0.50.954 | +3.40.695 | +11.10.207 | +1.20.891 | -2.20.800 | +4.20.628 | 52.2%46 | -5.50.515 | -4.30.615 | +1.80.830 |
| Open | +5.00.454 | +8.90.148 | +16.50.010 | +6.70.297 | +3.20.601 | +9.60.114 | +5.50.515 | 57.6%144 | +1.20.837 | +7.30.217 |
| Rectangle | +3.70.574 | +7.70.215 | +15.30.017 | +5.50.397 | +2.00.745 | +8.40.170 | +4.30.615 | -1.20.837 | 56.4%140 | +6.10.307 |
| Octagon | -2.30.727 | +1.60.799 | +9.20.149 | -0.60.925 | -4.00.522 | +2.40.701 | -1.80.830 | -7.30.217 | -6.10.307 | 50.4%141 |
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 counted364
Win rate53.6%
Widest swing16.1 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 |
|---|---|---|---|---|---|
| Open | 69.7% | +16.1 | 0.051 | 33 · | |
| Fence and open | 68.2% | +14.6 | 0.156 | 22 · | |
| Full fence | 67.5% | +13.9 | 0.061 | 40 · | |
| Breakable half fence | 56.4% | +2.8 | 0.707 | 39 · | |
| Breakable full fence | 50.0% | -3.6 | 0.671 | 32 · | |
| Octagon | 50.0% | -3.6 | 0.622 | 42 · | |
| Single wall | 46.5% | -7.1 | 0.323 | 43 · | |
| Low fence | 46.0% | -7.6 | 0.326 | 37 · | |
| Rectangle | 43.3% | -10.2 | 0.240 | 30 · | |
| Half fence | 41.9% | -11.6 | 0.174 | 31 · |
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 13.64 on 9 df, p 0.136
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 67.5%40 | +17.50.132 | +25.60.031 | +11.10.310 | +21.60.056 | +21.00.054 | -0.70.956 | -2.20.841 | +24.20.043 | +17.50.108 |
| Breakable full fence | -17.50.132 | 50.0%32 | +8.10.521 | -6.40.590 | +4.00.737 | +3.50.765 | -18.20.184 | -19.70.105 | +6.70.599 | +0.01.000 |
| Half fence | -25.60.031 | -8.10.521 | 41.9%31 | -14.50.229 | -4.00.740 | -4.60.696 | -26.20.059 | -27.80.025 | -1.40.912 | -8.10.495 |
| Breakable half fence | -11.10.310 | +6.40.590 | +14.50.229 | 56.4%39 | +10.50.362 | +9.90.370 | -11.80.366 | -13.30.246 | +13.10.281 | +6.40.564 |
| Low fence | -21.60.056 | -4.00.737 | +4.00.740 | -10.50.362 | 46.0%37 | -0.60.960 | -22.20.097 | -23.80.045 | +2.60.831 | -4.00.719 |
| Single wall | -21.00.054 | -3.50.765 | +4.60.696 | -9.90.370 | +0.60.960 | 46.5%43 | -21.70.097 | -23.20.043 | +3.20.788 | -3.50.748 |
| Fence and open | +0.70.956 | +18.20.184 | +26.20.059 | +11.80.366 | +22.20.097 | +21.70.097 | 68.2%22 | -1.50.905 | +24.90.076 | +18.20.164 |
| Open | +2.20.841 | +19.70.105 | +27.80.025 | +13.30.246 | +23.80.045 | +23.20.043 | +1.50.905 | 69.7%33 | +26.40.035 | +19.70.086 |
| Rectangle | -24.20.043 | -6.70.599 | +1.40.912 | -13.10.281 | -2.60.831 | -3.20.788 | -24.90.076 | -26.40.035 | 43.3%30 | -6.70.576 |
| Octagon | -17.50.108 | -0.01.000 | +8.10.495 | -6.40.564 | +4.00.719 | +3.50.748 | -18.20.164 | -19.70.086 | +6.70.576 | 50.0%42 |
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.