What AI Benchmarks Actually Measure: Adapting Convergent and Discriminant Validity to Interrogate Fifty-Six AI Benchmarks

• URL: http://arxiv.org/abs/2609.08812v1
• Date: Tue, 08 Sep 2026 14:38:24 GMT
• Title: What AI Benchmarks Actually Measure: Adapting Convergent and Discriminant Validity to Interrogate Fifty-Six AI Benchmarks
• Abstract summary: We adapt convergent and discriminant validity from the social sciences into an approach for interrogating AI benchmarks.<n>We label benchmarks with substantively similar purported concepts to a shared assigned concept.<n>We ask analogous questions at the item level using item response theory (IRT) models.
• Score: 27.62380587346823
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Benchmarks play a central role in the development and governance of models, yet it is often unclear whether they actually measure the concepts they purport to measure (e.g., reasoning, refusal). We adapt convergent and discriminant validity from the social sciences into an approach for interrogating AI benchmarks, applying it to 56 capability and safety benchmarks across 53 models. We label benchmarks with substantively similar purported concepts to a shared assigned concept, and ask whether model rankings on benchmarks with the same assigned concept correlate more strongly than rankings on benchmarks with different assigned concepts. We ask analogous questions at the item level using item response theory (IRT) models. We find that correlations between model rankings on benchmarks with the same assigned safety concepts are often weak, suggesting these concepts may be conceptualized inconsistently across benchmarks. For assigned capability concepts (e.g., reasoning, knowledge), model rankings are often as strongly correlated among benchmarks with the same assigned concept as between benchmarks with different assigned concepts, suggesting these capability concepts may not discriminate well from one another. In some cases, benchmarks that share design elements (e.g., score format) correlate more strongly than benchmarks with the same assigned concept. Finally, some individual benchmarks correlate more strongly with benchmarks assigned a different concept than with benchmarks sharing their own assigned concept, suggesting they may measure a different concept than they purport to. For example, BBQ-accuracy correlates more strongly with benchmarks labeled reasoning than with benchmarks that share its assigned concept, bias. To support future empirical work on benchmark validity, we release our extensive dataset of model outputs and scores at the item- and benchmark-level.

Related papers

• IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation [85.56193980646981]
  We propose IF-RewardBench, a comprehensive meta-evaluation benchmark for instruction-following.<n>For each instruction, we construct a preference graph containing all pairwise preferences among multiple responses.<n>Experiments on IF-RewardBench reveal significant deficiencies in current judge models.
  arXiv  Detail & Related papers  (2026-03-05T02:21:17Z)
• When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation [80.66788281323414]
  We analyze benchmark saturation across 60 Large Language Model (LLM) benchmarks selected from technical reports by major model developers.<n>Our analysis reveals that nearly half of the benchmarks exhibit saturation, with rates increasing as benchmarks age.<n>Expert-curated benchmarks resist saturation better than crowdsourced ones.
  arXiv  Detail & Related papers  (2026-02-18T16:51:37Z)
• Benchmark^2: Systematic Evaluation of LLM Benchmarks [66.2731798872668]
  We propose Benchmark2, a comprehensive framework comprising three complementary metrics.<n>We conduct experiments across 15 benchmarks spanning mathematics, reasoning, and knowledge domains.<n>Our analysis reveals significant quality variations among existing benchmarks and demonstrates that selective benchmark construction can achieve comparable evaluation performance.
  arXiv  Detail & Related papers  (2026-01-07T14:59:03Z)
• Uncovering Competency Gaps in Large Language Models and Their Benchmarks [11.572508874955659]
  We propose a new method that uses sparse autoencoders (SAEs) to automatically uncover both types of gaps.<n>We found that models consistently underperformed on concepts that stand in contrast to sycophantic behaviors.<n>Our method offers a representation-grounded approach to evaluation, enabling concept-level decomposition of benchmark scores.
  arXiv  Detail & Related papers  (2025-12-06T17:39:47Z)
• Benchmark Profiling: Mechanistic Diagnosis of LLM Benchmarks [34.09939383415074]
  Benchmark Profiling decomposes benchmark performance into ten cognitively grounded abilities.<n>It explains why performance gains do not always translate into user-perceived competence.
  arXiv  Detail & Related papers  (2025-09-23T15:32:47Z)
• Deprecating Benchmarks: Criteria and Framework [2.6449913368815516]
  We propose criteria to decide when to fully or partially deprecate benchmarks, and a framework for deprecating benchmarks.<n>Our work aims to advance the state of benchmarking towards rigorous and quality evaluations, especially for frontier models.
  arXiv  Detail & Related papers  (2025-07-08T22:29:06Z)
• ECBD: Evidence-Centered Benchmark Design for NLP [95.50252564938417]
  We propose Evidence-Centered Benchmark Design (ECBD), a framework which formalizes the benchmark design process into five modules. Each module requires benchmark designers to describe, justify, and support benchmark design choices. Our analysis reveals common trends in benchmark design and documentation that could threaten the validity of benchmarks' measurements.
  arXiv  Detail & Related papers  (2024-06-13T00:59:55Z)
• A Backdoor-based Explainable AI Benchmark for High Fidelity Evaluation of Attributions [60.06461883533697]
  We first identify a set of fidelity criteria that reliable benchmarks for attribution methods are expected to fulfill.<n>We then introduce a Backdoor-based eXplainable AI benchmark (BackX) that adheres to the desired fidelity criteria.<n>Our analysis also offers insights into defending against neural Trojans by utilizing the attributions.
  arXiv  Detail & Related papers  (2024-05-02T13:48:37Z)
• Benchmarks for Automated Commonsense Reasoning: A Survey [0.0]
  More than one hundred benchmarks have been developed to test the commonsense knowledge and commonsense reasoning abilities of AI systems. This paper surveys the development and uses of AI commonsense benchmarks.
  arXiv  Detail & Related papers  (2023-02-09T16:34:30Z)
• A Theoretically Grounded Benchmark for Evaluating Machine Commonsense [6.725087407394836]
  Theoretically-answered Commonsense Reasoning (TG-CSR) is based on discriminative question answering, but with questions designed to evaluate diverse aspects of commonsense. TG-CSR is based on a subset of commonsense categories first proposed as a viable theory of commonsense by Gordon and Hobbs. Preliminary results suggest that the benchmark is challenging even for advanced language representation models designed for discriminative CSR question answering tasks.
  arXiv  Detail & Related papers  (2022-03-23T04:06:01Z)
• Do Question Answering Modeling Improvements Hold Across Benchmarks? [84.48867898593052]
  We measure concurrence between 32 QA benchmarks on a set of 20 diverse modeling approaches. Despite years of intense community focus on a small number of benchmarks, the modeling improvements studied hold broadly.
  arXiv  Detail & Related papers  (2021-02-01T18:55:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.