| RatGPT vs Kazuya | 181–188 | 49.05% |
| RatGPT vs Hwoarang | 163–128 | 56.01% |
| RatGPT vs Bryan | 133–150 | 47.00% |
| RatGPT vs King | 136–112 | 54.84% |
| RatGPT vs Reina | 113–130 | 46.50% |
| RatGPT vs Heihachi | 129–110 | 53.97% |
| RatGPT vs Jin | 102–130 | 43.97% |
| RatGPT vs Paul | 104–99 | 51.23% |
| RatGPT vs Steve | 97–105 | 48.02% |
| RatGPT vs Dragunov | 78–104 | 42.86% |
| RatGPT vs Yoshimitsu | 74–83 | 47.13% |
| RatGPT vs Law | 72–81 | 47.06% |
| RatGPT vs Lili | 68–77 | 46.90% |
| RatGPT vs Devil Jin | 63–73 | 46.32% |
| RatGPT vs Asuka | 59–72 | 45.04% |
| RatGPT vs Armor King | 60–69 | 46.51% |
| RatGPT vs Lee | 49–66 | 42.61% |
| RatGPT vs Feng | 57–51 | 52.78% |
| RatGPT vs Clive | 58–48 | 54.72% |
| RatGPT vs Victor | 59–42 | 58.42% |
| RatGPT vs Xiaoyu | 46–46 | 50.00% |
| RatGPT vs Lars | 39–51 | 43.33% |
| RatGPT vs Nina | 42–44 | 48.84% |
| RatGPT vs Alisa | 44–41 | 51.76% |
| RatGPT vs Jun | 39–41 | 48.75% |
| RatGPT vs Eddy | 38–35 | 52.05% |
| RatGPT vs Jack-8 | 40–27 | 59.70% |
| RatGPT vs Azucena | 34–32 | 51.52% |
| RatGPT vs Fahkumram | 40–25 | 61.54% |
| RatGPT vs Lidia | 31–32 | 49.21% |
| RatGPT vs Leo | 25–29 | 46.30% |
| RatGPT vs Raven | 21–32 | 39.62% |
| RatGPT vs Leroy | 16–27 | 37.21% |
| RatGPT vs Claudio | 20–20 | 50.00% |
| RatGPT vs Anna | 15–24 | 38.46% |
| RatGPT vs Shaheen | 14–17 | 45.16% |
| RatGPT vs Kuma | 15–13 | 53.57% |
| RatGPT vs Zafina | 12–15 | 44.44% |
| RatGPT vs Miary Zo | 13–7 | 65.00% |
| RatGPT vs Panda | 8–1 | 88.89% |
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.