mlsanityData to 14 Oct 2026

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

arXiv 2411.12990 ↗First posted 20 Nov 2024cs.AI cs.LGcited by 114

Not on the map. Why?

Cited by 21 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

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.

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

49 of 111 references.

References · 49

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  5. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  6. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  7. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  8. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  9. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  10. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,080
  11. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998
  12. 2023AgentBench: Evaluating LLMs as Agentscited by 1,267
37 more
  1. 2023A Survey on Evaluation of Large Language Modelscited by 1,242
  2. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,239
  3. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 817
  4. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 807
  5. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 701
  6. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 690
  7. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 518
  8. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 483
  9. 2022PDEBENCH: An Extensive Benchmark for Scientific Machine Learningcited by 413
  10. 2021BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generationcited by 412
  11. 2021Persistent Anti-Muslim Bias in Large Language Modelscited by 377
  12. 2021AI and the Everything in the Whole Wide World Benchmarkcited by 349
  13. 2023Rethinking Benchmark and Contamination for Language Models with Rephrased Samplescited by 195
  14. 2023Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmarkcited by 182
  15. 2024Lessons from the Trenches on Reproducible Evaluation of Language Modelscited by 179
  16. 2023Time Travel in LLMs: Tracing Data Contamination in Large Language Modelscited by 177
  17. 2022Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AIcited by 171
  18. 2023Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarkscited by 142
  19. 2024When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboardscited by 137
  20. 2024Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systemscited by 96
  21. 2024Investigating Data Contamination for Pre-training Language Modelscited by 91
  22. 2024Red-Teaming for Generative AI: Silver Bullet or Security Theater?cited by 83
  23. 2022Mapping global dynamics of benchmark creation and saturation in artificial intelligencecited by 71
  24. 2022SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehiclescited by 66
  25. 2024Escalation Risks from Language Models in Military and Diplomatic Decision-Makingcited by 63
  26. 2023Rethinking Model Evaluation as Narrowing the Socio-Technical Gapcited by 56
  27. 2023An Open Source Data Contamination Report for Large Language Modelscited by 51
  28. 2020Benchmarking in Optimization: Best Practice and Open Issuescited by 38
  29. 2023Exploring the Sensitivity of LLMs' Decision-Making Capabilities: Insights from Prompt Variation and Hyperparameterscited by 32
  30. 2024ECBD: Evidence-Centered Benchmark Design for NLPcited by 28
  31. 2024Risks from Language Models for Automated Mental Healthcare: Ethics and Structure for Implementationcited by 27
  32. 2023It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performancecited by 26
  33. 2024Human vs. Machine: Behavioral Differences Between Expert Humans and Language Models in Wargame Simulationscited by 21
  34. 2024Machine Learning Data Practices through a Data Curation Lens: An Evaluation Frameworkcited by 18
  35. 2020WordCraft: An Environment for Benchmarking Commonsense Agentscited by 14
  36. 2024Promises and pitfalls of artificial intelligence for legal applicationscited by 14
  37. 2024Measuring Free-Form Decision-Making Inconsistency of Language Models in Military Crisis Simulationscited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 47; 2026: 65.

114 papers.

Sort:

By area:

