| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Toxicity Detection | Adv | Accuracy59.74 | 42 | |
| Code Retrieval | Adv | MRR48.6 | 9 | |
| NL2Code Search | Adv (test) | MRR57.27 | 7 | |
| Deepfake Detection | adv V2 | Accuracy92.3 | 2 | |
| Online Optimization with Long-Term Constraints | ADV constant rho | Metric- | 0 |