| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TopDown | PREFAB | F1 Score66.3 | 5 | 5mo ago | |
| TinyCars | PREFAB | F1 Score63.4 | 5 | 5mo ago | |
| Solid | PREFAB | F1 Score0.632 | 5 | 5mo ago | |
| Shootout | PREFAB | F1 Score65.6 | 5 | 5mo ago | |
| Run'N'Gun | PREFAB | F1 Score68.1 | 5 | 5mo ago | |
| Pirates! | PREFAB | F1 Score68.5 | 5 | 5mo ago | |
| Heist! | PREFAB | F1 Score63.7 | 5 | 5mo ago | |
| Endless | PREFAB | F1 Score63.5 | 5 | 5mo ago | |
| Apex | PREFAB | F1 Score64.8 | 5 | 5mo ago | |
| Gin Rummy vs. fixed expert | Stacked recipe | Win Rate34.2 | 4 | 17d ago | |
| Gin Rummy vs. prior self-play champion | Stacked recipe | Win Rate51.4 | 3 | 17d ago |