# Artificial Analysis releases Intelligence Index v5 with new private benchmarks

> Original title: Announcing Artificial Analysis Intelligence Index v5

- Source: Artificial Analysis Articles
- Published: 2026-10-27T04:00:00.000Z
- Bad Influence: https://badinfluence.news/items/dtzbnstxo5hgyz0ox8b76vozz
- Original: https://artificialanalysis.ai/articles/artificial-analysis-intelligence-index-v5

## Summary

Artificial Analysis has released Intelligence Index v5, its biggest update since v4, with 60% of the index now based on private test sets or held-out answers. Claude Opus 5.5 (max) leads at 58, ahead of GPT-6 Astra (max, 57), and the best open weights model, Kimi K3.1 Pro, scores 46 but has not released its weights. The update also adds FrontierCode 2.0 and Terminal-Bench-Science and launches the Progress Index v1 for tracking capability over time.

## Why it matters

The release shows how the benchmark mix, private test sets and effort settings change model rankings and cost, which matters for comparing models.