Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Goh vs Kage
Matches counted2,535
Win rate48.1%
Widest swing-4.9 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 |
|---|---|---|---|---|---|
| Breakable full fence | 51.9% | +3.8 | 0.217 | 239 | |
| Rectangle | 51.7% | +3.6 | 0.188 | 288 | |
| Open | 51.3% | +3.2 | 0.265 | 267 | |
| Single wall | 50.0% | +1.9 | 0.513 | 262 | |
| Fence and open | 49.6% | +1.5 | 0.732 | 123 | |
| Full fence | 46.4% | -1.7 | 0.603 | 224 | |
| Low fence | 45.6% | -2.5 | 0.403 | 248 | |
| Octagon | 44.8% | -3.3 | 0.255 | 270 | |
| Half fence | 44.1% | -4.0 | 0.187 | 245 | |
| Breakable half fence | 43.2% | -4.9 | 0.103 | 250 |
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 10.47 on 9 df, p 0.313
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 46.4%224 | -5.50.241 | +2.40.610 | +3.20.480 | +0.90.851 | -3.60.432 | -3.20.572 | -4.90.281 | -5.30.233 | +1.60.720 |
| Breakable full fence | +5.50.241 | 51.9%239 | +7.80.086 | +8.70.055 | +6.30.163 | +1.90.674 | +2.30.680 | +0.60.898 | +0.10.973 | +7.10.111 |
| Half fence | -2.40.610 | -7.80.086 | 44.1%245 | +0.90.843 | -1.50.741 | -5.90.182 | -5.50.317 | -7.20.102 | -7.70.078 | -0.70.867 |
| Breakable half fence | -3.20.480 | -8.70.055 | -0.90.843 | 43.2%250 | -2.40.595 | -6.80.123 | -6.40.244 | -8.10.065 | -8.50.048 | -1.60.711 |
| Low fence | -0.90.851 | -6.30.163 | +1.50.741 | +2.40.595 | 45.6%248 | -4.40.316 | -4.00.464 | -5.80.192 | -6.20.154 | +0.80.864 |
| Single wall | +3.60.432 | -1.90.674 | +5.90.182 | +6.80.123 | +4.40.316 | 50.0%262 | +0.40.941 | -1.30.763 | -1.70.684 | +5.20.231 |
| Fence and open | +3.20.572 | -2.30.680 | +5.50.317 | +6.40.244 | +4.00.464 | -0.40.941 | 49.6%123 | -1.70.753 | -2.10.691 | +4.80.378 |
| Open | +4.90.281 | -0.60.898 | +7.20.102 | +8.10.065 | +5.80.192 | +1.30.763 | +1.70.753 | 51.3%267 | -0.40.920 | +6.50.132 |
| Rectangle | +5.30.233 | -0.10.973 | +7.70.078 | +8.50.048 | +6.20.154 | +1.70.684 | +2.10.691 | +0.40.920 | 51.7%288 | +6.90.102 |
| Octagon | -1.60.720 | -7.10.111 | +0.70.867 | +1.60.711 | -0.80.864 | -5.20.231 | -4.80.378 | -6.50.132 | -6.90.102 | 44.8%270 |
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 counted2,224
Win rate48.3%
Widest swing-6.2 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 |
|---|---|---|---|---|---|
| Fence and open | 53.3% | +5.0 | 0.291 | 107 | |
| Rectangle | 52.4% | +4.1 | 0.168 | 248 | |
| Breakable full fence | 51.6% | +3.3 | 0.303 | 215 | |
| Open | 51.5% | +3.2 | 0.300 | 235 | |
| Single wall | 48.6% | +0.3 | 0.921 | 216 | |
| Octagon | 47.5% | -0.8 | 0.795 | 240 | |
| Full fence | 47.2% | -1.1 | 0.750 | 197 | |
| Low fence | 46.2% | -2.1 | 0.512 | 225 | |
| Half fence | 43.2% | -5.1 | 0.110 | 220 | |
| Breakable half fence | 42.1% | -6.2 | 0.056 | 216 |
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 10.80 on 9 df, p 0.290
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 47.2%197 | -4.40.370 | +4.00.409 | +5.10.300 | +1.00.840 | -1.40.776 | -6.10.313 | -4.30.375 | -5.20.275 | -0.30.952 |
| Breakable full fence | +4.40.370 | 51.6%215 | +8.40.078 | +9.50.048 | +5.40.257 | +3.00.531 | -1.60.781 | +0.10.977 | -0.80.865 | +4.10.379 |
