Artificial Analysis Intelligence Index v5.0

The Artificial Analysis Intelligence Index v5.0 is a comprehensive evaluation suite that assesses language model capabilities across reasoning, knowledge, math, and programming. It incorporates 9 evaluations, including AA-Briefcase v1.1, AutomationBench-AA, and Terminal-Bench 4.0, and is primarily text-based, English-language. The Intelligence Index is calculated as a weighted average across four categories: Knowledge Work, Coding, Science, and General. The suite also includes additional evaluations for multilingual, visual, and mathematical capabilities, but these are reported separately and not included in the Intelligence Index score. The index is a helpful synthesis of overall language model intelligence, but has limitations and may not apply to every use case.