Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Goh vs Shun
Matches counted1,983
Win rate50.7%
Widest swing-7.7 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 |
|---|---|---|---|---|---|
| Rectangle | 54.7% | +4.0 | 0.226 | 201 | |
| Breakable full fence | 54.6% | +3.9 | 0.221 | 218 | |
| Open | 52.1% | +1.4 | 0.699 | 165 | |
| Full fence | 50.8% | +0.1 | 0.974 | 189 | |
| Breakable half fence | 50.2% | -0.4 | 0.896 | 203 | |
| Half fence | 50.0% | -0.7 | 0.844 | 190 | |
| Octagon | 49.5% | -1.2 | 0.723 | 208 | |
| Single wall | 49.5% | -1.2 | 0.727 | 186 | |
| Low fence | 48.6% | -2.1 | 0.520 | 218 | |
| Fence and open | 43.0% | -7.7 | 0.080 | 121 |
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 6.30 on 9 df, p 0.710
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 50.8%189 | -3.80.445 | +0.80.877 | +0.50.914 | +2.20.662 | +1.30.797 | +7.80.179 | -1.30.803 | -3.90.437 | +1.30.800 |
| Breakable full fence | +3.80.445 | 54.6%218 | +4.60.355 | +4.30.373 | +6.00.213 | +5.10.304 | +11.60.040 | +2.50.632 | -0.10.977 | +5.10.295 |
| Half fence | -0.80.877 | -4.60.355 | 50.0%190 | -0.20.961 | +1.40.782 | +0.50.917 | +7.00.226 | -2.10.690 | -4.70.350 | +0.50.924 |
| Breakable half fence | -0.50.914 | -4.30.373 | +0.20.961 | 50.2%203 | +1.60.739 | +0.80.877 | +7.30.205 | -1.90.720 | -4.50.367 | +0.70.883 |
| Low fence | -2.20.662 | -6.00.213 | -1.40.782 | -1.60.739 | 48.6%218 | -0.80.867 | +5.60.318 | -3.50.498 | -6.10.212 | -0.90.853 |
| Single wall | -1.30.797 | -5.10.304 | -0.50.917 | -0.80.877 | +0.80.867 | 49.5%186 | +6.50.266 | -2.70.619 | -5.30.300 | -0.10.991 |
| Fence and open | -7.80.179 | -11.60.040 | -7.00.226 | -7.30.205 | -5.60.318 | -6.50.266 | 43.0%121 | -9.10.126 | -11.80.041 | -6.50.252 |
| Open | +1.30.803 | -2.50.632 | +2.10.690 | +1.90.720 | +3.50.498 | +2.70.619 | +9.10.126 | 52.1%165 | -2.60.619 | +2.60.618 |
| Rectangle | +3.90.437 | +0.10.977 | +4.70.350 | +4.50.367 | +6.10.212 | +5.30.300 | +11.80.041 | +2.60.619 | 54.7%201 | +5.20.292 |
| Octagon | -1.30.800 | -5.10.295 | -0.50.924 | -0.70.883 | +0.90.853 | +0.10.991 | +6.50.252 | -2.60.618 | -5.20.292 | 49.5%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 counted1,666
Win rate49.5%
Widest swing-5.8 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 |
|---|---|---|---|---|---|
| Rectangle | 53.7% | +4.2 | 0.241 | 175 | |
| Breakable full fence | 52.9% | +3.4 | 0.350 | 174 | |
| Open | 50.8% | +1.2 | 0.767 | 130 | |
| Octagon | 50.5% | +1.0 | 0.768 | 184 | |
| Breakable half fence | 50.3% | +0.8 | 0.829 | 183 | |
| Single wall | 49.4% | -0.2 | 0.965 | 154 | |
| Full fence | 48.3% | -1.2 | 0.759 | 149 | |
| Half fence | 48.2% | -1.4 | 0.716 | 164 | |
| Low fence | 44.5% | -5.0 | 0.164 | 173 | |
| Fence and open | 43.7% | -5.8 | 0.222 | 103 |
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 5.56 on 9 df, p 0.783
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 48.3%149 | -4.50.415 | +0.10.979 | -1.90.724 | +3.80.494 | -1.00.858 | +4.60.468 | -2.50.683 | -5.40.333 | -2.20.687 |
| Breakable full fence | +4.50.415 | 52.9%174 | +4.70.387 | +2.60.623 | +8.40.119 | +3.50.524 | +9.20.140 | +2.10.716 | -0.80.875 | +2.30.659 |
