Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Goh vs Jacky
Matches counted4,350
Win rate49.0%
Widest swing5.3 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 |
|---|---|---|---|---|---|
| Open | 54.3% | +5.3 | 0.019 | 438 | |
| Fence and open | 53.1% | +4.0 | 0.246 | 196 | |
| Full fence | 50.1% | +1.1 | 0.610 | 485 | |
| Rectangle | 49.6% | +0.6 | 0.797 | 399 | |
| Half fence | 48.9% | -0.1 | 0.966 | 413 | |
| Low fence | 48.7% | -0.3 | 0.893 | 468 | |
| Single wall | 48.4% | -0.6 | 0.784 | 434 | |
| Octagon | 48.0% | -1.0 | 0.669 | 433 | |
| Breakable half fence | 46.5% | -2.5 | 0.269 | 424 | |
| Breakable full fence | 44.9% | -4.1 | 0.071 | 430 |
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 10.83 on 9 df, p 0.287
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 50.1%485 | +5.20.115 | +1.20.722 | +3.60.273 | +1.40.669 | +1.70.603 | -3.00.484 | -4.20.198 | +0.50.887 | +2.10.532 |
| Breakable full fence | -5.20.115 | 44.9%430 | -4.00.242 | -1.60.643 | -3.80.250 | -3.50.302 | -8.20.057 | -9.50.005 | -4.70.172 | -3.20.353 |
| Half fence | -1.20.722 | +4.00.242 | 48.9%413 | +2.50.478 | +0.20.955 | +0.50.879 | -4.20.339 | -5.40.113 | -0.70.839 | +0.90.799 |
| Breakable half fence | -3.60.273 | +1.60.643 | -2.50.478 | 46.5%424 | -2.30.501 | -1.90.572 | -6.60.126 | -7.90.021 | -3.20.364 | -1.60.644 |
| Low fence | -1.40.669 | +3.80.250 | -0.20.955 | +2.30.501 | 48.7%468 | +0.30.921 | -4.30.307 | -5.60.091 | -0.90.790 | +0.70.838 |
| Single wall | -1.70.603 | +3.50.302 | -0.50.879 | +1.90.572 | -0.30.921 | 48.4%434 | -4.70.277 | -6.00.079 | -1.20.721 | +0.30.918 |
| Fence and open | +3.00.484 | +8.20.057 | +4.20.339 | +6.60.126 | +4.30.307 | +4.70.277 | 53.1%196 | -1.30.766 | +3.40.431 | +5.00.243 |
| Open | +4.20.198 | +9.50.005 | +5.40.113 | +7.90.021 | +5.60.091 | +6.00.079 | +1.30.766 | 54.3%438 | +4.70.173 | +6.30.063 |
| Rectangle | -0.50.887 | +4.70.172 | +0.70.839 | +3.20.364 | +0.90.790 | +1.20.721 | -3.40.431 | -4.70.173 | 49.6%399 | +1.60.647 |
| Octagon | -2.10.532 | +3.20.353 | -0.90.799 | +1.60.644 | -0.70.838 | -0.30.918 | -5.00.243 | -6.30.063 | -1.60.647 | 48.0%433 |
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 counted4,060
Win rate49.3%
Widest swing5.1 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 | 54.3% | +5.1 | 0.029 | 416 | |
| Fence and open | 54.0% | +4.8 | 0.183 | 187 | |
| Rectangle | 50.5% | +1.3 | 0.606 | 370 | |
| Octagon | 49.7% | +0.5 | 0.842 | 388 | |
| Full fence | 49.4% | +0.2 | 0.935 | 449 | |
| Single wall | 49.1% | -0.1 | 0.962 | 411 | |
| Half fence | 49.1% | -0.2 | 0.941 | 381 | |
| Low fence | 48.4% | -0.8 | 0.707 | 442 | |
| Breakable half fence | 46.7% | -2.6 | 0.271 | 405 | |
| Breakable full fence | 44.3% | -5.0 | 0.035 | 402 |
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 11.46 on 9 df, p 0.246
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 49.4%449 | +5.20.132 | +0.40.917 | +2.80.417 | +1.00.759 | +0.30.931 | -4.60.294 | -4.90.151 | -1.10.755 | -0.30.931 |
| Breakable full fence | -5.20.132 | 44.3%402 | -4.80.178 | -2.40.496 | -4.10.229 | -4.90.164 | -9.70.028 | -10.10.004 | -6.30.082 | -5.50.124 |
| Half fence | -0.40.917 | +4.80.178 | 49.1%381 | +2.40.498 | +0.70.849 | -0.10.985 | -4.90.269 | -5.20.139 | -1.50.689 | -0.70.855 |
