Redundancy Principles for MLLMs Benchmarks
Zicheng Zhang, Xiangyu Zhao, Xinyu Fang, Chunyi Li, Xiaohong Liu, Xiongkuo Min, Haodong Duan, Kai Chen
Abstract
With the rapid iteration of Multi-modality Large Language Models (MLLMs) and the evolving demands of the field, the number of benchmarks produced annually has surged into the hundreds. The rapid growth has inevitably led to significant redundancy among benchmarks. Therefore, it is crucial to take a step back and critically assess the current state of redundancy and propose targeted principles for constructing effective MLLM benchmarks. In this paper, we focus on redundancy from three key perspectives: 1) Redundancy of benchmark capability dimensions, 2) Redundancy in the number of test questions, and 3) Cross-benchmark redundancy within specific domains. Through the comprehensive analysis over hundreds of MLLMs’ performance across more than 20 benchmarks, we aim to quantitatively measure the level of redundancy lies in existing MLLM evaluations, provide valuable insights to guide the future development of MLLM benchmarks, and offer strategies to refine and address redundancy issues effectively.
BibTeX
@inproceedings{zhang-etal-2025-redundancy-principles,
title = "Redundancy Principles for {MLLM}s Benchmarks",
author = "Zhang, Zicheng and
Zhao, Xiangyu and
Fang, Xinyu and
Li, Chunyi and
Liu, Xiaohong and
Min, Xiongkuo and
Duan, Haodong and
Chen, Kai and
Zhai, Guangtao",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.612/",
doi = "10.18653/v1/2025.acl-long.612",
pages = "12492--12504",
ISBN = "979-8-89176-251-0"
}