| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Wikitext-10 | EntiGraph | Factual Accuracy1.46 | 10 | 14d ago | |
| SQuAD 2.0 | EmbGen | Factual Accuracy1.66 | 10 | 14d ago | |
| Pop-QA Cities 20 | InstructLab | Factual Accuracy1.75 | 10 | 14d ago | |
| MOCHA | Qwen 3 30B | Spearman Correlation0.872 | 6 | 2mo ago | |
| CUS-QA orig. | Qwen 3 30B | CS95.6 | 6 | 2mo ago | |
| CUS-QA en | Qwen 3 30B | CS Metric91.7 | 6 | 2mo ago |