cs.AIFeb 12, 2026

Benchmark Health Index: A Systematic Framework for Benchmarking the Benchmarks of LLMs

Authors: Longyuan Zhu, Hairan Hua, Linlin Miao, Wei Wang, Bing Zhao

Organizations: SKYEVAL Beijing, China · DAMO Academy, Alibaba Group Hangzhou, Zhejiang, China · Zhejiang University Hangzhou, Zhejiang, China

Abstract

Large Language Models (LLMs) are advancing rapidly, yet the benchmarks used to measure this progress are becoming increasingly unreliable. Score inflation and selective reporting have eroded the authority of standard benchmarks, leaving the community uncertain about which evaluation results remain trustworthy. We introduce the Benchmark Health Index (BHI), a pure data-driven framework for auditing evaluation sets along three orthogonal and complementary axes: (1) Capability Discrimination, measuring how sharply a benchmark separates model performance beyond noise; (2) Anti-Saturation, estimating remaining headroom before ceiling effects erode resolution and thus the benchmark's expected longevity; and (3) Impact, quantifying influence across academic and industrial ecosystems via adoption breadth and practice-shaping power. By distilling 106 validated benchmarks from the technical reports of 91 representative models in 2025, we systematically characterize the evaluation landscape. BHI is the first framework to quantify benchmark health at a macro level, providing a principled basis for benchmark selection and enabling dynamic lifecycle management for next-generation evaluation protocols.

Figures & tables

Appendix figures & tables20 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Benchmarks Are Not Atomic: Composition-Aware LLM Evaluation using BenchHub

    May 31, 2025Eunsu Kim, Haneul Yoo, Guijin Son +3LLM Evaluation