Pokémon
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Preference Learning | Pokémon (test) | Test AUC86 | 4 | |
| Competitive Pokémon Play | Pokémon OU against GPT-4o Gen 1 (test) | Win Rate0.7 | 3 | |
| Synthetic Image Detection | Pokémon (test) | AUCROC83 | 3 |
Showing 3 of 3 rows