Financial Language Modeling on Financial-domain benchmarks
83.9CFLUE-K ScoreYouZhi-14B
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| YouZhi-14BGroup=Our Models2026.06 | 83.9 | 42.4 | 78.1 | 91.5 | 89.4 | 87.2 | 78.8 | |
| DianJin-R1-7BGroup=Baselines2026.06 | 77.6 | 33.7 | 74.7 | 79 | 85.8 | 68.2 | 69.8 | |
| Qwen2.5-14B-Ins.Group=Base Models2026.06 | 73.4 | 35.6 | 72.7 | 83.3 | 85.6 | 83.5 | 72.4 | |
| YouZhi-7BGroup=Our Models2026.06 | 71.2 | 43.3 | 70.2 | 86.5 | 86.7 | 86.8 | 74.1 | |
| Qwen3.5-9BGroup=Baselines2026.06 | 70.7 | 37.1 | 78.1 | 85.7 | 84.7 | 82.4 | 73.1 | |
| Qwen3-8BGroup=Baselines2026.06 | 66.9 | 37.9 | 69.5 | 80.1 | 83.7 | 82.2 | 70.1 | |
| YiZhao-12B-ChatGroup=Baselines2026.06 | 62.1 | 39.6 | 63.8 | 84.5 | 86 | 82.4 | 69.7 | |
| OpenPangu-7BGroup=Base Models2026.06 | 50.7 | 36.5 | 57.2 | 70.1 | 81.7 | 66.5 | 60.5 |