| Breakable half fence | -2.80.417 | +2.40.496 | -2.40.498 | 46.7%405 | -1.80.611 | -2.50.478 | -7.30.097 | -7.70.028 | -3.90.281 | -3.10.386 |
| Low fence | -1.00.759 | +4.10.229 | -0.70.849 | +1.80.611 | 48.4%442 | -0.70.831 | -5.60.200 | -5.90.083 | -2.10.547 | -1.30.703 |
| Single wall | -0.30.931 | +4.90.164 | +0.10.985 | +2.50.478 | +0.70.831 | 49.1%411 | -4.90.270 | -5.20.136 | -1.40.698 | -0.60.867 |
| Fence and open | +4.60.294 | +9.70.028 | +4.90.269 | +7.30.097 | +5.60.200 | +4.90.270 | 54.0%187 | -0.30.943 | +3.50.439 | +4.30.337 |
| Open | +4.90.151 | +10.10.004 | +5.20.139 | +7.70.028 | +5.90.083 | +5.20.136 | +0.30.943 | 54.3%416 | +3.80.289 | +4.60.193 |
| Rectangle | +1.10.755 | +6.30.082 | +1.50.689 | +3.90.281 | +2.10.547 | +1.40.698 | -3.50.439 | -3.80.289 | 50.5%370 | +0.80.826 |
| Octagon | +0.30.931 | +5.50.124 | +0.70.855 | +3.10.386 | +1.30.703 | +0.60.867 | -4.30.337 | -4.60.193 | -0.80.826 | 49.7%388 |
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 counted290
Win rate45.5%
Widest swing12.8 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 |
|---|---|---|---|---|---|
| Full fence | 58.3% | +12.8 | 0.099 | 36 · | |
| Open | 54.5% | +9.0 | 0.376 | 22 · | |
| Low fence | 53.9% | +8.3 | 0.371 | 26 · | |
| Breakable full fence | 53.6% | +8.1 | 0.368 | 28 · | |
| Half fence | 46.9% | +1.4 | 0.870 | 32 · | |
| Breakable half fence | 42.1% | -3.4 | 0.757 | 19 · | |
| Rectangle | 37.9% | -7.6 | 0.387 | 29 · | |
| Single wall | 34.8% | -10.7 | 0.281 | 23 · | |
| Fence and open | 33.3% | -12.2 | 0.456 | 9 · | |
| Octagon | 33.3% | -12.2 | 0.074 | 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 9.66 on 9 df, p 0.379
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 58.3%36 | +4.80.703 | +11.40.345 | +16.20.252 | +4.50.725 | +23.60.078 | +25.00.179 | +3.80.777 | +20.40.102 | +25.00.024 |
| Breakable full fence | -4.80.703 | 53.6%28 | +6.70.605 | +11.50.440 | -0.30.984 | +18.80.180 | +20.20.291 | -1.00.945 | +15.60.236 | +20.20.087 |
| Half fence | -11.40.345 | -6.70.605 | 46.9%32 | +4.80.741 | -7.00.597 | +12.10.370 | +13.60.470 | -7.70.580 | +8.90.481 | +13.60.230 |
| Breakable half fence | -16.20.252 | -11.50.440 | -4.80.741 | 42.1%19 | -11.70.436 | +7.30.627 | +8.80.657 | -12.40.427 | +4.20.772 | +8.80.504 |
| Low fence | -4.50.725 | +0.30.984 | +7.00.597 | +11.70.436 | 53.9%26 | +19.10.181 | +20.50.289 | -0.70.961 | +15.90.237 | +20.50.090 |
| Single wall | -23.60.078 | -18.80.180 | -12.10.370 | -7.30.627 | -19.10.181 | 34.8%23 | +1.40.938 | -19.80.182 | -3.10.815 | +1.40.905 |
| Fence and open | -25.00.179 | -20.20.291 | -13.60.470 | -8.80.657 | -20.50.289 | -1.40.938 | 33.3%9 | -21.20.283 | -4.60.803 | +0.01.000 |
| Open | -3.80.777 | +1.00.945 | +7.70.580 | +12.40.427 | +0.70.961 | +19.80.182 | +21.20.283 | 54.5%22 | +16.60.238 | +21.20.096 |
| Rectangle | -20.40.102 | -15.60.236 | -8.90.481 | -4.20.772 | -15.90.237 | +3.10.815 | +4.60.803 | -16.60.238 | 37.9%29 | +4.60.686 |
| Octagon | -25.00.024 | -20.20.087 | -13.60.230 | -8.80.504 | -20.50.090 | -1.40.905 | -0.01.000 | -21.20.096 | -4.60.686 | 33.3%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.