Virtua Fighter 5 REVO · v1.10 · Character Matchup Winrates
Jacky vs Lei Fei
Matches counted2,936
Win rate49.1%
Widest swing-4.0 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Jacky's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Breakable half fence | 52.7% | +3.6 | 0.209 | 279 | |
| Single wall | 52.2% | +3.1 | 0.209 | 364 | |
| Full fence | 52.1% | +3.0 | 0.310 | 257 | |
| Half fence | 51.8% | +2.7 | 0.346 | 274 | |
| Low fence | 48.9% | -0.2 | 0.925 | 307 | |
| Breakable full fence | 48.1% | -1.0 | 0.720 | 293 | |
| Octagon | 47.5% | -1.7 | 0.562 | 274 | |
| Rectangle | 47.2% | -1.9 | 0.478 | 301 | |
| Fence and open | 45.4% | -3.7 | 0.365 | 141 | |
| Open | 45.1% | -4.0 | 0.129 | 315 |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Jacky's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 8.25 on 9 df, p 0.510
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 52.1%257 | +4.00.347 | +0.30.942 | -0.60.899 | +3.30.438 | -0.10.989 | +6.80.198 | +7.10.093 | +5.00.242 | +4.70.280 |
| Breakable full fence | -4.00.347 | 48.1%293 | -3.70.378 | -4.60.275 | -0.70.857 | -4.10.299 | +2.70.593 | +3.00.452 | +0.90.817 | +0.70.872 |
| Half fence | -0.30.942 | +3.70.378 | 51.8%274 | -0.90.839 | +3.00.476 | -0.40.926 | +6.40.214 | +6.70.102 | +4.60.265 | +4.40.305 |
| Breakable half fence | +0.60.899 | +4.60.275 | +0.90.839 | 52.7%279 | +3.80.355 | +0.50.902 | +7.30.158 | +7.60.064 | +5.50.185 | +5.20.218 |
| Low fence | -3.30.438 | +0.70.857 | -3.00.476 | -3.80.355 | 48.9%307 | -3.30.389 | +3.50.495 | +3.80.345 | +1.70.678 | +1.40.733 |
| Single wall | +0.10.989 | +4.10.299 | +0.40.926 | -0.50.902 | +3.30.389 | 52.2%364 | +6.80.170 | +7.10.064 | +5.00.197 | +4.80.235 |
| Fence and open | -6.80.198 | -2.70.593 | -6.40.214 | -7.30.158 | -3.50.495 | -6.80.170 | 45.4%141 | +0.30.951 | -1.80.726 | -2.10.691 |
| Open | -7.10.093 | -3.00.452 | -6.70.102 | -7.60.064 | -3.80.345 | -7.10.064 | -0.30.951 | 45.1%315 | -2.10.602 | -2.40.566 |
| Rectangle | -5.00.242 | -0.90.817 | -4.60.265 | -5.50.185 | -1.70.678 | -5.00.197 | +1.80.726 | +2.10.602 | 47.2%301 | -0.30.949 |
| Octagon | -4.70.280 | -0.70.872 | -4.40.305 | -5.20.218 | -1.40.733 | -4.80.235 | +2.10.691 | +2.40.566 | +0.30.949 | 47.5%274 |
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 counted2,509
Win rate48.7%
Widest swing-4.5 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Jacky's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Single wall | 52.3% | +3.6 | 0.181 | 304 | |
| Breakable half fence | 52.1% | +3.4 | 0.271 | 238 | |
| Half fence | 51.5% | +2.8 | 0.370 | 239 | |
| Full fence | 51.1% | +2.4 | 0.448 | 229 | |
| Low fence | 48.6% | -0.1 | 0.974 | 251 | |
| Breakable full fence | 47.6% | -1.1 | 0.713 | 250 | |
| Rectangle | 47.5% | -1.2 | 0.680 | 259 | |
| Octagon | 46.8% | -1.9 | 0.537 | 233 | |
| Fence and open | 44.5% | -4.2 | 0.372 | 110 | |
| Open | 44.2% | -4.5 | 0.115 | 278 |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Jacky's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 7.50 on 9 df, p 0.585
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 51.1%229 | +3.50.445 | -0.40.936 | -1.00.827 | +2.50.586 | -1.20.782 | +6.50.259 | +6.80.124 | +3.60.427 | +4.30.354 |
| Breakable full fence | -3.50.445 | 47.6%250 | -3.90.393 | -4.50.320 | -1.00.822 | -4.70.271 | +3.00.593 | +3.40.440 | +0.10.980 | +0.80.857 |
| Half fence | +0.40.936 | +3.90.393 | 51.5%239 | -0.60.889 | +2.90.527 | -0.80.846 | +6.90.230 | +7.20.101 | +4.00.376 | +4.70.309 |
