# MT-Bench

> 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.

- Identifier: PTL-0209
- Category: Benchmarks
- Canonical URL: https://protologue.com/t/mt-bench/
- Introduced: 2023

## 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.

## Broader terms

- [Benchmark](https://protologue.com/t/benchmark/)

## Related terms

- [LLM-as-a-Judge](https://protologue.com/t/llm-as-a-judge/)
- [LLM Judge Bias](https://protologue.com/t/llm-judge-bias/)
- [Chatbot Arena](https://protologue.com/t/chatbot-arena/)

## Sources

- Zheng et al. (2023). Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. https://arxiv.org/abs/2306.05685

## Cite this entry

Protologue. (2026). MT-Bench. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0209). https://protologue.com/t/mt-bench/

License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)