| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| BUCC (full) | VMSST | F1 (Cosine Similarity)87.8 | 12 | 4d ago | |
| Tatoeba (full) | VMSST CONTRASTIVE | Accuracy85.4 | 12 | 4d ago | |
| NorwegianCourts BitextMining | UEC | F1 Score92.96 | 10 | 4d ago | |
| NTREXBitextMining | UEC | F1 Score27.72 | 10 | 4d ago | |
| IndicGenBenchFloresBitextMining | E5 | F1 Score6.91 | 10 | 4d ago | |
| IN22 GenBitextMining | E5 | F18.85 | 10 | 4d ago | |
| Flores Bitext Mining | UEC | F1 Score19.55 | 10 | 4d ago | |
| BornholmBitextMining | UEC | F138.82 | 10 | 4d ago | |
| BUCC (test) | LaBSE | Score (de-en)95.9 | 6 | 4d ago | |
| FLORES-200 34 languages | DAP | d-xsim2.9 | 4 | 4d ago | |
| BUCC 4 languages | MEXMA | BUCC F198.93 | 4 | 4d ago | |
| Tatoeba 112 languages (test) | LaBSE | Accuracy83.7 | 4 | 4d ago | |
| FLORES-200 72 languages | LaBSE | o-xsim0.31 | 3 | 4d ago | |
| FLORES-200 81 languages | LaBSE | xsim0.92 | 3 | 4d ago |
