General Language Understanding on MMLU, AlpacaEval, Arena-Hard
73.41MMLU Accuracy
Qwen2.5-7B + DataFlow-Chat-15K
Updated 4d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| 73.41 | 10.11 | 110 | 28.21 | ||
2025.12 | 73.09 | 3.7 | 130 | 26.03 | |
2025.12 | 72.97 | 3.97 | 80 | 25.91 | |
2025.12 | 71.45 | 7.05 | 60 | 26.36 |