General Language Understanding on MMLU (Accuracy, IR)
71.6AccuracyQwen2.5-14B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen2.5-14BBackbone=Qwen2.5-14B, Post-training Strategy=Base2026.04 | 71.6 | 4.7 | |
| HyTuningBackbone=Qwen2.5-14B, Post-training Strategy=HyTuning2026.04 | 71.5 | 3.7 | |
| HyTuningBackbone=Qwen2.5-7B, Post-training Strategy=HyTuning2026.04 | 61.4 | 8.1 | |
| Qwen2.5-7BBackbone=Qwen2.5-7B, Post-training Strategy=Base2026.04 | 61.3 | 12.6 | |
| HyTuningBackbone=Qwen2.5-3B, Post-training Strategy=HyTuning2026.04 | 55.2 | 9.9 | |
| INTUITORBackbone=Qwen2.5-3B, Post-training Strategy=INTUITOR2026.04 | 47.6 | 21.1 | |
| RLPRBackbone=Qwen2.5-3B, Post-training Strategy=RLPR2026.04 | 45.1 | 23.9 | |
| RLVRBackbone=Qwen2.5-3B, Post-training Strategy=RLVR2026.04 | 45 | 24 | |
| HPTBackbone=Qwen2.5-3B, Post-training Strategy=HPT2026.04 | 45 | 24 | |
| Qwen2.5-3BBackbone=Qwen2.5-3B, Post-training Strategy=Base2026.04 | 44.9 | 24.1 | |
| RDBackbone=Qwen2.5-3B, Post-training Strategy=RD2026.04 | 44.9 | 24.5 | |
| SFTBackbone=Qwen2.5-3B, Post-training Strategy=SFT2026.04 | 44.3 | 25.1 |