Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Aoi vs Brad
Matches counted1,766
Win rate54.0%
Widest swing4.7 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Aoi's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Single wall | 58.7% | +4.7 | 0.204 | 167 | |
| Breakable full fence | 57.1% | +3.0 | 0.392 | 177 | |
| Open | 56.7% | +2.7 | 0.390 | 224 | |
| Fence and open | 55.6% | +1.5 | 0.790 | 72 · | |
| Low fence | 55.1% | +1.1 | 0.759 | 165 | |
| Full fence | 54.5% | +0.5 | 0.902 | 156 | |
| Half fence | 52.0% | -2.0 | 0.579 | 173 | |
| Rectangle | 51.1% | -2.9 | 0.413 | 178 | |
| Octagon | 50.5% | -3.5 | 0.321 | 182 | |
| Breakable half fence | 50.3% | -3.7 | 0.296 | 175 |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Aoi's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 5.68 on 9 df, p 0.772
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 54.5%156 | -2.60.637 | +2.50.655 | +4.20.445 | -0.70.905 | -4.20.447 | -1.10.880 | -2.20.670 | +3.40.539 | +3.90.470 |
| Breakable full fence | +2.60.637 | 57.1%177 | +5.00.344 | +6.80.202 | +1.90.722 | -1.60.761 | +1.50.828 | +0.40.941 | +5.90.262 | +6.50.216 |
| Half fence | -2.50.655 | -5.00.344 | 52.0%173 | +1.70.746 | -3.10.564 | -6.70.217 | -3.50.614 | -4.70.354 | +0.90.866 | +1.50.781 |
| Breakable half fence | -4.20.445 | -6.80.202 | -1.70.746 | 50.3%175 | -4.90.369 | -8.40.119 | -5.30.451 | -6.40.202 | -0.80.875 | -0.30.960 |
| Low fence | +0.70.905 | -1.90.722 | +3.10.564 | +4.90.369 | 55.1%165 | -3.50.516 | -0.40.954 | -1.60.762 | +4.00.455 | +4.60.391 |
| Single wall | +4.20.447 | +1.60.761 | +6.70.217 | +8.40.119 | +3.50.516 | 58.7%167 | +3.10.653 | +2.00.694 | +7.60.159 | +8.10.128 |
| Fence and open | +1.10.880 | -1.50.828 | +3.50.614 | +5.30.451 | +0.40.954 | -3.10.653 | 55.6%72 | -1.10.865 | +4.40.525 | +5.00.472 |
| Open | +2.20.670 | -0.40.941 | +4.70.354 | +6.40.202 | +1.60.762 | -2.00.694 | +1.10.865 | 56.7%224 | +5.60.265 | +6.20.217 |
| Rectangle | -3.40.539 | -5.90.262 | -0.90.866 | +0.80.875 | -4.00.455 | -7.60.159 | -4.40.525 | -5.60.265 | 51.1%178 | +0.60.913 |
| Octagon | -3.90.470 | -6.50.216 | -1.50.781 | +0.30.960 | -4.60.391 | -8.10.128 | -5.00.472 | -6.20.217 | -0.60.913 | 50.5%182 |
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 counted1,543
Win rate55.2%
Widest swing6.7 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Aoi's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Single wall | 61.9% | +6.7 | 0.098 | 139 | |
| Open | 59.0% | +3.8 | 0.249 | 200 | |
| Breakable full fence | 58.4% | +3.2 | 0.413 | 149 | |
| Full fence | 56.2% | +1.0 | 0.808 | 137 | |
| Low fence | 55.3% | +0.1 | 0.976 | 150 | |
| Fence and open | 54.8% | -0.4 | 0.951 | 62 · | |
| Half fence | 53.2% | -2.0 | 0.604 | 154 | |
| Rectangle | 51.9% | -3.4 | 0.363 | 162 | |
| Breakable half fence | 51.7% | -3.5 | 0.361 | 149 | |
| Octagon | 51.3% | -4.0 | 0.292 | 158 |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Aoi's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 7.03 on 9 df, p 0.634
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 56.2%137 | -2.20.709 | +3.00.613 | +4.50.443 | +0.90.882 | -5.70.338 | +1.40.857 | -2.80.610 | +4.30.452 | +4.90.396 |
| Breakable full fence | +2.20.709 | 58.4%149 | +5.10.368 | +6.70.244 | +3.10.594 | -3.50.547 | +3.50.635 | -0.60.909 | +6.50.247 | +7.10.210 |
