AI RESEARCH
AISafetyBenchExplorer: A Metric-Aware Catalogue of AI Safety Benchmarks Reveals Fragmented Measurement and Weak Benchmark Governance
arXiv CS.AI
•
ArXi:2604.12875v1 Announce Type: new 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.