List your company

Instruction Following on IFEval (Win Rate)

81.2Win RateRPO
52.0859.6467.274.76Jun 16, 2025

Evaluation results

MethodLinks
RPOModel=Qwen2.5-7B, Baseline=SFT, LLM Judge=GPT-4o2025.0681.2
RPOModel=LLaMA-3-8B, Baseline=SFT, LLM Judge=GPT-4o2025.0680.5
RPOModel=Qwen2.5-7B, Baseline=SFT, LLM Judge=Claude-3.52025.0680.4
RPOModel=LLaMA-3-8B, Baseline=SFT, LLM Judge=Claude-3.52025.0679.6
RPOModel=Mistral-7B, Baseline=SFT, LLM Judge=GPT-4o2025.0679.4
RPOModel=Mistral-7B, Baseline=SFT, LLM Judge=Claude-3.52025.0678.3
RPOModel=FlanT5-XL, Baseline=SFT, LLM Judge=GPT-4o2025.0673
RPOModel=FlanT5-XL, Baseline=SFT, LLM Judge=Claude-3.52025.0671.8
RPOModel=FlanT5-Large, Baseline=SFT, LLM Judge=GPT-4o2025.0668.9
RPOModel=FlanT5-Large, Baseline=SFT, LLM Judge=Claude-3.52025.0667.5
RPOModel=Qwen2.5-7B, Baseline=KTO, LLM Judge=GPT-4o2025.0663.9
RPOModel=FlanT5-Small, Baseline=SFT, LLM Judge=GPT-4o2025.0663.5
RPOModel=LLaMA-3-8B, Baseline=KTO, LLM Judge=GPT-4o2025.0663.1
RPOModel=Qwen2.5-7B, Baseline=KTO, LLM Judge=Claude-3.52025.0663.1
RPOModel=FlanT5-Small, Baseline=SFT, LLM Judge=Claude-3.52025.0662.8
RPOModel=LLaMA-3-8B, Baseline=KTO, LLM Judge=Claude-3.52025.0662.5
RPOModel=Mistral-7B, Baseline=KTO, LLM Judge=GPT-4o2025.0662.1
RPOModel=Mistral-7B, Baseline=KTO, LLM Judge=Claude-3.52025.0661.3
RPOModel=FlanT5-XL, Baseline=KTO, LLM Judge=GPT-4o2025.0661
RPOModel=FlanT5-XL, Baseline=KTO, LLM Judge=Claude-3.52025.0660.2
RPOModel=Qwen2.5-7B, Baseline=DRO, LLM Judge=GPT-4o2025.0659.5
RPOModel=FlanT5-Large, Baseline=KTO, LLM Judge=GPT-4o2025.0659.3
RPOModel=LLaMA-3-8B, Baseline=DRO, LLM Judge=GPT-4o2025.0659
RPOModel=Qwen2.5-7B, Baseline=DRO, LLM Judge=Claude-3.52025.0658.7
RPOModel=Mistral-7B, Baseline=DRO, LLM Judge=GPT-4o2025.0658.6
RPOModel=LLaMA-3-8B, Baseline=DRO, LLM Judge=Claude-3.52025.0658.2
RPOModel=FlanT5-Large, Baseline=KTO, LLM Judge=Claude-3.52025.0658.1
RPOModel=Mistral-7B, Baseline=DRO, LLM Judge=Claude-3.52025.0657.8
RPOModel=FlanT5-XL, Baseline=DRO, LLM Judge=GPT-4o2025.0657.2
RPOModel=FlanT5-Small, Baseline=KTO, LLM Judge=GPT-4o2025.0657.1
RPOModel=FlanT5-Small, Baseline=KTO, LLM Judge=Claude-3.52025.0656.4
RPOModel=FlanT5-XL, Baseline=DRO, LLM Judge=Claude-3.52025.0656.4
RPOModel=FlanT5-Large, Baseline=DRO, LLM Judge=GPT-4o2025.0655.8
RPOModel=FlanT5-Large, Baseline=DRO, LLM Judge=Claude-3.52025.0654.6
RPOModel=FlanT5-Small, Baseline=DRO, LLM Judge=GPT-4o2025.0654
RPOModel=FlanT5-Small, Baseline=DRO, LLM Judge=Claude-3.52025.0653.2