| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| PointBench | Point2Insert | Success Rate (%)94.44 | 18 | 3mo ago | |
| COCO 1K | SDID | VQA Score73 | 13 | 3mo ago | |
| RealTox | DLM-SWAI | PPL33.97 | 6 | 5d ago | |
| WikiPol | DLM-SWAI | Perplexity (PPL)44.02 | 6 | 5d ago | |
| OSE | PPL40.26 | 6 | 5d ago | ||
| RedPajama Generation Quality Prefixes (test) | Self-Improving Pretraining: RF-NLL (rollout vs. rewrite) | Standard Prefix Count32.4 | 4 | 3mo ago | |
| Airline Services | HippoRAG | Faithfulness89 | 4 | 3mo ago | |
| Building Management | HippoRAG | Faithfulness97 | 4 | 3mo ago | |
| Liquid Cooling | HippoRAG | Faithfulness90 | 4 | 3mo ago | |
| Data Center | SOPRAG | Faithfulness77 | 4 | 3mo ago |
