# AI Evaluation Should Require Standardized Item-Level Data Releases

arXiv: https://arxiv.org/abs/2604.03244 · HTML: https://mlsanity.com/paper/2604.03244/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 77 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Builds on (most cited first, 30 of 50)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems](https://mlsanity.com/paper/1905.00537/) (2019)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline](https://mlsanity.com/paper/2406.11939/) (2024)
- [Dynabench: Rethinking Benchmarking in NLP](https://mlsanity.com/paper/2104.14337/) (2021)
- [Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics](https://mlsanity.com/paper/2009.10795/) (2020)
- [DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining](https://mlsanity.com/paper/2305.10429/) (2023)
- [Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing](https://mlsanity.com/paper/2001.00973/) (2020)
- [Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models](https://mlsanity.com/paper/2410.07985/) (2024)
- [LiveBench: A Challenging, Contamination-Limited LLM Benchmark](https://mlsanity.com/paper/2406.19314/) (2024)
- [WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild](https://mlsanity.com/paper/2406.04770/) (2024)
- [What Will it Take to Fix Benchmarking in Natural Language Understanding?](https://mlsanity.com/paper/2104.02145/) (2021)
- [Time Travel in LLMs: Tracing Data Contamination in Large Language Models](https://mlsanity.com/paper/2308.08493/) (2023)
- [Adversarial Filters of Dataset Biases](https://mlsanity.com/paper/2002.04108/) (2020)
- [Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks](https://mlsanity.com/paper/2305.10160/) (2023)
- [The Benchmark Lottery](https://mlsanity.com/paper/2107.07002/) (2021)
- [Measuring what Matters: Construct Validity in Large Language Model Benchmarks](https://mlsanity.com/paper/2511.04703/) (2025)
- [Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models](https://mlsanity.com/paper/2103.06922/) (2021)
- [Mapping global dynamics of benchmark creation and saturation in artificial intelligence](https://mlsanity.com/paper/2203.04592/) (2022)
- [Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation](https://mlsanity.com/paper/2502.06559/) (2025)
- [Measurement to Meaning: A Validity-Centered Framework for AI Evaluation](https://mlsanity.com/paper/2505.10573/) (2025)
- [Rethinking Model Evaluation as Narrowing the Socio-Technical Gap](https://mlsanity.com/paper/2306.03100/) (2023)
- [Generalized Low Rank Models](https://mlsanity.com/paper/1410.0342/) (2014)
- [EmoBench: Evaluating the Emotional Intelligence of Large Language Models](https://mlsanity.com/paper/2402.12071/) (2024)

## Built on by (most cited first, 3 of 3)

- [Dimensionality and Measurement Precision in HLE's Multiple-Choice Subset](https://mlsanity.com/paper/2607.27420/) (2026)
- [Are Benchmarks Reliable? Toward Structural Diagnosis via Item-Level Capability Boundaries](https://mlsanity.com/paper/2609.33196/) (2026)
- [ChartBmkAgent: Harness-Governed Multi-Agent Construction of Chart QA Benchmarks from Sparse Error-Taxonomy Specifications](https://mlsanity.com/paper/2610.08106/) (2026)

## Abstract (arXiv)

This position paper argues that standardized item-level benchmark data should become the default infrastructure for AI evaluation. Current evaluations suffer from underspecified item selection, construct misalignment, and poor generalization. The root cause of these failures is a misplaced focus on aggregate model scores. Without item-level evidence, validity claims cannot be assessed, resulting in inflated capability claims, misdirected research, and unwarranted trust in deployed systems. Our position is that designing valid evaluations requires empirical evidence from item-level model responses, and the standardized release of such data should be treated as core AI evaluation infrastructure. Such a release, in addition, enables transparency, replicability, and auditability of evaluation results. To show the norm is both feasible and consequential, we construct OpenEval, an item-level archive of 10M responses across 155k items from widely-used benchmarks, under a unified schema that the AI evaluation community can develop upon. We demonstrate how item-level data can identify low-quality items, document construct misalignment, and recover validity evidence about benchmarks' internal structure. We address objections around contamination and author burden, and show each is tractable relative to the cost of decisions made on claims that cannot be trusted.