List your company

Instruction Following on AlpacaEval MIX-14K gpt4_turbo (test)

17.269LC Win RateDDRO
4.6857.95211.21914.486Apr 6, 2026

Evaluation results

MethodLinks
DDROBase Model=Llama-8B, Preference Dataset=MIX-14K2026.0417.269
RDROBase Model=Llama-8B, Preference Dataset=MIX-14K2026.0417.102
KTOBase Model=Llama-8B, Preference Dataset=MIX-14K2026.0413.921
KTOBase Model=Llama-3B, Preference Dataset=MIX-14K2026.0412.763
RDROBase Model=Llama-3B, Preference Dataset=MIX-14K2026.0412.72
DDROBase Model=Llama-3B, Preference Dataset=MIX-14K2026.0412.487
RDROBase Model=Qwen-3B, Preference Dataset=MIX-14K2026.048.793
DDROBase Model=Qwen-3B, Preference Dataset=MIX-14K2026.048.458
KTOBase Model=Qwen-3B, Preference Dataset=MIX-14K2026.048.24
KTOBase Model=Qwen-1.5B, Preference Dataset=MIX-14K2026.045.32
RDROBase Model=Qwen-1.5B, Preference Dataset=MIX-14K2026.045.297
DDROBase Model=Qwen-1.5B, Preference Dataset=MIX-14K2026.045.169