This paper presents the first systematic comparison investigating whether Large Reasoning Models (LRMs) are superior judges to non-reasoning LLMs. Our empirical analysis yields four key findings: 1) LRMs outperform non-reasoning LLMs in terms of judgment accuracy, particularly on reasoning-intensive tasks; 2) LRMs demonstrate superior evaluation instruction-following capabilities; 3) LRMs exhibit enhanced robustness against adversarial attacks targeting judgment tasks; 4) However, LRMs still exhibit strong evaluation biases. To mitigate this bias vulnerability, we propose PlanJudge, a lightweight evaluation strategy that prompts the model to generate an explicit evaluation plan before executing the judgment. Despite its simplicity, our experiments demonstrate that PlanJudge significantly mitigates biases in LLM-as-a-Judge while preserving overall judgment accuracy.
@article{arxiv.2601.03630,
title = {Reasoning Model Is Superior LLM-Judge, Yet Suffers from Biases},
author = {Hui Huang and Xuanxin Wu and Muyun Yang and Yuki Arase},
journal= {arXiv preprint arXiv:2601.03630},
year = {2026}
}