| Half fence | -4.00.409 | -8.40.078 | 43.2%220 | +1.10.824 | -3.00.519 | -5.40.255 | -10.10.086 | -8.30.076 | -9.20.046 | -4.30.353 |
| Breakable half fence | -5.10.300 | -9.50.048 | -1.10.824 | 42.1%216 | -4.10.387 | -6.50.176 | -11.10.059 | -9.40.047 | -10.30.027 | -5.40.250 |
| Low fence | -1.00.840 | -5.40.257 | +3.00.519 | +4.10.387 | 46.2%225 | -2.40.615 | -7.00.230 | -5.30.259 | -6.20.178 | -1.30.783 |
| Single wall | +1.40.776 | -3.00.531 | +5.40.255 | +6.50.176 | +2.40.615 | 48.6%216 | -4.70.430 | -2.90.541 | -3.80.413 | +1.10.813 |
| Fence and open | +6.10.313 | +1.60.781 | +10.10.086 | +11.10.059 | +7.00.230 | +4.70.430 | 53.3%107 | +1.80.760 | +0.80.883 | +5.80.321 |
| Open | +4.30.375 | -0.10.977 | +8.30.076 | +9.40.047 | +5.30.259 | +2.90.541 | -1.80.760 | 51.5%235 | -0.90.838 | +4.00.385 |
| Rectangle | +5.20.275 | +0.80.865 | +9.20.046 | +10.30.027 | +6.20.178 | +3.80.413 | -0.80.883 | +0.90.838 | 52.4%248 | +4.90.277 |
| Octagon | +0.30.952 | -4.10.379 | +4.30.353 | +5.40.250 | +1.30.783 | -1.10.813 | -5.80.321 | -4.00.385 | -4.90.277 | 47.5%240 |
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 counted311
Win rate46.6%
Widest swing-23.3 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 | 56.5% | +9.9 | 0.145 | 46 · | |
| Breakable full fence | 54.2% | +7.5 | 0.441 | 24 · | |
| Half fence | 52.0% | +5.4 | 0.574 | 25 · | |
| Breakable half fence | 50.0% | +3.4 | 0.676 | 34 · | |
| Open | 50.0% | +3.4 | 0.686 | 32 · | |
| Rectangle | 47.5% | +0.9 | 0.905 | 40 · | |
| Full fence | 40.7% | -5.9 | 0.521 | 27 · | |
| Low fence | 39.1% | -7.5 | 0.454 | 23 · | |
| Fence and open | 25.0% | -21.6 | 0.075 | 16 · | |
| Octagon | 23.3% | -23.3 | 0.007 | 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 13.29 on 9 df, p 0.150
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 40.7%27 | -13.40.338 | -11.30.416 | -9.30.471 | +1.60.908 | -15.80.193 | +15.70.295 | -9.30.477 | -6.80.585 | +17.40.158 |
| Breakable full fence | +13.40.338 | 54.2%24 | +2.20.879 | +4.20.754 | +15.00.302 | -2.40.851 | +29.20.068 | +4.20.757 | +6.70.606 | +30.80.020 |
| Half fence | +11.30.416 | -2.20.879 | 52.0%25 | +2.00.879 | +12.90.371 | -4.50.715 | +27.00.087 | +2.00.881 | +4.50.724 | +28.70.028 |
| Breakable half fence | +9.30.471 | -4.20.754 | -2.00.879 | 50.0%34 | +10.90.419 | -6.50.563 | +25.00.095 | +0.01.000 | +2.50.830 | +26.70.028 |
| Low fence | -1.60.908 | -15.00.302 | -12.90.371 | -10.90.419 | 39.1%23 | -17.40.173 | +14.10.357 | -10.90.425 | -8.40.520 | +15.80.214 |
| Single wall | +15.80.193 | +2.40.851 | +4.50.715 | +6.50.563 | +17.40.173 | 56.5%46 | +31.50.030 | +6.50.570 | +9.00.403 | +33.20.004 |
| Fence and open | -15.70.295 | -29.20.068 | -27.00.087 | -25.00.095 | -14.10.357 | -31.50.030 | 25.0%16 | -25.00.098 | -22.50.122 | +1.70.900 |
| Open | +9.30.477 | -4.20.757 | -2.00.881 | -0.01.000 | +10.90.425 | -6.50.570 | +25.00.098 | 50.0%32 | +2.50.833 | +26.70.030 |
| Rectangle | +6.80.585 | -6.70.606 | -4.50.724 | -2.50.830 | +8.40.520 | -9.00.403 | +22.50.122 | -2.50.833 | 47.5%40 | +24.20.038 |
| Octagon | -17.40.158 | -30.80.020 | -28.70.028 | -26.70.028 | -15.80.214 | -33.20.004 | -1.70.900 | -26.70.030 | -24.20.038 | 23.3%30 |
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.