Saved in:
Bibliographic Details
Main Authors: Ni, Shiwen, Chen, Guhong, Li, Shuaimin, Chen, Xuanang, Li, Siyi, Wang, Bingli, Wang, Qiyao, Wang, Xingjian, Zhang, Yifan, Fan, Liyang, Li, Chengming, Xu, Ruifeng, Sun, Le, Yang, Min
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.15361
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916911132966912
author Ni, Shiwen
Chen, Guhong
Li, Shuaimin
Chen, Xuanang
Li, Siyi
Wang, Bingli
Wang, Qiyao
Wang, Xingjian
Zhang, Yifan
Fan, Liyang
Li, Chengming
Xu, Ruifeng
Sun, Le
Yang, Min
author_facet Ni, Shiwen
Chen, Guhong
Li, Shuaimin
Chen, Xuanang
Li, Siyi
Wang, Bingli
Wang, Qiyao
Wang, Xingjian
Zhang, Yifan
Fan, Liyang
Li, Chengming
Xu, Ruifeng
Sun, Le
Yang, Min
contents In recent years, with the rapid development of the depth and breadth of large language models' capabilities, various corresponding evaluation benchmarks have been emerging in increasing numbers. As a quantitative assessment tool for model performance, benchmarks are not only a core means to measure model capabilities but also a key element in guiding the direction of model development and promoting technological innovation. We systematically review the current status and development of large language model benchmarks for the first time, categorizing 283 representative benchmarks into three categories: general capabilities, domain-specific, and target-specific. General capability benchmarks cover aspects such as core linguistics, knowledge, and reasoning; domain-specific benchmarks focus on fields like natural sciences, humanities and social sciences, and engineering technology; target-specific benchmarks pay attention to risks, reliability, agents, etc. We point out that current benchmarks have problems such as inflated scores caused by data contamination, unfair evaluation due to cultural and linguistic biases, and lack of evaluation on process credibility and dynamic environments, and provide a referable design paradigm for future benchmark innovation.
format Preprint
id arxiv_https___arxiv_org_abs_2508_15361
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Survey on Large Language Model Benchmarks
Ni, Shiwen
Chen, Guhong
Li, Shuaimin
Chen, Xuanang
Li, Siyi
Wang, Bingli
Wang, Qiyao
Wang, Xingjian
Zhang, Yifan
Fan, Liyang
Li, Chengming
Xu, Ruifeng
Sun, Le
Yang, Min
Computation and Language
In recent years, with the rapid development of the depth and breadth of large language models' capabilities, various corresponding evaluation benchmarks have been emerging in increasing numbers. As a quantitative assessment tool for model performance, benchmarks are not only a core means to measure model capabilities but also a key element in guiding the direction of model development and promoting technological innovation. We systematically review the current status and development of large language model benchmarks for the first time, categorizing 283 representative benchmarks into three categories: general capabilities, domain-specific, and target-specific. General capability benchmarks cover aspects such as core linguistics, knowledge, and reasoning; domain-specific benchmarks focus on fields like natural sciences, humanities and social sciences, and engineering technology; target-specific benchmarks pay attention to risks, reliability, agents, etc. We point out that current benchmarks have problems such as inflated scores caused by data contamination, unfair evaluation due to cultural and linguistic biases, and lack of evaluation on process credibility and dynamic environments, and provide a referable design paradigm for future benchmark innovation.
title A Survey on Large Language Model Benchmarks
topic Computation and Language
url https://arxiv.org/abs/2508.15361