List your company

General Knowledge Reasoning on MMLU College

73.12Accuracy (MMLU College GK Reasoning)Reason, Reward, Refine
32.050442.712753.37564.0373Jul 6, 2026

Evaluation results

MethodLinks
Reason, Reward, RefineModel=Phi 3.5 Mini 3.8B2026.0773.12
Reason, Reward, RefineModel=LLaMA 3.2 3B2026.0769.09
RAGModel=Phi 3.5 Mini 3.8B2026.0767.27
CoTModel=Phi 3.5 Mini 3.8B2026.0765.63
DPOModel=Phi 3.5 Mini 3.8B2026.0764.34
SFTModel=Phi 3.5 Mini 3.8B2026.0762.77
RAGModel=Qwen 2.5 1.5B2026.0762.27
RAGModel=LLaMA 3.2 3B2026.0761.82
Reason, Reward, RefineModel=LLaMA 3.2 1B2026.0757.89
Reason, Reward, RefineModel=Qwen 2.5 1.5B2026.0753.64
CoTModel=LLaMA 3.2 3B2026.0753.63
CoTModel=Qwen 2.5 1.5B2026.0752.62
DPOModel=LLaMA 3.2 3B2026.0750.85
RAGModel=LLaMA 3.2 1B2026.0745.82
SFTModel=LLaMA 3.2 3B2026.0745.76
SFTModel=Qwen 2.5 1.5B2026.0743.22
DPOModel=Qwen 2.5 1.5B2026.0743.22
SFTModel=LLaMA 3.2 1B2026.0738.14
DPOModel=LLaMA 3.2 1B2026.0736.44
CoTModel=LLaMA 3.2 1B2026.0733.63