List your company

Bilingual Response Generation on English en

54.1QA-F1HDPO
3.76416.83229.942.968Jun 11, 2026

Evaluation results

MethodLinks
HDPOModel=Gemma-2-2B2026.0654.10.27578.885.373.1
Bucket-SFTModel=Qwen2.5-3B2026.0647.60.2590.365.268.8
HDPOModel=Qwen2.5-1.5B2026.0646.30.46584.662.363.9
Bucket-SFTModel=Qwen2.5-1.5B2026.0644.40.42793.958.564.3
HDPOModel=Qwen2.5-3B2026.0641.80.4977.947.456.7
HDPOModel=Llama-3.2-3B2026.0640.50.36756060.4
Full-SFTModel=Qwen2.5-3B2026.0639.8649.4991.864.413.7
Bucket-SFTModel=Gemma-2-2B2026.0638.70.38387.151.659.5
Bucket-SFTModel=Llama-3.2-3B2026.0637.20.37386.743.956.6
DPOModel=Llama-3.2-3B2026.0635.624.43178.663.228.8
DPOModel=Qwen2.5-1.5B2026.0635.51.25984.75852.7
Full-SFTModel=Llama-3.2-3B2026.0634.41.13990.662.755
Full-SFTModel=Qwen2.5-1.5B2026.0631.75.01294.754.737.1
DPOModel=Gemma-2-2B2026.063128,52687.436.54.3
Full-SFTModel=Gemma-2-2B2026.0630.8411.7791.153.413.8
DPOModel=Qwen2.5-3B2026.0626.74.01475.752.338.1
BaseLMModel=Qwen2.5-1.5B2026.0624.86.34453.11723.5
BaseLMModel=Llama-3.2-3B2026.0622.79.77380.835.227.8
BaseLMModel=Qwen2.5-3B2026.06204.84755.830.927.7
BaseLMModel=Gemma-2-2B2026.0619.47,708.678.4274.8
CoTModel=Qwen2.5-3B2026.0610.12.29122.821.319.7
CoTModel=Llama-3.2-3B2026.06102.4331.518.620.3
CoTModel=Qwen2.5-1.5B2026.069.92.59230.722.220.8
CoTModel=Gemma-2-2B2026.065.74.87613.56.69.6