General Downstream Task Evaluation on Hugging Face Open LLM Leaderboard
68.4MMLUMath Teacher
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Math Teacher2026.05 | 68.4 | 80.8 | 68.5 | 54.3 | 66 | 86.7 | 75.4 | 89.2 | 73.7 | |
| Qwen3-4B2026.05 | 68.3 | 80.7 | 68.4 | 54.8 | 66.6 | 84.2 | 75.8 | 88.9 | 73.5 | |
| Code Teacher2026.05 | 68.3 | 80.2 | 68.3 | 54.8 | 65.7 | 85.8 | 75.7 | 89.7 | 73.6 | |
| OPD2026.05 | 68.3 | 80.3 | 68.4 | 54.6 | 66.5 | 88.6 | 75.5 | 89.2 | 73.9 | |
| Uni-OPD2026.05 | 68.3 | 80.3 | 68.3 | 54.6 | 66 | 88.6 | 75.7 | 89.2 | 73.9 |