Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Goh vs Lion
Matches counted2,243
Win rate46.8%
Widest swing5.7 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 full fence | 52.4% | +5.7 | 0.072 | 227 | |
| Half fence | 49.8% | +3.0 | 0.337 | 227 | |
| Rectangle | 48.2% | +1.4 | 0.679 | 193 | |
| Low fence | 47.8% | +1.0 | 0.740 | 228 | |
| Full fence | 47.4% | +0.6 | 0.847 | 245 | |
| Single wall | 45.4% | -1.4 | 0.665 | 216 | |
| Fence and open | 45.2% | -1.6 | 0.704 | 135 | |
| Breakable half fence | 44.5% | -2.2 | 0.466 | 238 | |
| Octagon | 43.5% | -3.2 | 0.314 | 216 | |
| Open | 43.5% | -3.3 | 0.319 | 207 |
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 6.62 on 9 df, p 0.677
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 47.4%245 | -5.10.270 | -2.40.597 | +2.80.536 | -0.50.920 | +2.00.671 | +2.20.686 | +3.90.411 | -0.80.861 | +3.80.410 |
| Breakable full fence | +5.10.270 | 52.4%227 | +2.60.573 | +7.90.089 | +4.60.325 | +7.00.138 | +7.20.183 | +8.90.063 | +4.20.387 | +8.90.061 |
| Half fence | +2.40.597 | -2.60.573 | 49.8%227 | +5.20.258 | +2.00.674 | +4.40.353 | +4.60.397 | +6.30.189 | +1.60.745 | +6.30.187 |
| Breakable half fence | -2.80.536 | -7.90.089 | -5.20.258 | 44.5%238 | -3.30.479 | -0.80.859 | -0.70.904 | +1.10.822 | -3.60.450 | +1.00.827 |
| Low fence | +0.50.920 | -4.60.325 | -2.00.674 | +3.30.479 | 47.8%228 | +2.40.607 | +2.60.629 | +4.30.365 | -0.40.938 | +4.30.365 |
| Single wall | -2.00.671 | -7.00.138 | -4.40.353 | +0.80.859 | -2.40.607 | 45.4%216 | +0.20.973 | +1.90.695 | -2.80.569 | +1.90.699 |
| Fence and open | -2.20.686 | -7.20.183 | -4.60.397 | +0.70.904 | -2.60.629 | -0.20.973 | 45.2%135 | +1.70.756 | -3.00.592 | +1.70.760 |
| Open | -3.90.411 | -8.90.063 | -6.30.189 | -1.10.822 | -4.30.365 | -1.90.695 | -1.70.756 | 43.5%207 | -4.70.345 | -0.00.993 |
| Rectangle | +0.80.861 | -4.20.387 | -1.60.745 | +3.60.450 | +0.40.938 | +2.80.569 | +3.00.592 | +4.70.345 | 48.2%193 | +4.70.344 |
| Octagon | -3.80.410 | -8.90.061 | -6.30.187 | -1.00.827 | -4.30.365 | -1.90.699 | -1.70.760 | +0.00.993 | -4.70.344 | 43.5%216 |
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 counted1,944
Win rate46.4%
Widest swing6.8 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 |
|---|---|---|---|---|---|
| Breakable full fence | 53.2% | +6.8 | 0.049 | 190 | |
| Half fence | 49.2% | +2.8 | 0.399 | 197 | |
| Rectangle | 48.8% | +2.4 | 0.528 | 162 | |
| Low fence | 47.7% | +1.3 | 0.696 | 197 | |
| Single wall | 46.5% | +0.1 | 0.971 | 187 | |
| Full fence | 46.5% | +0.1 | 0.972 | 215 | |
| Open | 44.0% | -2.4 | 0.488 | 182 | |
| Breakable half fence | 43.3% | -3.1 | 0.346 | 210 | |
| Octagon | 43.1% | -3.2 | 0.334 | 197 | |
| Fence and open | 43.0% | -3.4 | 0.467 | 107 |
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 7.15 on 9 df, p 0.621
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 46.5%215 | -6.70.182 | -2.70.580 | +3.20.510 | -1.20.807 | -0.00.998 | +3.50.550 | +2.50.610 | -2.30.664 | +3.40.493 |
| Breakable full fence | +6.70.182 | 53.2%190 | +3.90.441 | +9.80.050 | +5.40.284 | +6.60.198 | +10.20.092 | +9.20.076 | +4.40.411 | +10.00.049 |
