| Similarity | Rank | |
|---|---|---|
| pidgin | 0.789 | 39772 |
| swahili | 0.759 | 22254 |
| indo-european | 0.732 | 46370 |
| urdu | 0.717 | 33452 |
| multilingual | 0.709 | 29904 |
| farsi | 0.707 | 93641 |
| aymara | 0.703 | 66600 |
| trilingual | 0.701 | 99722 |
| gujarati | 0.701 | 56776 |
| esol | 0.700 | 69784 |
| hindi | 0.692 | 25493 |
| cyrillic | 0.689 | 43657 |
| bahasa | 0.689 | 79516 |
| sesotho | 0.682 | 82333 |
| sanskrit | 0.677 | 22373 |
| arabic | 0.672 | 9338 |
| translation | 0.667 | 4167 |
| aramaic | 0.666 | 38809 |
| back-translated | 0.666 | 75467 |
| language | 0.665 | 535 |
| topic-prominent | 0.665 | 71545 |
| illyrian | 0.661 | 50000 |
| glagolitic | 0.660 | 70131 |
| hausa | 0.660 | 56720 |
| quechua | 0.658 | 38285 |