BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices
This work addresses the need for reliable benchmark evaluation to inform model selection and policy in high-stakes AI applications, though it is incremental in providing a structured framework rather than a new paradigm.
The paper tackled the problem of inconsistent quality in AI benchmarks by developing an assessment framework with 46 best practices and evaluating 24 benchmarks, finding large quality differences and common issues like lack of statistical significance reporting and replicability.
AI models are increasingly prevalent in high-stakes environments, necessitating thorough assessment of their capabilities and risks. Benchmarks are popular for measuring these attributes and for comparing model performance, tracking progress, and identifying weaknesses in foundation and non-foundation models. They can inform model selection for downstream tasks and influence policy initiatives. However, not all benchmarks are the same: their quality depends on their design and usability. In this paper, we develop an assessment framework considering 46 best practices across an AI benchmark's lifecycle and evaluate 24 AI benchmarks against it. We find that there exist large quality differences and that commonly used benchmarks suffer from significant issues. We further find that most benchmarks do not report statistical significance of their results nor allow for their results to be easily replicated. To support benchmark developers in aligning with best practices, we provide a checklist for minimum quality assurance based on our assessment. We also develop a living repository of benchmark assessments to support benchmark comparability, accessible at betterbench.stanford.edu.