| Half fence | +2.70.580 | -3.90.441 | 49.2%197 | +5.90.232 | +1.50.762 | +2.70.595 | +6.20.297 | +5.30.303 | +0.50.929 | +6.10.225 |
| Breakable half fence | -3.20.510 | -9.80.050 | -5.90.232 | 43.3%210 | -4.40.375 | -3.20.523 | +0.30.954 | -0.60.901 | -5.40.297 | +0.20.970 |
| Low fence | +1.20.807 | -5.40.284 | -1.50.762 | +4.40.375 | 47.7%197 | +1.20.815 | +4.70.430 | +3.80.463 | -1.10.843 | +4.60.362 |
| Single wall | +0.00.998 | -6.60.198 | -2.70.595 | +3.20.523 | -1.20.815 | 46.5%187 | +3.50.558 | +2.60.620 | -2.20.676 | +3.40.506 |
| Fence and open | -3.50.550 | -10.20.092 | -6.20.297 | -0.30.954 | -4.70.430 | -3.50.558 | 43.0%107 | -1.00.873 | -5.80.353 | -0.20.979 |
| Open | -2.50.610 | -9.20.076 | -5.30.303 | +0.60.901 | -3.80.463 | -2.60.620 | +1.00.873 | 44.0%182 | -4.80.372 | +0.80.874 |
| Rectangle | +2.30.664 | -4.40.411 | -0.50.929 | +5.40.297 | +1.10.843 | +2.20.676 | +5.80.353 | +4.80.372 | 48.8%162 | +5.60.288 |
| Octagon | -3.40.493 | -10.00.049 | -6.10.225 | -0.20.970 | -4.60.362 | -3.40.506 | +0.20.979 | -0.80.874 | -5.60.288 | 43.1%197 |
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 counted299
Win rate49.2%
Widest swing-11.2 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 |
|---|---|---|---|---|---|
| Breakable half fence | 53.6% | +4.4 | 0.624 | 28 · | |
| Fence and open | 53.6% | +4.4 | 0.624 | 28 · | |
| Full fence | 53.3% | +4.2 | 0.630 | 30 · | |
| Half fence | 53.3% | +4.2 | 0.630 | 30 · | |
| Breakable full fence | 48.6% | -0.5 | 0.947 | 37 · | |
| Low fence | 48.4% | -0.8 | 0.927 | 31 · | |
| Octagon | 47.4% | -1.8 | 0.871 | 19 · | |
| Rectangle | 45.2% | -4.0 | 0.638 | 31 · | |
| Open | 40.0% | -9.2 | 0.338 | 25 · | |
| Single wall | 37.9% | -11.2 | 0.203 | 29 · |
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 3.30 on 9 df, p 0.951
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 53.3%30 | +4.70.703 | +0.01.000 | -0.20.986 | +4.90.699 | +15.40.235 | -0.20.986 | +13.30.324 | +8.20.523 | +6.00.684 |
| Breakable full fence | -4.70.703 | 48.6%37 | -4.70.703 | -4.90.694 | +0.30.983 | +10.70.384 | -4.90.694 | +8.70.502 | +3.50.774 | +1.30.928 |
| Half fence | -0.01.000 | +4.70.703 | 53.3%30 | -0.20.986 | +4.90.699 | +15.40.235 | -0.20.986 | +13.30.324 | +8.20.523 | +6.00.684 |
| Breakable half fence | +0.20.986 | +4.90.694 | +0.20.986 | 53.6%28 | +5.20.691 | +15.60.236 | +0.01.000 | +13.60.323 | +8.40.519 | +6.20.676 |
| Low fence | -4.90.699 | -0.30.983 | -4.90.699 | -5.20.691 | 48.4%31 | +10.50.414 | -5.20.691 | +8.40.530 | +3.20.799 | +1.00.944 |
| Single wall | -15.40.235 | -10.70.384 | -15.40.235 | -15.60.236 | -10.50.414 | 37.9%29 | -15.60.236 | -2.10.876 | -7.20.570 | -9.40.517 |
| Fence and open | +0.20.986 | +4.90.694 | +0.20.986 | -0.01.000 | +5.20.691 | +15.60.236 | 53.6%28 | +13.60.323 | +8.40.519 | +6.20.676 |
| Open | -13.30.324 | -8.70.502 | -13.30.324 | -13.60.323 | -8.40.530 | +2.10.876 | -13.60.323 | 40.0%25 | -5.20.698 | -7.40.625 |
| Rectangle | -8.20.523 | -3.50.774 | -8.20.523 | -8.40.519 | -3.20.799 | +7.20.570 | -8.40.519 | +5.20.698 | 45.2%31 | -2.20.879 |
| Octagon | -6.00.684 | -1.30.928 | -6.00.684 | -6.20.676 | -1.00.944 | +9.40.517 | -6.20.676 | +7.40.625 | +2.20.879 | 47.4%19 |
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.