Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Aoi vs Goh
Matches counted1,699
Win rate50.3%
Widest swing5.6 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 |
|---|---|---|---|---|---|
| Rectangle | 55.9% | +5.6 | 0.098 | 195 | |
| Fence and open | 52.9% | +2.5 | 0.625 | 87 | |
| Low fence | 52.0% | +1.7 | 0.637 | 173 | |
| Full fence | 51.6% | +1.3 | 0.705 | 182 | |
| Open | 51.2% | +0.9 | 0.813 | 168 | |
| Octagon | 49.2% | -1.1 | 0.745 | 193 | |
| Half fence | 49.1% | -1.3 | 0.737 | 159 | |
| Breakable full fence | 48.4% | -1.9 | 0.612 | 153 | |
| Single wall | 48.1% | -2.2 | 0.559 | 160 | |
| Breakable half fence | 46.1% | -4.2 | 0.251 | 167 |
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 4.94 on 9 df, p 0.839
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 51.6%182 | +3.30.549 | +2.60.633 | +5.50.301 | -0.40.944 | +3.50.516 | -1.20.851 | +0.50.932 | -4.20.408 | +2.40.639 |
| Breakable full fence | -3.30.549 | 48.4%153 | -0.70.903 | +2.30.686 | -3.60.510 | +0.20.966 | -4.50.502 | -2.80.613 | -7.50.163 | -0.80.874 |
| Half fence | -2.60.633 | +0.70.903 | 49.1%159 | +3.00.594 | -3.00.589 | +0.90.868 | -3.80.567 | -2.10.700 | -6.80.200 | -0.20.975 |
| Breakable half fence | -5.50.301 | -2.30.686 | -3.00.594 | 46.1%167 | -5.90.275 | -2.00.715 | -6.80.306 | -5.10.352 | -9.80.063 | -3.10.555 |
| Low fence | +0.40.944 | +3.60.510 | +3.00.589 | +5.90.275 | 52.0%173 | +3.90.477 | -0.80.897 | +0.80.878 | -3.90.457 | +2.80.593 |
| Single wall | -3.50.516 | -0.20.966 | -0.90.868 | +2.00.715 | -3.90.477 | 48.1%160 | -4.80.476 | -3.10.579 | -7.80.145 | -1.10.837 |
| Fence and open | +1.20.851 | +4.50.502 | +3.80.567 | +6.80.306 | +0.80.897 | +4.80.476 | 52.9%87 | +1.70.799 | -3.00.637 | +3.60.572 |
| Open | -0.50.932 | +2.80.613 | +2.10.700 | +5.10.352 | -0.80.878 | +3.10.579 | -1.70.799 | 51.2%168 | -4.70.370 | +2.00.709 |
| Rectangle | +4.20.408 | +7.50.163 | +6.80.200 | +9.80.063 | +3.90.457 | +7.80.145 | +3.00.637 | +4.70.370 | 55.9%195 | +6.70.188 |
| Octagon | -2.40.639 | +0.80.874 | +0.20.975 | +3.10.555 | -2.80.593 | +1.10.837 | -3.60.572 | -2.00.709 | -6.70.188 | 49.2%193 |
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 counted1,616
Win rate50.1%
Widest swing-5.9 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 |
|---|---|---|---|---|---|
| Rectangle | 55.9% | +5.7 | 0.095 | 188 | |
| Low fence | 52.7% | +2.5 | 0.485 | 169 | |
| Open | 51.9% | +1.7 | 0.643 | 162 | |
| Fence and open | 51.2% | +1.1 | 0.836 | 80 | |
| Full fence | 51.2% | +1.0 | 0.773 | 172 | |
| Half fence | 49.3% | -0.8 | 0.839 | 150 | |
| Octagon | 48.9% | -1.2 | 0.725 | 180 | |
| Single wall | 48.4% | -1.7 | 0.649 | 155 | |
| Breakable full fence | 47.9% | -2.2 | 0.577 | 142 | |
| Breakable half fence | 44.2% | -5.9 | 0.121 | 156 |
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 5.99 on 9 df, p 0.741
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 51.2%172 | +3.30.563 | +1.80.743 | +6.90.209 | -1.50.782 | +2.80.616 | -0.10.990 | -0.70.900 | -4.70.373 | +2.30.670 |
| Breakable full fence | -3.30.563 | 47.9%142 | -1.40.805 | +3.70.527 | -4.80.401 | -0.50.931 | -3.40.630 | -4.00.490 | -8.00.152 | -1.00.858 |
