Artificial Analysis Releases Intelligence Index v5 and Progress Index v1

Artificial Analysis announced the launch of Intelligence Index v5 on October 28, 2026, alongside the new Progress Index v1. The Intelligence Index is a composite measure of AI model capabilities across tasks reflecting real-world usage. Version 5 marks the largest upgrade since v4, with 60% of the index now based on evaluations using private test sets or held-out answers.

Two new benchmarks join the index: FrontierCode 2.0, a newly launched private benchmark from Cognition that grades real-world coding tasks on whether a repository maintainer would merge the agent's change, and Terminal-Bench-Science, which includes 70 agentic scientific research tasks run in a terminal environment. Three existing benchmarks were also upgraded: HLE-Diamond replaces Humanity's Last Exam with a refined 1,000-question version split evenly between reasoning and knowledge questions; AA-Omniscience v1.1 removes saturated and public-set questions while adding revised and new questions; and CritPt v2 is now a private 40-question hard subset revised by the authors and run with a code-execution tool.

Progress Index v1 tracks model capabilities over time on a continuous scale. AA-Briefcase, AutomationBench-AA, GDP.pdf and Terminal-Bench 4.0 remain in the index, while GDPval-AA v2.1, SciCode and AA-LCR v1.1 were removed.

Key results show Claude Opus 5.5 (max) leading with a score of 58, ahead of GPT-6 Astra (max) at 57 and GPT-6.1 Sol (max) at 55, with Anthropic and OpenAI holding the top five positions. The gap between open-weights and leading models widened from 3 to 12 points, with Kimi K3.1 Pro (weights not yet released) the top open-weights model at 46. Among released weights, DeepSeek V4.1 Flash 1017 (max) and GLM-5.3 (max) lead at 32.