| Half fence | -3.00.613 | -5.10.368 | 53.2%154 | +1.60.785 | -2.10.715 | -8.60.136 | -1.60.832 | -5.80.279 | +1.40.804 | +2.00.726 |
| Breakable half fence | -4.50.443 | -6.70.244 | -1.60.785 | 51.7%149 | -3.60.526 | -10.20.081 | -3.20.675 | -7.30.173 | -0.20.976 | +0.40.942 |
| Low fence | -0.90.882 | -3.10.594 | +2.10.715 | +3.60.526 | 55.3%150 | -6.50.260 | +0.50.947 | -3.70.492 | +3.50.538 | +4.10.475 |
| Single wall | +5.70.338 | +3.50.547 | +8.60.136 | +10.20.081 | +6.50.260 | 61.9%139 | +7.00.348 | +2.90.595 | +10.00.080 | +10.60.066 |
| Fence and open | -1.40.857 | -3.50.635 | +1.60.832 | +3.20.675 | -0.50.947 | -7.00.348 | 54.8%62 | -4.20.562 | +3.00.689 | +3.60.633 |
| Open | +2.80.610 | +0.60.909 | +5.80.279 | +7.30.173 | +3.70.492 | -2.90.595 | +4.20.562 | 59.0%200 | +7.20.173 | +7.70.144 |
| Rectangle | -4.30.452 | -6.50.247 | -1.40.804 | +0.20.976 | -3.50.538 | -10.00.080 | -3.00.689 | -7.20.173 | 51.9%162 | +0.60.916 |
| Octagon | -4.90.396 | -7.10.210 | -2.00.726 | -0.40.942 | -4.10.475 | -10.60.066 | -3.60.633 | -7.70.144 | -0.60.916 | 51.3%158 |
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 counted223
Win rate45.7%
Widest swing14.3 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Aoi's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Fence and open | 60.0% | +14.3 | 0.354 | 10 · | |
| Low fence | 53.3% | +7.6 | 0.541 | 15 · | |
| Breakable full fence | 50.0% | +4.3 | 0.628 | 28 · | |
| Octagon | 45.8% | +0.1 | 0.992 | 24 · | |
| Rectangle | 43.8% | -2.0 | 0.868 | 16 · | |
| Single wall | 42.9% | -2.9 | 0.743 | 28 · | |
| Breakable half fence | 42.3% | -3.4 | 0.709 | 26 · | |
| Full fence | 42.1% | -3.6 | 0.740 | 19 · | |
| Half fence | 42.1% | -3.6 | 0.740 | 19 · | |
| Open | 37.5% | -8.2 | 0.391 | 24 · |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Aoi's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 2.43 on 9 df, p 0.983
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 42.1%19 | -7.90.595 | +0.01.000 | -0.20.989 | -11.20.515 | -0.80.959 | -17.90.359 | +4.60.759 | -1.60.922 | -3.70.807 |
| Breakable full fence | +7.90.595 | 50.0%28 | +7.90.595 | +7.70.571 | -3.30.835 | +7.10.592 | -10.00.587 | +12.50.366 | +6.20.690 | +4.20.764 |
| Half fence | -0.01.000 | -7.90.595 | 42.1%19 | -0.20.989 | -11.20.515 | -0.80.959 | -17.90.359 | +4.60.759 | -1.60.922 | -3.70.807 |
| Breakable half fence | +0.20.989 | -7.70.571 | +0.20.989 | 42.3%26 | -11.00.495 | -0.60.967 | -17.70.341 | +4.80.729 | -1.40.927 | -3.50.802 |
| Low fence | +11.20.515 | +3.30.835 | +11.20.515 | +11.00.495 | 53.3%15 | +10.50.512 | -6.70.742 | +15.80.332 | +9.60.594 | +7.50.648 |
| Single wall | +0.80.959 | -7.10.592 | +0.80.959 | +0.60.967 | -10.50.512 | 42.9%28 | -17.10.351 | +5.40.695 | -0.90.954 | -3.00.829 |
| Fence and open | +17.90.359 | +10.00.587 | +17.90.359 | +17.70.341 | +6.70.742 | +17.10.351 | 60.0%10 | +22.50.229 | +16.20.420 | +14.20.452 |
| Open | -4.60.759 | -12.50.366 | -4.60.759 | -4.80.729 | -15.80.332 | -5.40.695 | -22.50.229 | 37.5%24 | -6.20.693 | -8.30.558 |
| Rectangle | +1.60.922 | -6.20.690 | +1.60.922 | +1.40.927 | -9.60.594 | +0.90.954 | -16.20.420 | +6.20.693 | 43.8%16 | -2.10.897 |
| Octagon | +3.70.807 | -4.20.764 | +3.70.807 | +3.50.802 | -7.50.648 | +3.00.829 | -14.20.452 | +8.30.558 | +2.10.897 | 45.8%24 |
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.