Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Goh vs Jeffry
Matches counted2,426
Win rate49.4%
Widest swing-6.6 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 |
|---|---|---|---|---|---|
| Octagon | 55.0% | +5.5 | 0.069 | 242 | |
| Fence and open | 52.9% | +3.4 | 0.402 | 140 | |
| Open | 52.8% | +3.4 | 0.259 | 250 | |
| Breakable full fence | 51.2% | +1.7 | 0.593 | 215 | |
| Rectangle | 49.3% | -0.1 | 0.980 | 229 | |
| Single wall | 49.3% | -0.1 | 0.965 | 207 | |
| Low fence | 49.0% | -0.4 | 0.884 | 245 | |
| Breakable half fence | 48.0% | -1.4 | 0.630 | 246 | |
| Full fence | 44.2% | -5.2 | 0.065 | 276 | |
| Half fence | 42.8% | -6.6 | 0.025 | 257 |
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 12.71 on 9 df, p 0.176
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 44.2%276 | -7.00.125 | +1.40.744 | -3.80.389 | -4.80.275 | -5.10.269 | -8.70.095 | -8.60.049 | -5.10.249 | -10.80.015 |
| Breakable full fence | +7.00.125 | 51.2%215 | +8.40.070 | +3.20.494 | +2.20.640 | +1.90.698 | -1.70.755 | -1.60.725 | +1.80.702 | -3.80.417 |
| Half fence | -1.40.744 | -8.40.070 | 42.8%257 | -5.20.245 | -6.20.165 | -6.50.164 | -10.10.055 | -10.00.024 | -6.50.148 | -12.20.007 |
| Breakable half fence | +3.80.389 | -3.20.494 | +5.20.245 | 48.0%246 | -1.00.822 | -1.30.781 | -4.90.356 | -4.80.282 | -1.40.764 | -7.00.122 |
| Low fence | +4.80.275 | -2.20.640 | +6.20.165 | +1.00.822 | 49.0%245 | -0.30.950 | -3.90.464 | -3.80.395 | -0.40.937 | -6.00.187 |
| Single wall | +5.10.269 | -1.90.698 | +6.50.164 | +1.30.781 | +0.30.950 | 49.3%207 | -3.60.513 | -3.50.453 | -0.10.988 | -5.70.229 |
| Fence and open | +8.70.095 | +1.70.755 | +10.10.055 | +4.90.356 | +3.90.464 | +3.60.513 | 52.9%140 | +0.10.991 | +3.50.513 | -2.10.691 |
| Open | +8.60.049 | +1.60.725 | +10.00.024 | +4.80.282 | +3.80.395 | +3.50.453 | -0.10.991 | 52.8%250 | +3.50.450 | -2.20.631 |
| Rectangle | +5.10.249 | -1.80.702 | +6.50.148 | +1.40.764 | +0.40.937 | +0.10.988 | -3.50.513 | -3.50.450 | 49.3%229 | -5.60.223 |
| Octagon | +10.80.015 | +3.80.417 | +12.20.007 | +7.00.122 | +6.00.187 | +5.70.229 | +2.10.691 | +2.20.631 | +5.60.223 | 55.0%242 |
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 counted2,323
Win rate50.1%
Widest swing-6.7 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 |
|---|---|---|---|---|---|
| Octagon | 55.2% | +5.2 | 0.092 | 239 | |
| Fence and open | 53.6% | +3.6 | 0.389 | 138 | |
| Open | 53.1% | +3.1 | 0.316 | 239 | |
| Breakable full fence | 52.0% | +1.9 | 0.569 | 202 | |
| Rectangle | 50.0% | -0.1 | 0.984 | 224 | |
| Single wall | 50.0% | -0.1 | 0.985 | 192 | |
| Low fence | 49.1% | -0.9 | 0.768 | 236 | |
| Breakable half fence | 48.7% | -1.4 | 0.663 | 232 | |
| Full fence | 45.6% | -4.5 | 0.125 | 261 | |
| Half fence | 43.3% | -6.7 | 0.025 | 247 |
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 11.23 on 9 df, p 0.260
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 45.6%261 | -6.40.173 | +2.30.606 | -3.10.489 | -3.60.427 | -4.40.353 | -8.00.127 | -7.50.092 | -4.40.333 | -9.60.031 |
| Breakable full fence | +6.40.173 | 52.0%202 | +8.70.067 | +3.30.496 | +2.80.555 | +2.00.694 | -1.60.766 | -1.20.808 | +2.00.683 | -3.20.495 |
