Bilingual Response Generation on Chinese zh
55.5QA-F1
HDPO
Updated 1mo ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.06 | 55.5 | 23.494 | 85.2 | 18.8 | 24.5 | |
2026.06 | 50.2 | 0.584 | 96.4 | 65.6 | 66.9 | |
2026.06 | 47.9 | 0.346 | 96.8 | 63.6 | 68.4 | |
2026.06 | 46 | 0.633 | 94.8 | 61.3 | 63.6 | |
2026.06 | 45 | 0.375 | 85.1 | 83.2 | 69.4 | |
2026.06 | 44.9 | 23.537 | 74.8 | 18.2 | 22.3 | |
2026.06 | 44.9 | 0.428 | 70.7 | 87.7 | 66.5 | |
2026.06 | 44.7 | 2.932 | 94.9 | 57.4 | 49.8 | |
2026.06 | 35.8 | 0.917 | 91.8 | 45.8 | 52.9 | |
2026.06 | 35.2 | 1.439 | 94.6 | 41.8 | 48.9 | |
2026.06 | 32.4 | 39.365 | 96.7 | 44.3 | 24.2 | |
2026.06 | 32.3 | 37.53 | 73.7 | 7.9 | 14.8 | |
2026.06 | 29.7 | 18.23 | 72.5 | 34.2 | 24.9 | |
2026.06 | 26.5 | 0.932 | 87.9 | 29.2 | 43.3 | |
2026.06 | 23.8 | 16.056 | 51.1 | 16.3 | 18.4 | |
2026.06 | 20.2 | 2.479 | 64 | 52.5 | 37.4 | |
2026.06 | 19.5 | 2.466 | 58.6 | 22.5 | 29.3 | |
2026.06 | 10.8 | 13.152 | 36.4 | 5.9 | 11.3 | |
2026.06 | 10.3 | 31.843 | 55.2 | 3.4 | 8.8 | |
2026.06 | 8.1 | 36.75 | 34.2 | 1.6 | 5.8 | |
2026.06 | 5.3 | 1.215 | 32.2 | 6.6 | 15 | |
2026.06 | 2.2 | 1.685 | 28.9 | 8 | 11.7 | |
2026.06 | 1.1 | 4.431 | 25.5 | 1.6 | 5.5 | |
2026.06 | 1 | 1.923 | 32.1 | 2.5 | 7.2 |