List your company

General Evaluation on UltraFeedback Aggregate

59.59Overall Average ScoreLP-SFT
20.350830.537940.72550.9121Jul 6, 2026

Evaluation results

MethodLinks
LP-SFTBackbone=Qwen3-14B2026.0759.59
ASFTBackbone=Qwen3-14B2026.0757.43
EAFTBackbone=Qwen3-14B2026.0755.94
CEBackbone=Qwen3-14B2026.0755.54
LP-SFTBackbone=Qwen3-4B2026.0754.74
GEMBackbone=Qwen3-14B2026.0753.55
EAFTBackbone=Qwen3-4B2026.0751
ASFTBackbone=Qwen3-4B2026.0750.53
CEBackbone=Qwen3-4B2026.0749.9
GEMBackbone=Qwen3-4B2026.0749.39
DFTBackbone=Qwen3-14B2026.0748.47
DFTBackbone=Qwen3-4B2026.0744.02
LP-SFTBackbone=Llama3.1-8B2026.0734.01
GEMBackbone=Llama3.1-8B2026.0732.86
CEBackbone=Llama3.1-8B2026.0732.74
EAFTBackbone=Llama3.1-8B2026.0731.79
ASFTBackbone=Llama3.1-8B2026.0730.71
DFTBackbone=Llama3.1-8B2026.0721.86