Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Brad vs Goh
Matches counted2,193
Win rate50.9%
Widest swing-8.2 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Brad's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Half fence | 57.6% | +6.7 | 0.089 | 151 | |
| Full fence | 57.1% | +6.2 | 0.050 | 224 | |
| Single wall | 53.6% | +2.7 | 0.420 | 209 | |
| Breakable full fence | 52.9% | +1.9 | 0.539 | 227 | |
| Low fence | 51.0% | +0.1 | 0.969 | 237 | |
| Rectangle | 50.4% | -0.5 | 0.865 | 240 | |
| Open | 49.5% | -1.4 | 0.663 | 224 | |
| Fence and open | 47.5% | -3.5 | 0.437 | 118 | |
| Octagon | 47.0% | -3.9 | 0.186 | 249 | |
| Breakable half fence | 42.7% | -8.2 | 0.017 | 192 |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Brad's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 14.60 on 9 df, p 0.103
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 57.1%224 | +4.30.361 | -0.50.928 | +14.40.003 | +6.10.190 | +3.50.457 | +9.70.088 | +7.60.107 | +6.70.147 | +10.20.027 |
| Breakable full fence | -4.30.361 | 52.9%227 | -4.80.363 | +10.20.038 | +1.80.697 | -0.70.880 | +5.40.341 | +3.30.482 | +2.40.597 | +5.90.200 |
| Half fence | +0.50.928 | +4.80.363 | 57.6%151 | +14.90.006 | +6.60.206 | +4.00.448 | +10.20.098 | +8.10.125 | +7.20.165 | +10.60.039 |
| Breakable half fence | -14.40.003 | -10.20.038 | -14.90.006 | 42.7%192 | -8.30.085 | -10.90.029 | -4.80.414 | -6.80.163 | -7.70.111 | -4.30.371 |
| Low fence | -6.10.190 | -1.80.697 | -6.60.206 | +8.30.085 | 51.0%237 | -2.50.593 | +3.60.523 | +1.50.747 | +0.60.889 | +4.10.370 |
| Single wall | -3.50.457 | +0.70.880 | -4.00.448 | +10.90.029 | +2.50.593 | 53.6%209 | +6.10.287 | +4.00.401 | +3.20.502 | +6.60.159 |
| Fence and open | -9.70.088 | -5.40.341 | -10.20.098 | +4.80.414 | -3.60.523 | -6.10.287 | 47.5%118 | -2.10.712 | -3.00.599 | +0.50.933 |
| Open | -7.60.107 | -3.30.482 | -8.10.125 | +6.80.163 | -1.50.747 | -4.00.401 | +2.10.712 | 49.5%224 | -0.90.853 | +2.60.577 |
| Rectangle | -6.70.147 | -2.40.597 | -7.20.165 | +7.70.111 | -0.60.889 | -3.20.502 | +3.00.599 | +0.90.853 | 50.4%240 | +3.40.448 |
| Octagon | -10.20.027 | -5.90.200 | -10.60.039 | +4.30.371 | -4.10.370 | -6.60.159 | -0.50.933 | -2.60.577 | -3.40.448 | 47.0%249 |
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 counted2,007
Win rate50.4%
Widest swing-7.5 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Brad's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Full fence | 57.5% | +7.2 | 0.027 | 212 | |
| Half fence | 56.0% | +5.7 | 0.164 | 141 | |
| Single wall | 52.9% | +2.5 | 0.469 | 193 | |
| Breakable full fence | 51.4% | +1.0 | 0.752 | 216 | |
| Low fence | 51.1% | +0.8 | 0.811 | 221 | |
| Rectangle | 49.5% | -0.8 | 0.795 | 210 | |
| Open | 49.5% | -0.9 | 0.795 | 206 | |
| Octagon | 46.9% | -3.5 | 0.265 | 222 | |
| Fence and open | 43.0% | -7.4 | 0.116 | 107 | |
| Breakable half fence | 42.9% | -7.5 | 0.037 | 175 |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Brad's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 14.29 on 9 df, p 0.112
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 57.5%212 | +6.20.201 | +1.50.778 | +14.70.004 | +6.40.180 | +4.70.342 | +14.60.014 | +8.00.100 | +8.00.098 | +10.70.026 |
| Breakable full fence | -6.20.201 | 51.4%216 | -4.60.390 | +8.50.093 | +0.30.957 | -1.50.768 | +8.40.155 | +1.90.700 | +1.90.700 | +4.50.342 |
