Benchmark Health Index: A Systematic Framework for Benchmarking the Benchmarks of LLMs
This addresses the issue of benchmark erosion for the LLM community, providing a principled tool for benchmark selection and management, though it is incremental as it builds on existing evaluation concerns.
The paper tackles the problem of unreliable benchmarks for Large Language Models (LLMs) by introducing the Benchmark Health Index (BHI), a data-driven framework that audits benchmarks across three axes, resulting in a systematic characterization of 106 benchmarks from 91 models in 2025.
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.