Artificial Analysis Index v5: open-weight models fall 12 points behind

Nov 3, 2026
Artificial Analysis released version 5 of its Intelligence Index, with 60% of the evaluation based on private test sets or held out answers. Claude Opus 5.5 leads the ranking with 58 points.

In a post published on October 27, Artificial Analysis released version 5 of its Intelligence Index, with 60% of the evaluation based on private test sets or held out answers. The organization also introduced its Progress Index, which tracks model capability over time on a continuous scale.

The updated index adds FrontierCode 2.0, a private coding benchmark with 132 tasks from open source repositories, and Terminal-Bench-Science, which covers 70 scientific research tasks. It also upgrades HLE-Diamond, AA-Omniscience and CritPt, while retaining four existing evaluations and removing three others.

Anthropic's Claude Opus 5.5 leads the index with 58 points, followed by OpenAI's GPT-6 Astra with 57 and GPT-6.1 Sol with 55. Anthropic and OpenAI hold the top five positions, while Gemini 4 Argon ranks next with 50.

Kimi K3.1 Pro is the highest scoring open weights model at 46, although its weights have not yet been released. Among models with released weights, DeepSeek V4.1 Flash 1017 and GLM-5.3 lead at 32. Across the 10 highest scoring models, the reported cost per task ranges from $0.96 for GPT-6.1 Terra to $13.04 for Claude Fable 5.1.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

Guide
23 AI meeting assistants for financial advisors

23 AI meeting assistants for financial advisors

What each one captures, what it keeps and which records it changes, from standalone apps to the AI built into advisor CRMs.

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.