Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Goh vs Lau
Matches counted2,667
Win rate48.0%
Widest swing6.3 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 |
|---|---|---|---|---|---|
| Single wall | 54.3% | +6.3 | 0.035 | 256 | |
| Breakable half fence | 51.9% | +3.9 | 0.143 | 312 | |
| Open | 50.5% | +2.5 | 0.379 | 273 | |
| Full fence | 48.9% | +0.8 | 0.772 | 266 | |
| Half fence | 47.8% | -0.3 | 0.926 | 268 | |
| Low fence | 46.5% | -1.5 | 0.632 | 230 | |
| Octagon | 45.8% | -2.2 | 0.461 | 251 | |
| Fence and open | 44.5% | -3.5 | 0.399 | 137 | |
| Rectangle | 44.0% | -4.0 | 0.158 | 275 | |
| Breakable full fence | 42.7% | -5.3 | 0.062 | 274 |
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 12.97 on 9 df, p 0.164
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 48.9%266 | +6.20.150 | +1.10.797 | -3.00.465 | +2.40.601 | -5.40.215 | +4.30.408 | -1.70.697 | +4.90.256 | +3.00.487 |
| Breakable full fence | -6.20.150 | 42.7%274 | -5.10.237 | -9.20.026 | -3.80.390 | -11.60.008 | -1.80.725 | -7.80.066 | -1.30.759 | -3.10.473 |
| Half fence | -1.10.797 | +5.10.237 | 47.8%268 | -4.20.318 | +1.20.782 | -6.50.135 | +3.20.537 | -2.80.517 | +3.80.379 | +1.90.657 |
| Breakable half fence | +3.00.465 | +9.20.026 | +4.20.318 | 51.9%312 | +5.40.214 | -2.40.573 | +7.40.149 | +1.40.740 | +7.90.055 | +6.10.150 |
| Low fence | -2.40.601 | +3.80.390 | -1.20.782 | -5.40.214 | 46.5%230 | -7.80.087 | +2.00.710 | -4.00.368 | +2.50.571 | +0.70.877 |
| Single wall | +5.40.215 | +11.60.008 | +6.50.135 | +2.40.573 | +7.80.087 | 54.3%256 | +9.80.065 | +3.80.388 | +10.30.018 | +8.50.056 |
| Fence and open | -4.30.408 | +1.80.725 | -3.20.537 | -7.40.149 | -2.00.710 | -9.80.065 | 44.5%137 | -6.00.250 | +0.50.919 | -1.30.807 |
| Open | +1.70.697 | +7.80.066 | +2.80.517 | -1.40.740 | +4.00.368 | -3.80.388 | +6.00.250 | 50.5%273 | +6.50.125 | +4.70.279 |
| Rectangle | -4.90.256 | +1.30.759 | -3.80.379 | -7.90.055 | -2.50.571 | -10.30.018 | -0.50.919 | -6.50.125 | 44.0%275 | -1.80.676 |
| Octagon | -3.00.487 | +3.10.473 | -1.90.657 | -6.10.150 | -0.70.877 | -8.50.056 | +1.30.807 | -4.70.279 | +1.80.676 | 45.8%251 |
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 counted2,215
Win rate48.9%
Widest swing-5.6 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 | 54.2% | +5.3 | 0.066 | 264 | |
| Single wall | 53.6% | +4.8 | 0.134 | 220 | |
| Full fence | 50.5% | +1.6 | 0.619 | 212 | |
| Open | 49.3% | +0.5 | 0.880 | 223 | |
| Half fence | 49.3% | +0.5 | 0.882 | 221 | |
| Octagon | 48.1% | -0.8 | 0.812 | 206 | |
| Low fence | 47.1% | -1.8 | 0.613 | 189 | |
| Rectangle | 44.8% | -4.1 | 0.193 | 230 | |
| Fence and open | 44.0% | -4.9 | 0.280 | 116 | |
| Breakable full fence | 43.2% | -5.6 | 0.078 | 222 |
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 10.97 on 9 df, p 0.278
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 50.5%212 | +7.20.131 | +1.10.811 | -3.70.422 | +3.40.499 | -3.20.510 | +6.50.260 | +1.10.811 | +5.70.231 | +2.40.622 |
| Breakable full fence | -7.20.131 | 43.2%222 | -6.10.200 | -10.90.016 | -3.90.435 | -10.40.029 | -0.70.899 | -6.10.198 | -1.50.742 | -4.80.318 |
| Half fence | -1.10.811 | +6.10.200 | 49.3%221 | -4.80.287 | +2.20.652 | -4.30.365 | +5.30.350 | -0.00.999 | +4.50.334 | +1.30.794 |