  1. 2025Measuring what Matters: Construct Validity in Large Language Model Benchmarkscited by 119
  2. 2025Establishing Best Practices for Building Rigorous Agentic Benchmarkscited by 102
  3. 2025A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibilitycited by 93
  4. 2025Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluationcited by 60
  5. 2025Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directionscited by 48
  6. 2026When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturationcited by 33
  7. 2025Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapointscited by 23
  8. 2025On Robustness and Reliability of Benchmark-Based Evaluation of LLMscited by 23
  9. 2024More than Marketing? On the Information Value of AI Benchmarks for Practitionerscited by 17
  10. 2025Potemkin Understanding in Large Language Modelscited by 15
  11. 2025MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Applicationcited by 14
  12. 2025Do Repetitions Matter? Strengthening Reliability in LLM Evaluationscited by 14
38 more
  1. 2025Whose Personae? Synthetic Persona Experiments in LLM Research and Pathways to Transparencycited by 14
  2. 2026Automated Benchmark Auditing for AI Agents and Large Language Modelscited by 12
  3. 2024Evaluation-Driven Development and Operations of LLM Agents: A Process Model and Reference Architecturecited by 11
  4. 2026Benchmarks Saturate When The Model Gets Smarter Than The Judgecited by 11
  5. 2025Benchmarking is Broken -- Don't Let AI be its Own Judgecited by 8
  6. 2026SorryDB: Can AI Provers Complete Real-World Lean Theorems?cited by 8
  7. 2026Computational Hermeneutics: Evaluating generative AI as a cultural technologycited by 8
  8. 2025Critical Foreign Policy Decisions (CFPD)-Benchmark: Measuring Diplomatic Preferences in Large Language Modelscited by 7
  9. 2025Can we Debias Social Stereotypes in AI-Generated Images? Examining Text-to-Image Outputs and User Perceptionscited by 6
  10. 2025Datasheets Aren't Enough: DataRubrics for Automated Quality Metrics and Accountabilitycited by 6
  11. 2025Bench-2-CoP: Can We Trust Benchmarking for EU AI Compliance?cited by 6
  12. 2026What Twelve LLM Agent Benchmark Papers Disclose About Themselves: A Pilot Audit and an Open Scoring Schemacited by 6
  13. 2025Analyzing the Ethical Logic of Eight Large Language Modelscited by 5
  14. 2025Auditing the Ethical Logic of Generative AI Modelscited by 5
  15. 2025Social Bias in Popular Question-Answering Benchmarkscited by 5
  16. 2025Measuring What Matters: Connecting AI Ethics Evaluations to System Attributes, Hazards, and Harmscited by 5
  17. 2026JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessmentcited by 5
  18. 2025Reproducibility Study of Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiationcited by 4
  19. 2025Mapping AI Benchmark Data to Quantitative Risk Estimates Through Expert Elicitationcited by 4
  20. 2025Who Evaluates AI's Social Impacts? Mapping Coverage and Gaps in First and Third Party Evaluationscited by 4
  21. 2025EvalCards: A Framework for Standardized Evaluation Reportingcited by 4
  22. 2026Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agentscited by 4
  23. 2025DICE: A Framework for Dimensional and Contextual Evaluation of Language Modelscited by 3
  24. 2025The Convergent Ethics of AI? Analyzing Moral Foundation Priorities in Large Language Models with a Multi-Framework Approachcited by 3
  25. 2025Benchmarks Are Not Atomic: Composition-Aware LLM Evaluation using BenchHubcited by 3
  26. 2025Risk Management for Mitigating Benchmark Failure Modes: BenchRiskcited by 3
  27. 2025Better Datasets Start From RefineLab: Automatic Optimization for High-Quality Dataset Refinementcited by 3
  28. 2026Agent Benchmarks Fail Public Sector Requirementscited by 3
  29. 2026AI Cartography: Mapping the Latent Landscape of AI Benchmark Ecosystemscited by 3
  30. 2026Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Resultscited by 3
  31. 2026MMGist: A Comprehensive Multimodal Benchmark for 2027cited by 3
  32. 2026The Double Measurement Confound in Agent Benchmarks: De-Scaffolding, Ground-Truth Scoring, and Reliability Beyond the Meancited by 3
  33. 2025VLM@school -- Evaluation of AI image understanding on German middle school knowledgecited by 2
  34. 2025QFrBLiMP: a Quebec-French Benchmark of Linguistic Minimal Pairscited by 2
  35. 2025Culture In a Frame: C3B as a Comic-Based Benchmark for Multimodal Culturally Awarenesscited by 2
  36. 2025ConsistencyAI: A Benchmark to Assess LLMs' Factual Consistency When Responding to Different Demographic Groupscited by 2
  37. 2026Robustness as an Emergent Property of Task Performancecited by 2
  38. 2026Knowledge without Wisdom: Measuring Misalignment between LLMs and Intended Impactcited by 2

50 most cited of 114 All 114 (JSON)