Artificial Analysis announced Intelligence Index v5 on Oct 28, 2026, calling it its biggest upgrade since v4 in January.

Artificial Analysis announced Intelligence Index v5 on Oct 28, 2026, calling it its biggest upgrade since v4 in January.

60% of the Index is now based on private test sets or held-out answers. New are FrontierCode 2.0 from Cognition, real-world coding tasks graded on whether a maintainer would merge the change, and Terminal-Bench-Science, 70 agentic science tasks in a terminal. Upgraded are HLE-Diamond replacing Humanity's Last Exam, AA-Omniscience v1.1, and CritPt v2 hard subset. Staying are AA-Briefcase, AutomationBench-AA, GDP.pdf and Terminal-Bench 4.0. Removed are GDPval-AA v2.1, SciCode and AA-LCR v1.1.

It also launched Progress Index v1 to track capability over time on one continuous scale, with weights detailed here.

Rankings: Claude Opus 5.5 (max) leads at 58, ahead of GPT-6 Astra (max, 57) and GPT-6.1 Sol (max, 55), with Anthropic and OpenAI holding the top five and Gemini 4 Argon (high) next at 50. The open-weights gap widened from 3 to 12 points: Kimi K3.1 Pro at 46 with weights unreleased, while released-weights leaders DeepSeek V4.1 Flash 1017 (max) and GLM-5.3 (max) are at 32.

Cost per task varies over 13x among the top 10: GPT-6.1 Terra (max) cheapest at $0.96, Claude Fable 5.1 (max) most expensive at $13.04.