Artificial Analysis Intelligence Index v4.2

The Artificial Analysis Intelligence Index v4.2 introduces three new evaluations—AA-Briefcase for multi-week agentic knowledge-work tasks, Surge’s GDP.pdf requiring reasoning across 4,592 PDF pages, and GPQA Diamond—while doubling private held-out weighting to 40% to curb gaming. Updated grading infrastructure improves scoring accuracy, and results show Anthropic’s Claude Fable 5.1 leading, OpenAI’s GPT-6 Astra second, with GPT-6 also topping the output-token efficiency frontier.