| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| STS-B (test) | SGS | Kendall's Tau (STS-B)76.5 | 6 | 1mo ago | |
| BIOSSES (test) | Kendall's Tau (x100)83 | 6 | 1mo ago | ||
| Insurance tasks HQ subset N = 1334 | DeepSeek-R1 + Fine-tune | Mean Score89.9 | 6 | 4mo ago | |
| Quora Question Pairs Classes = 2 | F1 Score84.9 | 5 | 29d ago | ||
| TitleSimCurated Classes = 2 | ANYSIMLITE | Accuracy88.73 | 4 | 29d ago | |
| BK3 (Books3) | PME | BLEU90 | 2 | 4mo ago | |
| Wiki Wikipedia | PME | BLEU89 | 2 | 4mo ago | |
| CC (Common Crawl) | PME | BLEU89 | 2 | 4mo ago |