List your company

Multi-turn Conversation on MT-Bench (Win Rate)

77.1Win RateRPO
49.74856.84963.9571.051Jun 16, 2025

Evaluation results

MethodLinks
RPOModel=Qwen2.5-7B, Baseline=SFT, LLM Judge=GPT-4o2025.0677.1
RPOModel=Qwen2.5-7B, Baseline=SFT, LLM Judge=Claude-3.52025.0676.8
RPOModel=LLaMA-3-8B, Baseline=SFT, LLM Judge=GPT-4o2025.0676.4
RPOModel=LLaMA-3-8B, Baseline=SFT, LLM Judge=Claude-3.52025.0675.9
RPOModel=Mistral-7B, Baseline=SFT, LLM Judge=GPT-4o2025.0675.1
RPOModel=Mistral-7B, Baseline=SFT, LLM Judge=Claude-3.52025.0674.6
RPOModel=FlanT5-XL, Baseline=SFT, LLM Judge=GPT-4o2025.0668.2
RPOModel=FlanT5-XL, Baseline=SFT, LLM Judge=Claude-3.52025.0667.4
RPOModel=FlanT5-Large, Baseline=SFT, LLM Judge=GPT-4o2025.0664.3
RPOModel=FlanT5-Large, Baseline=SFT, LLM Judge=Claude-3.52025.0663.8
RPOModel=Qwen2.5-7B, Baseline=KTO, LLM Judge=GPT-4o2025.0661.5
RPOModel=LLaMA-3-8B, Baseline=KTO, LLM Judge=GPT-4o2025.0661
RPOModel=Qwen2.5-7B, Baseline=KTO, LLM Judge=Claude-3.52025.0660.9
RPOModel=LLaMA-3-8B, Baseline=KTO, LLM Judge=Claude-3.52025.0660.3
RPOModel=Mistral-7B, Baseline=KTO, LLM Judge=GPT-4o2025.0660.2
RPOModel=Mistral-7B, Baseline=KTO, LLM Judge=Claude-3.52025.0659.1
RPOModel=FlanT5-Small, Baseline=SFT, LLM Judge=GPT-4o2025.0658.8
RPOModel=FlanT5-Small, Baseline=SFT, LLM Judge=Claude-3.52025.0657.9
RPOModel=FlanT5-XL, Baseline=KTO, LLM Judge=GPT-4o2025.0657.4
RPOModel=FlanT5-XL, Baseline=KTO, LLM Judge=Claude-3.52025.0656.9
RPOModel=Qwen2.5-7B, Baseline=DRO, LLM Judge=GPT-4o2025.0656.8
RPOModel=LLaMA-3-8B, Baseline=DRO, LLM Judge=GPT-4o2025.0656.2
RPOModel=Qwen2.5-7B, Baseline=DRO, LLM Judge=Claude-3.52025.0656.1
RPOModel=FlanT5-Large, Baseline=KTO, LLM Judge=GPT-4o2025.0656
RPOModel=Mistral-7B, Baseline=DRO, LLM Judge=GPT-4o2025.0655.9
RPOModel=LLaMA-3-8B, Baseline=DRO, LLM Judge=Claude-3.52025.0655.8
RPOModel=FlanT5-Large, Baseline=KTO, LLM Judge=Claude-3.52025.0655.4
RPOModel=Mistral-7B, Baseline=DRO, LLM Judge=Claude-3.52025.0655.2
RPOModel=FlanT5-Small, Baseline=KTO, LLM Judge=GPT-4o2025.0653.7
RPOModel=FlanT5-XL, Baseline=DRO, LLM Judge=GPT-4o2025.0653.5
RPOModel=FlanT5-Small, Baseline=KTO, LLM Judge=Claude-3.52025.0652.9
RPOModel=FlanT5-Large, Baseline=DRO, LLM Judge=GPT-4o2025.0652.9
RPOModel=FlanT5-XL, Baseline=DRO, LLM Judge=Claude-3.52025.0652.8
RPOModel=FlanT5-Large, Baseline=DRO, LLM Judge=Claude-3.52025.0652.1
RPOModel=FlanT5-Small, Baseline=DRO, LLM Judge=GPT-4o2025.0651.5
RPOModel=FlanT5-Small, Baseline=DRO, LLM Judge=Claude-3.52025.0650.8