| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Text generation | 1024 samples | Perplexity (GPT-2)104.44 | 30 | |
| Image Editing | 100 evaluation samples (test) | L1 Loss0.0146 | 6 | |
| Adversarial Attack Transferability | 1,000 samples (held-out) | Flip Rate98.8 | 5 | |
| Clustering | 500-point samples | Sample ARI0.724 | 3 |