# Artificial Analysis releases Intelligence Index v5 with mostly private test sets

> Original title: Artificial Analysis Intelligence Index v5 is now live!

- Source: Testing Catalog
- Published: 2026-10-28T08:10:08.000Z
- Bad Influence: https://badinfluence.news/items/ofkwjgmvkxefqnw1fvhg8nhxa
- Original: https://x.com/testingcatalog/status/2115355422034960876

## Summary

Artificial Analysis has released Intelligence Index v5, 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), while the top open-weights model, Kimi K3.1 Pro, scores 46 but has not released its weights.

## Post

Artificial Analysis Intelligence Index v5 is now live!

> It includes 2 new benchmarks and 3 upgrades, and most of the Index is built on private datasets. 

> New benchmarks include FrontierCode 2.0 from Cognition and Terminal-Bench-Science. 

> Claude Opus 5.5 (max) leads at 58, ahead of GPT-6 Astra (max, 57) and GPT-6.1 Sol (max, 55): Anthropic and OpenAI hold the top five models. Gemini 4 Argon (high) is next at 50. 

Claude Code still remains in the lead (no surprise here), while we have quite an accurate distribution for the rest. 

A new chart also shows model release dates 👀

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHVtAWcCXoAEgiBp.jpg&mode=thumb&exp=1793404800&sig=b2b9b7065f7a6053)

## Quoted post @ArtificialAnlys

> Announcing Artificial Analysis Intelligence Index v5, featuring 2 new benchmarks and 3 upgrades. For the first time, the majority of the Index is built on private datasets
> 
> The Artificial Analysis Intelligence Index is our composite measure of model capabilities across tasks reflecting real-world usage today. v5 is our biggest upgrade since v4 launched in January. With v5, 60% of the Index is now based on evaluations with private test sets or held-out answers.
> 
> Alongside Intelligence Index v5, we’re launching the Artificial Analysis Progress Index v1, which tracks model capability over time on one continuous scale.
> 
> New to the Intelligence Index:
> 
> ➤ FrontierCode 2.0: Cognition's newly-launched private benchmark of real-world coding tasks, graded on whether a repository maintainer would merge the agent's change
> 
> ➤ Terminal-Bench-Science: 70 agentic scientific research tasks, run in a terminal environment
> 
> Upgraded:
> 
> ➤ HLE-Diamond (replacing Humanity's Last Exam): a refined 1,000-question version of Humanity's Last Exam, split evenly between reasoning and knowledge questions
> 
> ➤ AA-Omniscience v1.1: An updated dataset with saturated and public set questions removed, new questions added, and ambiguous or erroneous questions revised
> 
> ➤ CritPt v2: a private, 40-question hard subset of CritPt v2, revised by the CritPt authors and run with a code-execution tool
> 
> Staying in the Index: AA-Briefcase, AutomationBench-AA, GDP.pdf and Terminal-Bench 4.0
> 
> Removed from the Index: GDPval-AA v2.1, SciCode, and AA-LCR v1.1
> 
> Key results:
> 
> ➤ Claude Opus 5.5 (max) leads at 58, ahead of GPT-6 Astra (max, 57) and GPT-6.1 Sol (max, 55): Anthropic and OpenAI hold the top five models. Gemini 4 Argon (high) is next at 50
> 
> ➤ The open weights gap widens from 3 points to 12: Kimi K3.1 Pro (weights not yet released) is the top open weights model at 46. Among released weights, DeepSeek V4.1 Flash 1017 (max) and GLM-5.3 (max) lead at 32 - 26 points behind the leader and below Claude Haiku 5.5 (max, 36)
> 
> ➤ Cost per task varies by more than 13x among the leading models: of the 10 highest-scoring models shown, GPT-6.1 Terra (max) is the cheapest at $0.96 per Intelligence Index task and Claude Fable 5.1 (max) the most expensive at $13.04

https://x.com/ArtificialAnlys/status/2115265133467635877