| JackGPT vs Bryan | 344–341 | 50.22% |
| JackGPT vs Dragunov | 328–320 | 50.62% |
| JackGPT vs Kazuya | 342–298 | 53.44% |
| JackGPT vs Hwoarang | 326–277 | 54.06% |
| JackGPT vs Steve | 294–298 | 49.66% |
| JackGPT vs Paul | 250–258 | 49.21% |
| JackGPT vs King | 189–253 | 42.76% |
| JackGPT vs Asuka | 218–223 | 49.43% |
| JackGPT vs Lili | 215–223 | 49.09% |
| JackGPT vs Jin | 211–215 | 49.53% |
| JackGPT vs Yoshimitsu | 230–194 | 54.25% |
| JackGPT vs Feng | 215–199 | 51.93% |
| JackGPT vs Heihachi | 178–232 | 43.41% |
| JackGPT vs Law | 202–166 | 54.89% |
| JackGPT vs Reina | 197–168 | 53.97% |
| JackGPT vs Lars | 191–173 | 52.47% |
| JackGPT vs Devil Jin | 181–178 | 50.42% |
| JackGPT vs Xiaoyu | 176–173 | 50.43% |
| JackGPT vs Victor | 178–158 | 52.98% |
| JackGPT vs Lee | 182–153 | 54.33% |
| JackGPT vs Jun | 150–153 | 49.50% |
| JackGPT vs Nina | 136–159 | 46.10% |
| JackGPT vs Jack-8 | 135–158 | 46.08% |
| JackGPT vs Alisa | 166–127 | 56.66% |
| JackGPT vs Lidia | 154–130 | 54.23% |
| JackGPT vs Azucena | 139–136 | 50.55% |
| JackGPT vs Eddy | 159–113 | 58.46% |
| JackGPT vs Shaheen | 116–153 | 43.12% |
| JackGPT vs Leo | 133–130 | 50.57% |
| JackGPT vs Claudio | 123–130 | 48.62% |
| JackGPT vs Raven | 114–128 | 47.11% |
| JackGPT vs Leroy | 131–106 | 55.27% |
| JackGPT vs Clive | 114–122 | 48.31% |
| JackGPT vs Zafina | 106–87 | 54.92% |
| JackGPT vs Kuma | 93–88 | 51.38% |
| JackGPT vs Anna | 98–82 | 54.44% |
| JackGPT vs Fahkumram | 55–77 | 41.67% |
| JackGPT vs Armor King | 52–62 | 45.61% |
| JackGPT vs Miary Zo | 44–44 | 50.00% |
| JackGPT vs Panda | 38–41 | 48.10% |
Limitations
This data is often requested to give insight into which characters you have more trouble with than others, but it is not particularly helpful for that. The main issue is that it is heavily skewed by how strong the opponents you play are.
For example, this data suggests my worst matchup is clearly vs Reina, but that's just because most of those games are vs Yagami.
There is a way to account for this being worked on. The central idea is to assign each matchup a rating vs you which adjusts based on the result, much like the regular rating but also based on the rating of each player. With this, it would give a better summary of how well you perform vs each character.
In the meantime, this page is here to present the data as requested.