AISafetyBenchExplorer: A Metric-Aware Catalogue of AI Safety Benchmarks Reveals Fragmented Measurement and Weak Benchmark Governance

• URL: http://arxiv.org/abs/2604.12875v2
• Date: Thu, 23 Apr 2026 13:27:05 GMT
• Title: AISafetyBenchExplorer: A Metric-Aware Catalogue of AI Safety Benchmarks Reveals Fragmented Measurement and Weak Benchmark Governance
• Abstract summary: We present AISafetyBenchExplorer, a structured catalogue of 195 AI safety benchmarks released between 2018 and 2026.<n>We identify a central structural problem: benchmark proliferation has outpaced measurement standardization.<n>At the metric level, the catalogue shows that familiar labels such as accuracy, F1 score, safety score, and aggregate benchmark scores often conceal materially different judges, aggregation rules, and threat models.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid expansion of large language model (LLM) safety evaluation has produced a substantial benchmark ecosystem, but not a correspondingly coherent measurement ecosystem. We present AISafetyBenchExplorer, a structured catalogue of 195 AI safety benchmarks released between 2018 and 2026, organized through a multi-sheet schema that records benchmark-level metadata, metric-level definitions, benchmark-paper metadata, and repository activity. This design enables meta-analysis not only of what benchmarks exist, but also of how safety is operationalized, aggregated, and judged across the literature. Using the updated catalogue, we identify a central structural problem: benchmark proliferation has outpaced measurement standardization. The current landscape is dominated by medium-complexity benchmarks (94/195), while only 7 benchmarks occupy the Popular tier. The workbook further reports strong concentration around English-only evaluation (165/195), evaluation-only resources (170/195), stale GitHub repositories (137/195), stale Hugging Face datasets (96/195), and heavy reliance on arXiv preprints among benchmarks with known venue metadata. At the metric level, the catalogue shows that familiar labels such as accuracy, F1 score, safety score, and aggregate benchmark scores often conceal materially different judges, aggregation rules, and threat models. We argue that the field's main failure mode is fragmentation rather than scarcity. Researchers now have many benchmark artifacts, but they often lack a shared measurement language, a principled basis for benchmark selection, and durable stewardship norms for post publication maintenance. AISafetyBenchExplorer addresses this gap by providing a traceable benchmark catalogue, a controlled metadata schema, and a complexity taxonomy that together support more rigorous benchmark discovery, comparison, and meta-evaluation.

Related papers

• Unsteady Metrics and Benchmarking Cultures of AI Model Builders [0.2238062620016784]
  Benchmarking-Cultures-25 is a dataset of 231 benchmarks highlighted across 139 model releases in 2025 from 11 major AI builders.<n>We develop a unified taxonomy mapping terminology to a shared framework of measured signals based on what benchmark authors claim to measure.
  arXiv  Detail & Related papers  (2026-05-13T22:39:10Z)
• Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents [6.787194586338237]
  We present the first systematic analysis dedicated to agent safety benchmarks as evaluation instruments.<n>A coverage matrix reveals broad risk coverage but limited methodological convergence, while the taxonomy analysis shows a behavioral-benchmark core concentrated in sandboxed, constrained, and often safety-only evaluation.<n>Across the landscape, we find that benchmark choice can yield contradictory safety conclusions, coverage counts often overstate evaluation depth, environment fidelity shapes reported safety, the field disproportionately tests externally imposed rather than agent-internal risks, metric fragmentation limits comparison, and remains effectively unbenchmarked.
  arXiv  Detail & Related papers  (2026-04-11T04:25:19Z)
• DEP: A Decentralized Large Language Model Evaluation Protocol [51.3646001384887]
  Decentralized Evaluation Protocol (DEP) is a decentralized yet unified and standardized evaluation framework.<n>By decoupling users, LLMs, and benchmarks, DEP enables modular, plug-and-play evaluation.<n>We develop DEP Toolkit, a protocol-compatible toolkit that supports features such as breakpoint resume, concurrent requests, and congestion control.
  arXiv  Detail & Related papers  (2026-03-01T16:10:16Z)
• 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)
• Fantastic Bugs and Where to Find Them in AI Benchmarks [28.604919035475188]
  We introduce a framework for systematic benchmark revision that leverages statistical analysis of response patterns to flag potentially invalid questions.<n>Our approach builds on a core assumption commonly used in AI evaluations that the mean score sufficiently summarizes model performance.<n>Across nine widely used benchmarks, our method guides expert review to identify problematic questions with up to 84% precision.
  arXiv  Detail & Related papers  (2025-11-20T22:49:21Z)
• Do Large Language Model Benchmarks Test Reliability? [66.1783478365998]
  We investigate how well current benchmarks quantify model reliability.<n>Motivated by this gap in the evaluation of reliability, we propose the concept of so-called platinum benchmarks.<n>We evaluate a wide range of models on these platinum benchmarks and find that, indeed, frontier LLMs still exhibit failures on simple tasks.
  arXiv  Detail & Related papers  (2025-02-05T18:58:19Z)
• How Should We Build A Benchmark? Revisiting 274 Code-Related Benchmarks For LLMs [60.25940747590386]
  We propose How2Bench, which is comprised of a 55-criteria checklist as a set of guidelines to govern the development of code-related benchmarks comprehensively.<n>We profiled 274 benchmarks released within the past decade and found concerning issues.<n>Nearly 70% of the benchmarks did not take measures for data quality assurance; over 10% did not even open source or only partially open source.
  arXiv  Detail & Related papers  (2025-01-18T09:51:57Z)
• SeCodePLT: A Unified Platform for Evaluating the Security of Code GenAI [58.29510889419971]
  Existing benchmarks for evaluating the security risks and capabilities of code-generating large language models (LLMs) face several key limitations.<n>We introduce a general and scalable benchmark construction framework that begins with manually validated, high-quality seed examples and expands them via targeted mutations.<n>Applying this framework to Python, C/C++, and Java, we build SeCodePLT, a dataset of more than 5.9k samples spanning 44 CWE-based risk categories and three security capabilities.
  arXiv  Detail & Related papers  (2024-10-14T21:17:22Z)
• MENLI: Robust Evaluation Metrics from Natural Language Inference [26.53850343633923]
  Recently proposed BERT-based evaluation metrics for text generation perform well on standard benchmarks but are vulnerable to adversarial attacks. We develop evaluation metrics based on Natural Language Inference (NLI) We show that our NLI based metrics are much more robust to the attacks than the recent BERT-based metrics.
  arXiv  Detail & Related papers  (2022-08-15T16:30:14Z)
• Exploring and Analyzing Machine Commonsense Benchmarks [0.13999481573773073]
  We argue that the lack of a common vocabulary for aligning these approaches' metadata limits researchers in their efforts to understand systems' deficiencies. We describe our initial MCS Benchmark Ontology, an common vocabulary that formalizes benchmark metadata.
  arXiv  Detail & Related papers  (2020-12-21T19:01:55Z)
• GO FIGURE: A Meta Evaluation of Factuality in Summarization [131.1087461486504]
  We introduce GO FIGURE, a meta-evaluation framework for evaluating factuality evaluation metrics. Our benchmark analysis on ten factuality metrics reveals that our framework provides a robust and efficient evaluation. It also reveals that while QA metrics generally improve over standard metrics that measure factuality across domains, performance is highly dependent on the way in which questions are generated.
  arXiv  Detail & Related papers  (2020-10-24T08:30:20Z)

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.