{
  "id": "mt-bench",
  "code": "PTL-0209",
  "term": "MT-Bench",
  "aliases": [],
  "category": "benchmarks",
  "definition": "MT-Bench is a benchmark of 80 two-turn questions across categories such as writing, reasoning, math, and coding, in which a strong LLM acts as the judge and scores each response.",
  "description": "It was introduced with the systematic study of LLM-as-a-judge, which found that strong model judges agreed with human preferences about as well as people agreed with each other, and also documented judge biases. Its small size and reliance on a model judge limit how finely it can separate today's models.",
  "example": null,
  "broader": [
    "benchmark"
  ],
  "narrower": [],
  "related": [
    "llm-as-a-judge",
    "llm-judge-bias",
    "chatbot-arena"
  ],
  "introduced": 2023,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena",
      "authors": "Zheng et al.",
      "year": 2023,
      "url": "https://arxiv.org/abs/2306.05685"
    }
  ],
  "url": "https://protologue.com/t/mt-bench/",
  "citation": "Protologue. (2026). MT-Bench. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0209). https://protologue.com/t/mt-bench/"
}