| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| PhotoChat (test) | DRIBER ChatGPT 0613 | F1 Score65.6 | 26 | 4d ago | |
| Tamil | Reptile | Accuracy94.5 | 6 | 4d ago | |
| FSC | Reptile | Accuracy99.2 | 6 | 4d ago | |
| Grabo | Reptile | Accuracy98.9 | 5 | 4d ago | |
| Painting Assistor Evaluation Set (test) | MagicQuill (Ours) | GPT-4 Similarity2.712 | 4 | 4d ago | |
| MANTIS | Oracle-Gen | AP77.1 | 4 | 4d ago | |
| CN | Reptile | Accuracy55.2 | 4 | 4d ago | |
| Shopee Production Traffic (online) | QE-Rec | CSAT17 | 2 | 4d ago |