| Half fence | -0.10.979 | -4.70.387 | 48.2%164 | -2.10.696 | +3.70.500 | -1.20.833 | +4.50.475 | -2.60.658 | -5.50.308 | -2.40.659 |
| Breakable half fence | +1.90.724 | -2.60.623 | +2.10.696 | 50.3%183 | +5.80.276 | +0.90.866 | +6.60.285 | -0.50.931 | -3.40.515 | -0.30.959 |
| Low fence | -3.80.494 | -8.40.119 | -3.70.500 | -5.80.276 | 44.5%173 | -4.80.381 | +0.80.895 | -6.30.280 | -9.20.086 | -6.00.254 |
| Single wall | +1.00.858 | -3.50.524 | +1.20.833 | -0.90.866 | +4.80.381 | 49.4%154 | +5.70.373 | -1.40.812 | -4.40.429 | -1.20.827 |
| Fence and open | -4.60.468 | -9.20.140 | -4.50.475 | -6.60.285 | -0.80.895 | -5.70.373 | 43.7%103 | -7.10.283 | -10.00.106 | -6.80.265 |
| Open | +2.50.683 | -2.10.716 | +2.60.658 | +0.50.931 | +6.30.280 | +1.40.812 | +7.10.283 | 50.8%130 | -2.90.611 | +0.20.969 |
| Rectangle | +5.40.333 | +0.80.875 | +5.50.308 | +3.40.515 | +9.20.086 | +4.40.429 | +10.00.106 | +2.90.611 | 53.7%175 | +3.20.548 |
| Octagon | +2.20.687 | -2.30.659 | +2.40.659 | +0.30.959 | +6.00.254 | +1.20.827 | +6.80.265 | -0.20.969 | -3.20.548 | 50.5%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 counted317
Win rate56.8%
Widest swing-17.9 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 |
|---|---|---|---|---|---|
| Low fence | 64.4% | +7.7 | 0.263 | 45 · | |
| Half fence | 61.5% | +4.8 | 0.609 | 26 · | |
| Rectangle | 61.5% | +4.8 | 0.609 | 26 · | |
| Breakable full fence | 61.4% | +4.6 | 0.509 | 44 · | |
| Full fence | 60.0% | +3.2 | 0.660 | 40 · | |
| Open | 57.1% | +0.4 | 0.964 | 35 · | |
| Breakable half fence | 50.0% | -6.8 | 0.527 | 20 · | |
| Single wall | 50.0% | -6.8 | 0.414 | 32 · | |
| Octagon | 41.7% | -15.1 | 0.120 | 24 · | |
| Fence and open | 38.9% | -17.9 | 0.115 | 18 · |
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 7.63 on 9 df, p 0.571
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 60.0%40 | -1.40.898 | -1.50.901 | +10.00.461 | -4.40.673 | +10.00.396 | +21.10.136 | +2.90.802 | -1.50.901 | +18.30.155 |
| Breakable full fence | +1.40.898 | 61.4%44 | -0.20.988 | +11.40.394 | -3.10.764 | +11.40.324 | +22.50.107 | +4.20.704 | -0.20.988 | +19.70.119 |
| Half fence | +1.50.901 | +0.20.988 | 61.5%26 | +11.50.434 | -2.90.807 | +11.50.380 | +22.60.139 | +4.40.730 | +0.01.000 | +19.90.160 |
| Breakable half fence | -10.00.461 | -11.40.394 | -11.50.434 | 50.0%20 | -14.40.273 | +0.01.000 | +11.10.492 | -7.10.609 | -11.50.434 | +8.30.580 |
| Low fence | +4.40.673 | +3.10.764 | +2.90.807 | +14.40.273 | 64.4%45 | +14.40.205 | +25.60.064 | +7.30.506 | +2.90.807 | +22.80.069 |
| Single wall | -10.00.396 | -11.40.324 | -11.50.380 | -0.01.000 | -14.40.205 | 50.0%32 | +11.10.449 | -7.10.558 | -11.50.380 | +8.30.536 |
| Fence and open | -21.10.136 | -22.50.107 | -22.60.139 | -11.10.492 | -25.60.064 | -11.10.449 | 38.9%18 | -18.20.208 | -22.60.139 | -2.80.856 |
| Open | -2.90.802 | -4.20.704 | -4.40.730 | +7.10.609 | -7.30.506 | +7.10.558 | +18.20.208 | 57.1%35 | -4.40.730 | +15.50.243 |
| Rectangle | +1.50.901 | +0.20.988 | -0.01.000 | +11.50.434 | -2.90.807 | +11.50.380 | +22.60.139 | +4.40.730 | 61.5%26 | +19.90.160 |
| Octagon | -18.30.155 | -19.70.119 | -19.90.160 | -8.30.580 | -22.80.069 | -8.30.536 | +2.80.856 | -15.50.243 | -19.90.160 | 41.7%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.