List your company

Bilingual Response Generation on Chinese zh

55.5QA-F1HDPO
-1.1813.53528.2542.965Jun 11, 2026

Evaluation results

MethodLinks
HDPOModel=Gemma-2-2B2026.0655.523.49485.218.824.5
Bucket-SFTModel=Qwen2.5-3B2026.0650.20.58496.465.666.9
Bucket-SFTModel=Qwen2.5-1.5B2026.0647.90.34696.863.668.4
Bucket-SFTModel=Llama-3.2-3B2026.06460.63394.861.363.6
HDPOModel=Qwen2.5-1.5B2026.06450.37585.183.269.4
HDPOModel=Qwen2.5-3B2026.0644.923.53774.818.222.3
HDPOModel=Llama-3.2-3B2026.0644.90.42870.787.766.5
Full-SFTModel=Qwen2.5-3B2026.0644.72.93294.957.449.8
Full-SFTModel=Qwen2.5-1.5B2026.0635.80.91791.845.852.9
Full-SFTModel=Gemma-2-2B2026.0635.21.43994.641.848.9
Bucket-SFTModel=Gemma-2-2B2026.0632.439.36596.744.324.2
DPOModel=Qwen2.5-3B2026.0632.337.5373.77.914.8
BaseLMModel=Llama-3.2-3B2026.0629.718.2372.534.224.9
Full-SFTModel=Llama-3.2-3B2026.0626.50.93287.929.243.3
DPOModel=Qwen2.5-1.5B2026.0623.816.05651.116.318.4
BaseLMModel=Qwen2.5-3B2026.0620.22.4796452.537.4
BaseLMModel=Qwen2.5-1.5B2026.0619.52.46658.622.529.3
BaseLMModel=Gemma-2-2B2026.0610.813.15236.45.911.3
DPOModel=Llama-3.2-3B2026.0610.331.84355.23.48.8
DPOModel=Gemma-2-2B2026.068.136.7534.21.65.8
CoTModel=Qwen2.5-3B2026.065.31.21532.26.615
CoTModel=Qwen2.5-1.5B2026.062.21.68528.9811.7
CoTModel=Llama-3.2-3B2026.061.14.43125.51.65.5
CoTModel=Gemma-2-2B2026.0611.92332.12.57.2