Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Goh vs Vanessa
Matches counted1,633
Win rate48.3%
Widest swing8.2 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Goh's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Open | 56.5% | +8.2 | 0.051 | 131 | |
| Breakable half fence | 53.5% | +5.2 | 0.171 | 155 | |
| Octagon | 50.0% | +1.7 | 0.627 | 184 | |
| Full fence | 48.9% | +0.6 | 0.860 | 186 | |
| Breakable full fence | 46.9% | -1.4 | 0.688 | 177 | |
| Fence and open | 46.2% | -2.1 | 0.679 | 93 | |
| Rectangle | 45.3% | -3.0 | 0.421 | 159 | |
| Half fence | 44.4% | -3.9 | 0.314 | 153 | |
| Low fence | 43.7% | -4.6 | 0.209 | 167 | |
| Single wall | 43.6% | -4.8 | 0.200 | 163 |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Goh's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 10.00 on 9 df, p 0.350
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 48.9%186 | +2.00.698 | +4.50.411 | -4.60.395 | +5.20.327 | +5.40.316 | +2.70.672 | -7.60.184 | +3.60.499 | -1.10.836 |
| Breakable full fence | -2.00.698 | 46.9%177 | +2.50.656 | -6.70.226 | +3.20.554 | +3.30.537 | +0.70.918 | -9.60.096 | +1.60.768 | -3.10.555 |
| Half fence | -4.50.411 | -2.50.656 | 44.4%153 | -9.10.110 | +0.70.895 | +0.90.874 | -1.80.784 | -12.10.043 | -0.80.882 | -5.60.309 |
| Breakable half fence | +4.60.395 | +6.70.226 | +9.10.110 | 53.5%155 | +9.80.078 | +10.00.075 | +7.30.265 | -2.90.619 | +8.30.143 | +3.50.515 |
| Low fence | -5.20.327 | -3.20.554 | -0.70.895 | -9.80.078 | 43.7%167 | +0.10.977 | -2.50.695 | -12.80.029 | -1.60.775 | -6.30.239 |
| Single wall | -5.40.316 | -3.30.537 | -0.90.874 | -10.00.075 | -0.10.977 | 43.6%163 | -2.70.678 | -12.90.028 | -1.70.755 | -6.40.230 |
| Fence and open | -2.70.672 | -0.70.918 | +1.80.784 | -7.30.265 | +2.50.695 | +2.70.678 | 46.2%93 | -10.20.130 | +1.00.883 | -3.80.554 |
| Open | +7.60.184 | +9.60.096 | +12.10.043 | +2.90.619 | +12.80.029 | +12.90.028 | +10.20.130 | 56.5%131 | +11.20.058 | +6.50.256 |
| Rectangle | -3.60.499 | -1.60.768 | +0.80.882 | -8.30.143 | +1.60.775 | +1.70.755 | -1.00.883 | -11.20.058 | 45.3%159 | -4.70.383 |
| Octagon | +1.10.836 | +3.10.555 | +5.60.309 | -3.50.515 | +6.30.239 | +6.40.230 | +3.80.554 | -6.50.256 | +4.70.383 | 50.0%184 |
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 counted1,281
Win rate48.4%
Widest swing9.9 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Goh's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Open | 58.3% | +9.9 | 0.043 | 96 | |
| Breakable half fence | 51.4% | +3.0 | 0.515 | 111 | |
| Octagon | 50.0% | +1.6 | 0.683 | 144 | |
| Fence and open | 49.3% | +0.9 | 0.868 | 75 · | |
| Breakable full fence | 49.2% | +0.8 | 0.838 | 132 | |
| Full fence | 47.6% | -0.8 | 0.846 | 149 | |
| Single wall | 45.9% | -2.5 | 0.537 | 133 | |
| Rectangle | 44.8% | -3.6 | 0.375 | 134 | |
| Half fence | 43.0% | -5.4 | 0.210 | 121 | |
| Low fence | 40.9% | -7.5 | 0.069 | 132 |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Goh's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 9.62 on 9 df, p 0.382
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 47.6%149 | -1.60.790 | +4.70.443 | -3.70.555 | +6.70.256 | +1.80.764 | -1.70.812 | -10.70.102 | +2.90.628 | -2.40.688 |
| Breakable full fence | +1.60.790 | 49.2%132 | +6.30.318 | -2.10.743 | +8.30.174 | +3.40.582 | -0.10.990 | -9.10.174 | +4.50.466 | -0.80.900 |
