# BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices

arXiv: https://arxiv.org/abs/2411.12990 · HTML: https://mlsanity.com/paper/2411.12990/

## Key facts

- Cited by 114 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 111 references that are in the map.
- First posted on arXiv 20 Nov 2024.

## Builds on (most cited first, 30 of 49)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [BBQ: A Hand-Built Bias Benchmark for Question Answering](https://mlsanity.com/paper/2110.08193/) (2021)
- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [Leveraging Procedural Generation to Benchmark Reinforcement Learning](https://mlsanity.com/paper/1912.01588/) (2019)
- [PDEBENCH: An Extensive Benchmark for Scientific Machine Learning](https://mlsanity.com/paper/2210.07182/) (2022)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [Persistent Anti-Muslim Bias in Large Language Models](https://mlsanity.com/paper/2101.05783/) (2021)
- [AI and the Everything in the Whole Wide World Benchmark](https://mlsanity.com/paper/2111.15366/) (2021)
- [Rethinking Benchmark and Contamination for Language Models with Rephrased Samples](https://mlsanity.com/paper/2311.04850/) (2023)
- [Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark](https://mlsanity.com/paper/2304.03279/) (2023)
- [Lessons from the Trenches on Reproducible Evaluation of Language Models](https://mlsanity.com/paper/2405.14782/) (2024)
- [Time Travel in LLMs: Tracing Data Contamination in Large Language Models](https://mlsanity.com/paper/2308.08493/) (2023)
- [Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI](https://mlsanity.com/paper/2204.01075/) (2022)
- [Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks](https://mlsanity.com/paper/2305.10160/) (2023)

## Built on by (most cited first, 30 of 114)

- [Measuring what Matters: Construct Validity in Large Language Model Benchmarks](https://mlsanity.com/paper/2511.04703/) (2025)
- [Establishing Best Practices for Building Rigorous Agentic Benchmarks](https://mlsanity.com/paper/2507.02825/) (2025)
- [A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility](https://mlsanity.com/paper/2504.07086/) (2025)
- [Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation](https://mlsanity.com/paper/2502.06559/) (2025)
- [Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions](https://mlsanity.com/paper/2510.25445/) (2025)
- [When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation](https://mlsanity.com/paper/2602.16763/) (2026)
- [Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints](https://mlsanity.com/paper/2503.01747/) (2025)
- [On Robustness and Reliability of Benchmark-Based Evaluation of LLMs](https://mlsanity.com/paper/2509.04013/) (2025)
- [More than Marketing? On the Information Value of AI Benchmarks for Practitioners](https://mlsanity.com/paper/2412.05520/) (2024)
- [Potemkin Understanding in Large Language Models](https://mlsanity.com/paper/2506.21521/) (2025)
- [MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application](https://mlsanity.com/paper/2506.14028/) (2025)
- [Do Repetitions Matter? Strengthening Reliability in LLM Evaluations](https://mlsanity.com/paper/2509.24086/) (2025)
- [Whose Personae? Synthetic Persona Experiments in LLM Research and Pathways to Transparency](https://mlsanity.com/paper/2512.00461/) (2025)
- [Automated Benchmark Auditing for AI Agents and Large Language Models](https://mlsanity.com/paper/2605.26079/) (2026)
- [Evaluation-Driven Development and Operations of LLM Agents: A Process Model and Reference Architecture](https://mlsanity.com/paper/2411.13768/) (2024)
- [Benchmarks Saturate When The Model Gets Smarter Than The Judge](https://mlsanity.com/paper/2601.19532/) (2026)
- [Benchmarking is Broken -- Don't Let AI be its Own Judge](https://mlsanity.com/paper/2510.07575/) (2025)
- [SorryDB: Can AI Provers Complete Real-World Lean Theorems?](https://mlsanity.com/paper/2603.02668/) (2026)
- [Computational Hermeneutics: Evaluating generative AI as a cultural technology](https://mlsanity.com/paper/2604.16403/) (2026)
- [Critical Foreign Policy Decisions (CFPD)-Benchmark: Measuring Diplomatic Preferences in Large Language Models](https://mlsanity.com/paper/2503.06263/) (2025)
- [Can we Debias Social Stereotypes in AI-Generated Images? Examining Text-to-Image Outputs and User Perceptions](https://mlsanity.com/paper/2505.20692/) (2025)
- [Datasheets Aren't Enough: DataRubrics for Automated Quality Metrics and Accountability](https://mlsanity.com/paper/2506.01789/) (2025)
- [Bench-2-CoP: Can We Trust Benchmarking for EU AI Compliance?](https://mlsanity.com/paper/2508.05464/) (2025)
- [What Twelve LLM Agent Benchmark Papers Disclose About Themselves: A Pilot Audit and an Open Scoring Schema](https://mlsanity.com/paper/2605.21404/) (2026)
- [Analyzing the Ethical Logic of Eight Large Language Models](https://mlsanity.com/paper/2501.08951/) (2025)
- [Auditing the Ethical Logic of Generative AI Models](https://mlsanity.com/paper/2504.17544/) (2025)
- [Social Bias in Popular Question-Answering Benchmarks](https://mlsanity.com/paper/2505.15553/) (2025)
- [Measuring What Matters: Connecting AI Ethics Evaluations to System Attributes, Hazards, and Harms](https://mlsanity.com/paper/2510.10339/) (2025)
- [JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment](https://mlsanity.com/paper/2605.25240/) (2026)
- [Reproducibility Study of Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation](https://mlsanity.com/paper/2502.16242/) (2025)

## Abstract (arXiv)

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.