| Half fence | -1.50.778 | +4.60.390 | 56.0%141 | +13.20.020 | +4.90.363 | +3.20.565 | +13.00.042 | +6.50.233 | +6.50.232 | +9.20.088 |
| Breakable half fence | -14.70.004 | -8.50.093 | -13.20.020 | 42.9%175 | -8.30.102 | -10.00.055 | -0.10.982 | -6.70.194 | -6.70.192 | -4.00.428 |
| Low fence | -6.40.180 | -0.30.957 | -4.90.363 | +8.30.102 | 51.1%221 | -1.70.727 | +8.10.167 | +1.60.738 | +1.60.739 | +4.30.367 |
| Single wall | -4.70.342 | +1.50.768 | -3.20.565 | +10.00.055 | +1.70.727 | 52.9%193 | +9.90.102 | +3.30.505 | +3.30.505 | +6.00.222 |
| Fence and open | -14.60.014 | -8.40.155 | -13.00.042 | +0.10.982 | -8.10.167 | -9.90.102 | 43.0%107 | -6.50.273 | -6.50.271 | -3.90.511 |
| Open | -8.00.100 | -1.90.700 | -6.50.233 | +6.70.194 | -1.60.738 | -3.30.505 | +6.50.273 | 49.5%206 | -0.00.998 | +2.70.581 |
| Rectangle | -8.00.098 | -1.90.700 | -6.50.232 | +6.70.192 | -1.60.739 | -3.30.505 | +6.50.271 | +0.00.998 | 49.5%210 | +2.70.578 |
| Octagon | -10.70.026 | -4.50.342 | -9.20.088 | +4.00.428 | -4.30.367 | -6.00.222 | +3.90.511 | -2.70.581 | -2.70.578 | 46.9%222 |
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 counted186
Win rate57.0%
Widest swing33.9 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Brad's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Fence and open | 90.9% | +33.9 | 0.019 | 11 · | |
| Breakable full fence | 81.8% | +24.8 | 0.086 | 11 · | |
| Half fence | 80.0% | +23.0 | 0.131 | 10 · | |
| Single wall | 62.5% | +5.5 | 0.641 | 16 · | |
| Rectangle | 56.7% | -0.3 | 0.969 | 30 · | |
| Full fence | 50.0% | -7.0 | 0.613 | 12 · | |
| Low fence | 50.0% | -7.0 | 0.555 | 16 · | |
| Open | 50.0% | -7.0 | 0.529 | 18 · | |
| Octagon | 48.1% | -8.8 | 0.316 | 27 · | |
| Breakable half fence | 41.2% | -15.8 | 0.167 | 17 · |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Brad's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 13.82 on 9 df, p 0.129
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 50.0%12 | -31.80.110 | -30.00.145 | +8.80.638 | +0.01.000 | -12.50.508 | -40.90.033 | +0.01.000 | -6.70.695 | +1.90.915 |
| Breakable full fence | +31.80.110 | 81.8%11 | +1.80.916 | +40.60.034 | +31.80.093 | +19.30.280 | -9.10.534 | +31.80.087 | +25.10.138 | +33.70.057 |
| Half fence | +30.00.145 | -1.80.916 | 80.0%10 | +38.80.050 | +30.00.126 | +17.50.347 | -10.90.476 | +30.00.119 | +23.30.187 | +31.90.082 |
| Breakable half fence | -8.80.638 | -40.60.034 | -38.80.050 | 41.2%17 | -8.80.611 | -21.30.221 | -49.70.008 | -8.80.600 | -15.50.307 | -7.00.651 |
| Low fence | -0.01.000 | -31.80.093 | -30.00.126 | +8.80.611 | 50.0%16 | -12.50.476 | -40.90.027 | +0.01.000 | -6.70.665 | +1.90.907 |
| Single wall | +12.50.508 | -19.30.280 | -17.50.347 | +21.30.221 | +12.50.476 | 62.5%16 | -28.40.098 | +12.50.464 | +5.80.702 | +14.30.362 |
| Fence and open | +40.90.033 | +9.10.534 | +10.90.476 | +49.70.008 | +40.90.027 | +28.40.098 | 90.9%11 | +40.90.025 | +34.20.040 | +42.80.014 |
| Open | -0.01.000 | -31.80.087 | -30.00.119 | +8.80.600 | -0.01.000 | -12.50.464 | -40.90.025 | 50.0%18 | -6.70.654 | +1.90.903 |
| Rectangle | +6.70.695 | -25.10.138 | -23.30.187 | +15.50.307 | +6.70.665 | -5.80.702 | -34.20.040 | +6.70.654 | 56.7%30 | +8.50.520 |
| Octagon | -1.90.915 | -33.70.057 | -31.90.082 | +7.00.651 | -1.90.907 | -14.30.362 | -42.80.014 | -1.90.903 | -8.50.520 | 48.1%27 |
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.