Artificial Analysis launches v1.1 Capability Indices across six occupations

ArtificialAnlys · x · 2026-09-15

Artificial Analysis released Capability Indices v1.1, combining slices of its Intelligence Index v4.3 evaluations with specialized evaluations under updated domain weights. The indices map ONET occupational tasks to benchmarks weighted by how often each capability appears across occupations, covering six domains: Finance & Accounting, Strategy & Ops, Legal, Healthcare & Medical, Engineering, and Economics. Benchmarks include AA-Omniscience, GDPval-AA v2, AA-Briefcase, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, Terminal-Bench v4.0, CritPt and more. Published scores now reflect the updated weights.

Related event: Artificial Analysis Capability Indices v1.1: Claude Leads All Six Domains(3 posts)→

Original post →

More from Models

Models channel →