# Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation

arXiv: https://arxiv.org/abs/2605.30916 · HTML: https://mlsanity.com/paper/2605.30916/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 44 of its 68 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 30 of 44)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [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)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models](https://mlsanity.com/paper/2309.12284/) (2023)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)
- [Are Emergent Abilities of Large Language Models a Mirage?](https://mlsanity.com/paper/2304.15004/) (2023)
- [From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge](https://mlsanity.com/paper/2411.16594/) (2024)
- [Dynabench: Rethinking Benchmarking in NLP](https://mlsanity.com/paper/2104.14337/) (2021)
- [Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks](https://mlsanity.com/paper/2103.14749/) (2021)
- [AI and the Everything in the Whole Wide World Benchmark](https://mlsanity.com/paper/2111.15366/) (2021)
- [NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark](https://mlsanity.com/paper/2310.18018/) (2023)
- [State of What Art? A Call for Multi-Prompt LLM Evaluation](https://mlsanity.com/paper/2401.00595/) (2023)
- [tinyBenchmarks: evaluating LLMs with fewer examples](https://mlsanity.com/paper/2402.14992/) (2024)
- [Measurement and Fairness](https://mlsanity.com/paper/1912.05511/) (2019)
- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [What Will it Take to Fix Benchmarking in Natural Language Understanding?](https://mlsanity.com/paper/2104.02145/) (2021)
- [OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data](https://mlsanity.com/paper/2410.01560/) (2024)
- [Are We Done with MMLU?](https://mlsanity.com/paper/2406.04127/) (2024)
- [ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems](https://mlsanity.com/paper/2505.11831/) (2025)
- [Categorizing Variants of Goodhart's Law](https://mlsanity.com/paper/1803.04585/) (2018)
- [Benchmark Data Contamination of Large Language Models: A Survey](https://mlsanity.com/paper/2406.04244/) (2024)
- [AI Sandbagging: Language Models can Strategically Underperform on Evaluations](https://mlsanity.com/paper/2406.07358/) (2024)
- [The Benchmark Lottery](https://mlsanity.com/paper/2107.07002/) (2021)
- [Observational Scaling Laws and the Predictability of Language Model Performance](https://mlsanity.com/paper/2405.10938/) (2024)
- [BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices](https://mlsanity.com/paper/2411.12990/) (2024)

## Abstract (arXiv)

AI benchmarks have well-documented limitations, with prior work examining contamination, saturation, and construct underspecification. Aggregation has received far less attention: benchmarks are typically summarized by uniformly averaging item-level scores, implicitly treating every test item as equally valuable. We model benchmarking as a multitask principal-agent game and show that the welfare loss from a benchmark is determined jointly by three item-level primitives: alignment with normative welfare priorities, marginal improvability, and performance variance. We translate the theory into an audit framework that ranks items along each of these three axes, and apply it to OLMES items using WORKBank for welfare, the EvoLM 4B suite for improvability, and the PolyPythias 410M panel for variance. The framework surfaces items that are Pareto-inferior within OLMES subject to a pro-worker welfare operationalization. All code is available at https://github.com/stair-lab/principal-agent-benchmarks.