List your company
ResearchFormerly WizWand

Instruction Following on AlpacaEval 2.0 (Pairwise Win Rates)

92.8Instruct vs. Pretrained Win RateCME-GRPO
0.44824.42448.472.376May 27, 2026
Updated 5mo ago

Evaluation results

MethodLinks
CME-GRPOGenerator=Llama-3.2-1B-It, Pretrained baseline=Llama-3.2-1B, Instruct baseline=Llama-3.2-1B-It, Training Regime=Instruction-Tuned baselines, Reference Model=gemma-3-1b-it, LLM Judge=GPT-5.2 and Claude Sonnet 4.62026.0592.894.853.37.544.242.2
CME-GRPOGenerator=Qwen2.5-0.5B-It, Pretrained baseline=Qwen2.5-0.5B, Instruct baseline=Qwen2.5-0.5B-It, Training Regime=Instruction-Tuned baselines, Reference Model=Llama-3.2-1B-Instruct, LLM Judge=GPT-5.2 and Claude Sonnet 4.62026.057783.552.57.821.720.2
CME-GRPOGenerator=OLMo-1B-SFT, Pretrained baseline=OLMo-1B-SFT, Instruct baseline=OLMo-1B-DPO, Training Regime=SFT baselines, Reference Model=gemma-3-1b-it, LLM Judge=GPT-5.2 and Claude Sonnet 4.62026.0540.861.4443136.237.6
CME-GRPOGenerator=Qwen2.5-0.5B, Pretrained baseline=Qwen2.5-0.5B, Instruct baseline=Qwen2.5-0.5B-It, Training Regime=Pretrained baselines, Reference Model=gemma-3-1b-it, LLM Judge=GPT-5.2 and Claude Sonnet 4.62026.052371.434713.222.6
CME-GRPOGenerator=Llama-3.2-1B, Pretrained baseline=Llama-3.2-1B, Instruct baseline=Llama-3.2-1B-It, Training Regime=Pretrained baselines, Reference Model=gemma-3-1b-it, LLM Judge=GPT-5.2 and Claude Sonnet 4.62026.057.2556.56.59.842.2
CME-GRPOGenerator=Gemma-3-1B-pt, Pretrained baseline=gemma-3-1b-pt, Instruct baseline=gemma-3-1b-it, Training Regime=Pretrained baselines, Reference Model=Llama-3.2-1B-Instruct, LLM Judge=GPT-5.2 and Claude Sonnet 4.62026.05461.29.25.29.259.2