| Breakable half fence | +3.70.422 | +10.90.016 | +4.80.287 | 54.2%264 | +7.10.137 | +0.50.907 | +10.20.067 | +4.80.287 | +9.40.037 | +6.10.189 |
| Low fence | -3.40.499 | +3.90.435 | -2.20.652 | -7.10.137 | 47.1%189 | -6.50.187 | +3.10.595 | -2.20.651 | +2.30.637 | -1.00.847 |
| Single wall | +3.20.510 | +10.40.029 | +4.30.365 | -0.50.907 | +6.50.187 | 53.6%220 | +9.70.092 | +4.30.364 | +8.90.060 | +5.60.250 |
| Fence and open | -6.50.260 | +0.70.899 | -5.30.350 | -10.20.067 | -3.10.595 | -9.70.092 | 44.0%116 | -5.40.348 | -0.80.885 | -4.10.480 |
| Open | -1.10.811 | +6.10.198 | +0.00.999 | -4.80.287 | +2.20.651 | -4.30.364 | +5.40.348 | 49.3%223 | +4.50.333 | +1.30.793 |
| Rectangle | -5.70.231 | +1.50.742 | -4.50.334 | -9.40.037 | -2.30.637 | -8.90.060 | +0.80.885 | -4.50.333 | 44.8%230 | -3.30.493 |
| Octagon | -2.40.622 | +4.80.318 | -1.30.794 | -6.10.189 | +1.00.847 | -5.60.250 | +4.10.480 | -1.30.793 | +3.30.493 | 48.1%206 |
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 counted452
Win rate44.0%
Widest swing14.3 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 |
|---|---|---|---|---|---|
| Single wall | 58.3% | +14.3 | 0.071 | 36 · | |
| Open | 56.0% | +12.0 | 0.071 | 50 · | |
| Fence and open | 47.6% | +3.6 | 0.734 | 21 · | |
| Low fence | 43.9% | -0.1 | 0.987 | 41 · | |
| Full fence | 42.6% | -1.4 | 0.821 | 54 · | |
| Half fence | 40.4% | -3.6 | 0.599 | 47 · | |
| Breakable full fence | 40.4% | -3.6 | 0.574 | 52 · | |
| Rectangle | 40.0% | -4.0 | 0.566 | 45 · | |
| Breakable half fence | 39.6% | -4.5 | 0.512 | 48 · | |
| Octagon | 35.6% | -8.5 | 0.228 | 45 · |
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 8.57 on 9 df, p 0.477
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 42.6%54 | +2.20.818 | +2.20.826 | +3.00.758 | -1.30.898 | -15.70.143 | -5.00.694 | -13.40.172 | +2.60.794 | +7.00.476 |
| Breakable full fence | -2.20.818 | 40.4%52 | -0.10.997 | +0.80.935 | -3.50.733 | -17.90.097 | -7.20.571 | -15.60.115 | +0.40.969 | +4.80.625 |
| Half fence | -2.20.826 | +0.10.997 | 40.4%47 | +0.80.933 | -3.50.742 | -17.90.106 | -7.20.579 | -15.60.125 | +0.40.967 | +4.90.631 |
| Breakable half fence | -3.00.758 | -0.80.935 | -0.80.933 | 39.6%48 | -4.30.680 | -18.80.089 | -8.00.534 | -16.40.104 | -0.40.967 | +4.00.689 |
| Low fence | +1.30.898 | +3.50.733 | +3.50.742 | +4.30.680 | 43.9%41 | -14.40.206 | -3.70.781 | -12.10.251 | +3.90.714 | +8.30.429 |
| Single wall | +15.70.143 | +17.90.097 | +17.90.106 | +18.80.089 | +14.40.206 | 58.3%36 | +10.70.433 | +2.30.829 | +18.30.101 | +22.80.041 |
| Fence and open | +5.00.694 | +7.20.571 | +7.20.579 | +8.00.534 | +3.70.781 | -10.70.433 | 47.6%21 | -8.40.518 | +7.60.560 | +12.10.350 |
| Open | +13.40.172 | +15.60.115 | +15.60.125 | +16.40.104 | +12.10.251 | -2.30.829 | +8.40.518 | 56.0%50 | +16.00.119 | +20.40.046 |
| Rectangle | -2.60.794 | -0.40.969 | -0.40.967 | +0.40.967 | -3.90.714 | -18.30.101 | -7.60.560 | -16.00.119 | 40.0%45 | +4.40.664 |
| Octagon | -7.00.476 | -4.80.625 | -4.90.631 | -4.00.689 | -8.30.429 | -22.80.041 | -12.10.350 | -20.40.046 | -4.40.664 | 35.6%45 |
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.