LMSYS Arena Introduces AutoEval, a Reward Model for Automated Evaluation

arena · x · 2026-08-13

LMSYS Arena has announced AutoEval, a reward model trained on tens of millions of historical human battle data.

Unlike traditional LLM-as-judge methods, AutoEval remains a live benchmark. Derived from real-world battles, the reward model scores based on human prompts and model responses, allowing it to estimate human preferences and deliver evaluation results at frontier speed.

Original post →

More from Models

Models channel →