Constrained Machine Translation on Sand-Glass Zh-Es (test)
0.671Cometkiwideepseek-v3
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| deepseek-v3Category=w/o Syllable Constraint2026.01 | 0.671 | — | 0.884 | 0.191 | 99.6 | |
| gpt-5*Category=w/o Syllable Constraint2026.01 | 0.671 | — | 0.899 | 0.206 | — | |
| claude-4.1-opusCategory=w/o Syllable Constraint2026.01 | 0.668 | — | 0.9 | 0.22 | 21.3 | |
| gemini-2.5-pro*Category=w/o Syllable Constraint2026.01 | 0.668 | — | 0.883 | 0.212 | — | |
| claude-4.1-opusCategory=Translate + Modify Pipeline (2 run)2026.01 | 0.643 | — | 0.876 | 0.246 | 37.6 | |
| claude-4.1-opusCategory=w/ Syllable Constraint2026.01 | 0.631 | — | 0.849 | 0.261 | 13.5 | |
| claude-4.1-opusCategory=Best of N2026.01 | 0.621 | — | 0.857 | 0.304 | 110 | |
| HOMURA (Rubric)Category=HOMURA2026.01 | 0.62 | — | 0.863 | 0.26 | 13.1 | |
| HOMURA (Reason)Category=HOMURA2026.01 | 0.605 | — | 0.858 | 0.309 | 13.2 | |
| gemini-2.5-pro*Category=Translate + Modify Pipeline (2 run)2026.01 | 0.602 | — | 0.84 | 0.25 | — | |
| gemini-2.5-pro*Category=w/ Syllable Constraint2026.01 | 0.586 | — | 0.827 | 0.252 | — | |
| gpt-5*Category=w/ Syllable Constraint2026.01 | 0.586 | — | 0.833 | 0.27 | — | |
| gpt-5*Category=Translate + Modify Pipeline (2 run)2026.01 | 0.557 | — | 0.82 | 0.234 | — | |
| deepseek-v3Category=w/ Syllable Constraint2026.01 | 0.556 | — | 0.868 | 0.225 | 16.3 | |
| gemini-2.5-pro*Category=Best of N2026.01 | 0.554 | — | 0.858 | 0.235 | — | |
| deepseek-v3Category=Translate + Modify Pipeline (2 run)2026.01 | 0.543 | — | 0.873 | 0.221 | 102.1 | |
| gpt-5*Category=Best of N2026.01 | 0.529 | — | 0.855 | 0.256 | — | |
| deepseek-v3Category=Best of N2026.01 | 0.522 | — | 0.851 | 0.275 | 113.6 |