| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Human Evaluation Chinese N=10 | MADE | Win Rate85 | 3 | 1mo ago | |
| Human Evaluation Turkish tr N=10 | MADE | Win Rate95 | 3 | 1mo ago | |
| Human Evaluation Thai N=10 | MADE | Win Rate95 | 3 | 1mo ago | |
| Human Evaluation Russian N=10 | MADE | Win Rate90 | 3 | 1mo ago | |
| Human Evaluation Portuguese N=10 (pt) | MADE | Win Rate97.5 | 3 | 1mo ago | |
| Human Evaluation Polish N=10 | MADE | Win Rate90 | 3 | 1mo ago | |
| Human Evaluation Korean N=10 | MADE | Win Rate95 | 3 | 1mo ago | |
| Human Evaluation Italian N=10 | MADE | Win Rate90 | 3 | 1mo ago | |
| Human Evaluation French N=10 | MADE | Win Rate65 | 3 | 1mo ago | |
| Human Evaluation English N=10 | MADE | Win Rate80 | 3 | 1mo ago | |
| Human Evaluation German N=10 (de) | MADE | Win Rate95 | 3 | 1mo ago | |
| Human Evaluation Arabic N=10 | MADE | Win Rate77.5 | 3 | 1mo ago |