| Half fence | -4.70.443 | -6.30.318 | 43.0%121 | -8.40.202 | +2.10.739 | -2.90.644 | -6.30.385 | -15.30.025 | -1.80.772 | -7.00.254 |
| Breakable half fence | +3.70.555 | +2.10.743 | +8.40.202 | 51.4%111 | +10.40.104 | +5.50.393 | +2.00.787 | -7.00.314 | +6.60.305 | +1.40.831 |
| Low fence | -6.70.256 | -8.30.174 | -2.10.739 | -10.40.104 | 40.9%132 | -5.00.416 | -8.40.240 | -17.40.009 | -3.90.524 | -9.10.130 |
| Single wall | -1.80.764 | -3.40.582 | +2.90.644 | -5.50.393 | +5.00.416 | 45.9%133 | -3.50.630 | -12.50.063 | +1.10.858 | -4.10.491 |
| Fence and open | +1.70.812 | +0.10.990 | +6.30.385 | -2.00.787 | +8.40.240 | +3.50.630 | 49.3%75 | -9.00.241 | +4.50.526 | -0.70.925 |
| Open | +10.70.102 | +9.10.174 | +15.30.025 | +7.00.314 | +17.40.009 | +12.50.063 | +9.00.241 | 58.3%96 | +13.60.043 | +8.30.205 |
| Rectangle | -2.90.628 | -4.50.466 | +1.80.772 | -6.60.305 | +3.90.524 | -1.10.858 | -4.50.526 | -13.60.043 | 44.8%134 | -5.20.383 |
| Octagon | +2.40.688 | +0.80.900 | +7.00.254 | -1.40.831 | +9.10.130 | +4.10.491 | +0.70.925 | -8.30.205 | +5.20.383 | 50.0%144 |
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 counted352
Win rate48.0%
Widest swing-14.7 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Goh's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Breakable half fence | 59.1% | +11.1 | 0.116 | 44 · | |
| Low fence | 54.3% | +6.3 | 0.434 | 35 · | |
| Full fence | 54.0% | +6.0 | 0.437 | 37 · | |
| Open | 51.4% | +3.4 | 0.670 | 35 · | |
| Half fence | 50.0% | +2.0 | 0.813 | 32 · | |
| Octagon | 50.0% | +2.0 | 0.789 | 40 · | |
| Rectangle | 48.0% | -0.0 | 0.999 | 25 · | |
| Breakable full fence | 40.0% | -8.0 | 0.249 | 45 · | |
| Fence and open | 33.3% | -14.7 | 0.201 | 18 · | |
| Single wall | 33.3% | -14.7 | 0.092 | 30 · |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Goh's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 8.81 on 9 df, p 0.455
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 54.0%37 | +14.10.204 | +4.00.737 | -5.00.649 | -0.20.984 | +20.70.090 | +20.70.149 | +2.60.824 | +6.00.640 | +4.00.722 |
| Breakable full fence | -14.10.204 | 40.0%45 | -10.00.384 | -19.10.072 | -14.30.204 | +6.70.559 | +6.70.623 | -11.40.308 | -8.00.517 | -10.00.355 |
| Half fence | -4.00.737 | +10.00.384 | 50.0%32 | -9.10.431 | -4.30.726 | +16.70.184 | +16.70.254 | -1.40.907 | +2.00.881 | +0.01.000 |
| Breakable half fence | +5.00.649 | +19.10.072 | +9.10.431 | 59.1%44 | +4.80.668 | +25.80.030 | +25.80.065 | +7.70.496 | +11.10.373 | +9.10.403 |
| Low fence | +0.20.984 | +14.30.204 | +4.30.726 | -4.80.668 | 54.3%35 | +21.00.090 | +21.00.148 | +2.90.811 | +6.30.631 | +4.30.711 |
| Single wall | -20.70.090 | -6.70.559 | -16.70.184 | -25.80.030 | -21.00.090 | 33.3%30 | +0.01.000 | -18.10.142 | -14.70.269 | -16.70.163 |
| Fence and open | -20.70.149 | -6.70.623 | -16.70.254 | -25.80.065 | -21.00.148 | -0.01.000 | 33.3%18 | -18.10.210 | -14.70.336 | -16.70.238 |
| Open | -2.60.824 | +11.40.308 | +1.40.907 | -7.70.496 | -2.90.811 | +18.10.142 | +18.10.210 | 51.4%35 | +3.40.793 | +1.40.902 |
| Rectangle | -6.00.640 | +8.00.517 | -2.00.881 | -11.10.373 | -6.30.631 | +14.70.269 | +14.70.336 | -3.40.793 | 48.0%25 | -2.00.875 |
| Octagon | -4.00.722 | +10.00.355 | -0.01.000 | -9.10.403 | -4.30.711 | +16.70.163 | +16.70.238 | -1.40.902 | +2.00.875 | 50.0%40 |
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.