| Half fence | -2.30.606 | -8.70.067 | 43.3%247 | -5.40.237 | -5.80.199 | -6.70.164 | -10.30.052 | -9.80.030 | -6.70.147 | -11.90.009 |
| Breakable half fence | +3.10.489 | -3.30.496 | +5.40.237 | 48.7%232 | -0.40.923 | -1.30.791 | -4.90.360 | -4.40.336 | -1.30.782 | -6.50.157 |
| Low fence | +3.60.427 | -2.80.555 | +5.80.199 | +0.40.923 | 49.1%236 | -0.80.862 | -4.50.404 | -4.00.385 | -0.80.856 | -6.10.185 |
| Single wall | +4.40.353 | -2.00.694 | +6.70.164 | +1.30.791 | +0.80.862 | 50.0%192 | -3.60.516 | -3.10.517 | +0.01.000 | -5.20.280 |
| Fence and open | +8.00.127 | +1.60.766 | +10.30.052 | +4.90.360 | +4.50.404 | +3.60.516 | 53.6%138 | +0.50.928 | +3.60.503 | -1.60.763 |
| Open | +7.50.092 | +1.20.808 | +9.80.030 | +4.40.336 | +4.00.385 | +3.10.517 | -0.50.928 | 53.1%239 | +3.10.500 | -2.10.646 |
| Rectangle | +4.40.333 | -2.00.683 | +6.70.147 | +1.30.782 | +0.80.856 | -0.01.000 | -3.60.503 | -3.10.500 | 50.0%224 | -5.20.260 |
| Octagon | +9.60.031 | +3.20.495 | +11.90.009 | +6.50.157 | +6.10.185 | +5.20.280 | +1.60.763 | +2.10.646 | +5.20.260 | 55.2%239 |
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 counted103
Win rate35.0%
Widest swing-35.0 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 |
|---|---|---|---|---|---|
| Open | 45.5% | +10.5 | 0.440 | 11 · | |
| Low fence | 44.4% | +9.5 | 0.532 | 9 · | |
| Single wall | 40.0% | +5.0 | 0.657 | 15 · | |
| Breakable full fence | 38.5% | +3.5 | 0.776 | 13 · | |
| Breakable half fence | 35.7% | +0.8 | 0.949 | 14 · | |
| Octagon | 33.3% | -1.6 | 0.952 | 3 · | |
| Half fence | 30.0% | -5.0 | 0.730 | 10 · | |
| Full fence | 20.0% | -14.9 | 0.189 | 15 · | |
| Rectangle | 20.0% | -14.9 | 0.472 | 5 · | |
| Fence and open | 0.0% | -35.0 | 0.295 | 2 · |
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 4.30 on 9 df, p 0.890
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 20.0%15 | -18.50.281 | -10.00.566 | -15.70.344 | -24.40.202 | -20.00.232 | +20.00.486 | -25.40.165 | +0.01.000 | -13.30.612 |
| Breakable full fence | +18.50.281 | 38.5%13 | +8.50.673 | +2.80.883 | -6.00.779 | -1.50.934 | +38.50.283 | -7.00.729 | +18.50.457 | +5.10.869 |
| Half fence | +10.00.566 | -8.50.673 | 30.0%10 | -5.70.770 | -14.40.515 | -10.00.610 | +30.00.371 | -15.40.466 | +10.00.680 | -3.30.913 |
| Breakable half fence | +15.70.344 | -2.80.883 | +5.70.770 | 35.7%14 | -8.70.675 | -4.30.812 | +35.70.308 | -9.70.622 | +15.70.516 | +2.40.938 |
| Low fence | +24.40.202 | +6.00.779 | +14.40.515 | +8.70.675 | 44.4%9 | +4.40.831 | +44.40.237 | -1.00.964 | +24.40.360 | +11.10.735 |
| Single wall | +20.00.232 | +1.50.934 | +10.00.610 | +4.30.812 | -4.40.831 | 40.0%15 | +40.00.266 | -5.50.781 | +20.00.417 | +6.70.829 |
| Fence and open | -20.00.486 | -38.50.283 | -30.00.371 | -35.70.308 | -44.40.237 | -40.00.266 | 0.0%2 | -45.50.224 | -20.00.495 | -33.30.361 |
| Open | +25.40.165 | +7.00.729 | +15.40.466 | +9.70.622 | +1.00.964 | +5.50.781 | +45.50.224 | 45.5%11 | +25.40.330 | +12.10.707 |
| Rectangle | -0.01.000 | -18.50.457 | -10.00.680 | -15.70.516 | -24.40.360 | -20.00.417 | +20.00.495 | -25.40.330 | 20.0%5 | -13.30.673 |
| Octagon | +13.30.612 | -5.10.869 | +3.30.913 | -2.40.938 | -11.10.735 | -6.70.829 | +33.30.361 | -12.10.707 | +13.30.673 | 33.3%3 |
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.