Introducing v0.5 of the AI Safety Benchmark from MLCommons

25 Dec 2025 · MIT AI Risk Repository – Blog Global

A structured, openly available AI safety evaluation taxonomy gives APS agencies a reference point for assessing chat-based AI system risks.

Key points

Summary

The MIT AI Risk Repository spotlights the MLCommons AI Safety Benchmark v0.5, a taxonomy developed by an industry-academic consortium that defines 13 hazard categories for chat-tuned language models. Seven categories are covered by practical safety test prompts and a grading system, with an open platform (ModelBench) available for evaluation. The item notes that v0.5 has since been superseded by AILuminate v1.0, released February 2025. For APS practitioners evaluating conversational AI tools, the taxonomy offers a structured reference for safety risk scoping, though the more current AILuminate version would be the appropriate starting point.

Implications for Australian agencies

Implications are AI-generated. Starting points, not advice.