| Breakable half fence | +1.00.827 | +4.50.320 | +0.60.889 | 52.1%238 | +3.50.440 | -0.20.963 | +7.50.190 | +7.90.075 | +4.60.304 | +5.30.248 |
| Low fence | -2.50.586 | +1.00.822 | -2.90.527 | -3.50.440 | 48.6%251 | -3.70.386 | +4.10.477 | +4.40.315 | +1.10.801 | +1.80.688 |
| Single wall | +1.20.782 | +4.70.271 | +0.80.846 | +0.20.963 | +3.70.386 | 52.3%304 | +7.80.163 | +8.10.052 | +4.80.255 | +5.50.205 |
| Fence and open | -6.50.259 | -3.00.593 | -6.90.230 | -7.50.190 | -4.10.477 | -7.80.163 | 44.5%110 | +0.30.957 | -2.90.604 | -2.20.698 |
| Open | -6.80.124 | -3.40.440 | -7.20.101 | -7.90.075 | -4.40.315 | -8.10.052 | -0.30.957 | 44.2%278 | -3.20.451 | -2.50.566 |
| Rectangle | -3.60.427 | -0.10.980 | -4.00.376 | -4.60.304 | -1.10.801 | -4.80.255 | +2.90.604 | +3.20.451 | 47.5%259 | +0.70.875 |
| Octagon | -4.30.354 | -0.80.857 | -4.70.309 | -5.30.248 | -1.80.688 | -5.50.205 | +2.20.698 | +2.50.566 | -0.70.875 | 46.8%233 |
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 counted427
Win rate51.5%
Widest swing9.2 pts
Survive correction0
Period2026/03/26 – 2026/09/23
Where it was fought
Jacky's win rate on each stage, against this matchup everywhere| Stage | Stage effect | Win % | Change | p | Matches |
|---|---|---|---|---|---|
| Full fence | 60.7% | +9.2 | 0.314 | 28 · | |
| Breakable half fence | 56.1% | +4.6 | 0.538 | 41 · | |
| Half fence | 54.3% | +2.8 | 0.733 | 35 · | |
| Single wall | 51.7% | +0.1 | 0.981 | 60 · | |
| Open | 51.4% | -0.2 | 0.983 | 37 · | |
| Octagon | 51.2% | -0.3 | 0.967 | 41 · | |
| Breakable full fence | 51.2% | -0.4 | 0.960 | 43 · | |
| Low fence | 50.0% | -1.5 | 0.807 | 56 · | |
| Fence and open | 48.4% | -3.1 | 0.717 | 31 · | |
| Rectangle | 45.2% | -6.3 | 0.391 | 42 · |
p < 0.05 on its ownStill there after correcting for how many were tested
Stage against stage
Jacky's win rate on the row's stage, minus the same on the column'sAll ten shapes at once: chi-square 2.24 on 9 df, p 0.987
| Stage | Full | Break. full | Half | Break. half | Low | Wall | Mixed | Open | Rect | Oct |
|---|---|---|---|---|---|---|---|---|---|---|
| Full fence | 60.7%28 | +9.60.429 | +6.40.608 | +4.60.703 | +10.70.353 | +9.00.427 | +12.30.343 | +9.40.452 | +15.50.204 | +9.50.436 |
| Breakable full fence | -9.60.429 | 51.2%43 | -3.10.784 | -4.90.650 | +1.20.909 | -0.50.960 | +2.80.814 | -0.20.987 | +5.90.585 | -0.10.996 |
| Half fence | -6.40.608 | +3.10.784 | 54.3%35 | -1.80.874 | +4.30.691 | +2.60.805 | +5.90.632 | +2.90.803 | +9.10.429 | +3.10.790 |
| Breakable half fence | -4.60.703 | +4.90.650 | +1.80.874 | 56.1%41 | +6.10.552 | +4.40.661 | +7.70.516 | +4.80.675 | +10.90.322 | +4.90.658 |
| Low fence | -10.70.353 | -1.20.909 | -4.30.691 | -6.10.552 | 50.0%56 | -1.70.858 | +1.60.885 | -1.40.898 | +4.80.641 | -1.20.906 |
| Single wall | -9.00.427 | +0.50.960 | -2.60.805 | -4.40.661 | +1.70.858 | 51.7%60 | +3.30.767 | +0.30.976 | +6.40.523 | +0.50.965 |
| Fence and open | -12.30.343 | -2.80.814 | -5.90.632 | -7.70.516 | -1.60.885 | -3.30.767 | 48.4%31 | -3.00.808 | +3.10.790 | -2.80.812 |
| Open | -9.40.452 | +0.20.987 | -2.90.803 | -4.80.675 | +1.40.898 | -0.30.976 | +3.00.808 | 51.4%37 | +6.10.587 | +0.10.991 |
| Rectangle | -15.50.204 | -5.90.585 | -9.10.429 | -10.90.322 | -4.80.641 | -6.40.523 | -3.10.790 | -6.10.587 | 45.2%42 | -6.00.586 |
| Octagon | -9.50.436 | +0.10.996 | -3.10.790 | -4.90.658 | +1.20.906 | -0.50.965 | +2.80.812 | -0.10.991 | +6.00.586 | 51.2%41 |
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.