General Knowledge Reasoning on MMLU College
73.12Accuracy (MMLU College GK Reasoning)Reason, Reward, Refine
Evaluation Results
| Method | Links | |
|---|---|---|
| Reason, Reward, RefineModel=Phi 3.5 Mini 3.8B2026.07 | 73.12 | |
| Reason, Reward, RefineModel=LLaMA 3.2 3B2026.07 | 69.09 | |
| RAGModel=Phi 3.5 Mini 3.8B2026.07 | 67.27 | |
| CoTModel=Phi 3.5 Mini 3.8B2026.07 | 65.63 | |
| DPOModel=Phi 3.5 Mini 3.8B2026.07 | 64.34 | |
| SFTModel=Phi 3.5 Mini 3.8B2026.07 | 62.77 | |
| RAGModel=Qwen 2.5 1.5B2026.07 | 62.27 | |
| RAGModel=LLaMA 3.2 3B2026.07 | 61.82 | |
| Reason, Reward, RefineModel=LLaMA 3.2 1B2026.07 | 57.89 | |
| Reason, Reward, RefineModel=Qwen 2.5 1.5B2026.07 | 53.64 | |
| CoTModel=LLaMA 3.2 3B2026.07 | 53.63 | |
| CoTModel=Qwen 2.5 1.5B2026.07 | 52.62 | |
| DPOModel=LLaMA 3.2 3B2026.07 | 50.85 | |
| RAGModel=LLaMA 3.2 1B2026.07 | 45.82 | |
| SFTModel=LLaMA 3.2 3B2026.07 | 45.76 | |
| SFTModel=Qwen 2.5 1.5B2026.07 | 43.22 | |
| DPOModel=Qwen 2.5 1.5B2026.07 | 43.22 | |
| SFTModel=LLaMA 3.2 1B2026.07 | 38.14 | |
| DPOModel=LLaMA 3.2 1B2026.07 | 36.44 | |
| CoTModel=LLaMA 3.2 1B2026.07 | 33.63 |