Artificial Analysis Intelligence Index v5

The Artificial Analysis Intelligence Index v5 has been released, featuring 2 new benchmarks and 3 upgrades. The Index now relies on private datasets for 60% of its evaluations. The Index includes 7 benchmarks: AA-Briefcase, AutomationBench-AA, GDP.pdf, Terminal-Bench 4.0, FrontierCode 2.0, Terminal-Bench-Science, and CritPt v2. The Index tracks model capabilities across tasks reflecting real-world usage. The top 5 models are Claude Opus 5.5, GPT-6 Astra, GPT-6.1 Sol, Gemini 4 Argon, and Anthropic's model. The open weights gap between the top models has widened to 3 points. The Artificial Analysis Progress Index v1 tracks model capability over time on a continuous scale.