| Half fence | -1.80.743 | +1.40.805 | 49.3%150 | +5.10.371 | -3.30.553 | +0.90.869 | -1.90.782 | -2.50.657 | -6.50.233 | +0.40.936 |
| Breakable half fence | -6.90.209 | -3.70.527 | -5.10.371 | 44.2%156 | -8.40.129 | -4.20.462 | -7.00.306 | -7.60.174 | -11.60.032 | -4.70.393 |
| Low fence | +1.50.782 | +4.80.401 | +3.30.553 | +8.40.129 | 52.7%169 | +4.30.442 | +1.40.835 | +0.80.883 | -3.20.546 | +3.80.481 |
| Single wall | -2.80.616 | +0.50.931 | -0.90.869 | +4.20.462 | -4.30.442 | 48.4%155 | -2.90.677 | -3.50.537 | -7.50.168 | -0.50.927 |
| Fence and open | +0.10.990 | +3.40.630 | +1.90.782 | +7.00.306 | -1.40.835 | +2.90.677 | 51.2%80 | -0.60.930 | -4.60.489 | +2.40.725 |
| Open | +0.70.900 | +4.00.490 | +2.50.657 | +7.60.174 | -0.80.883 | +3.50.537 | +0.60.930 | 51.9%162 | -4.00.454 | +3.00.584 |
| Rectangle | +4.70.373 | +8.00.152 | +6.50.233 | +11.60.032 | +3.20.546 | +7.50.168 | +4.60.489 | +4.00.454 | 55.9%188 | +7.00.181 |
| Octagon | -2.30.670 | +1.00.858 | -0.40.936 | +4.70.393 | -3.80.481 | +0.50.927 | -2.40.725 | -3.00.584 | -7.00.181 | 48.9%180 |
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 counted83
Win rate54.2%
Widest swing-29.2 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 |
|---|---|---|---|---|---|
| Breakable half fence | 72.7% | +18.5 | 0.186 | 11 · | |
| Fence and open | 71.4% | +17.2 | 0.339 | 7 · | |
| Full fence | 60.0% | +5.8 | 0.696 | 10 · | |
| Rectangle | 57.1% | +2.9 | 0.871 | 7 · | |
| Breakable full fence | 54.5% | +0.3 | 0.981 | 11 · | |
| Octagon | 53.9% | -0.4 | 0.977 | 13 · | |
| Half fence | 44.4% | -9.8 | 0.533 | 9 · | |
| Single wall | 40.0% | -14.2 | 0.510 | 5 · | |
| Open | 33.3% | -20.9 | 0.286 | 6 · | |
| Low fence | 25.0% | -29.2 | 0.229 | 4 · |
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 5.70 on 9 df, p 0.770
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 60.0%10 | +5.50.801 | +15.60.498 | -12.70.537 | +35.00.237 | +20.00.464 | -11.40.627 | +26.70.302 | +2.90.906 | +6.20.768 |
| Breakable full fence | -5.50.801 | 54.5%11 | +10.10.653 | -18.20.375 | +29.60.310 | +14.60.590 | -16.90.474 | +21.20.402 | -2.60.914 | +0.70.973 |
| Half fence | -15.60.498 | -10.10.653 | 44.4%9 | -28.30.199 | +19.40.506 | +4.40.872 | -27.00.280 | +11.10.667 | -12.70.614 | -9.40.665 |
| Breakable half fence | +12.70.537 | +18.20.375 | +28.30.199 | 72.7%11 | +47.70.095 | +32.70.210 | +1.30.952 | +39.40.115 | +15.60.494 | +18.90.341 |
| Low fence | -35.00.237 | -29.60.310 | -19.40.506 | -47.70.095 | 25.0%4 | -15.00.635 | -46.40.137 | -8.30.778 | -32.10.303 | -28.90.312 |
| Single wall | -20.00.464 | -14.60.590 | -4.40.872 | -32.70.210 | +15.00.635 | 40.0%5 | -31.40.276 | +6.70.819 | -17.10.558 | -13.80.599 |
| Fence and open | +11.40.627 | +16.90.474 | +27.00.280 | -1.30.952 | +46.40.137 | +31.40.276 | 71.4%7 | +38.10.170 | +14.30.577 | +17.60.444 |
| Open | -26.70.302 | -21.20.402 | -11.10.667 | -39.40.115 | +8.30.778 | -6.70.819 | -38.10.170 | 33.3%6 | -23.80.391 | -20.50.405 |
| Rectangle | -2.90.906 | +2.60.914 | +12.70.614 | -15.60.494 | +32.10.303 | +17.10.558 | -14.30.577 | +23.80.391 | 57.1%7 | +3.30.888 |
| Octagon | -6.20.768 | -0.70.973 | +9.40.665 | -18.90.341 | +28.90.312 | +13.80.599 | -17.60.444 | +20.50.405 | -3.30.888 | 53.9%13 |
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.