Intelligence Index v4.2 at a glance
Artificial Analysis added two knowledge-work evaluations, removed a saturated science quiz, and doubled the private share of the index to 40%.
What changed with Intelligence Index v4.2
On September 4, 2026, Artificial Analysis released v4.2 of its Intelligence Index. It added AA-Briefcase, an agentic knowledge-work test with a private set, and GDP.pdf from Surge AI, which checks reasoning over long documents spanning 4,592 pages. GPQA Diamond was removed because top models had saturated it.
Intelligence Index v4.2 in numbers
Values are copied from the linked source on the date shown. They are not IA Compa measurements.
- Share of index on private held-out testsas of · Source for Share of index on private held-out tests: artificialanalysis.ai (opens in a new tab)
- 40%
Why Intelligence Index v4.2 matters for businesses
Private, held-out test sets rose to 40% of the index, double the v4.1 share, and several graders were tightened. For agencies, the new document-reasoning and office-task tests are a closer match to the reports, contracts, and spreadsheets that business automations actually handle.
Sources for this story
- Artificial Analysis Intelligence Index v4.2 (opens in a new tab)Official
Artificial Analysis · artificialanalysis.ai
Last verified: . IA Compa summarizes public announcements for business readers. We are not affiliated with the companies mentioned. Always confirm details, pricing, and availability with the official source.
- #benchmarks
- #artificial-analysis
- #intelligence-index
