Announcing Artificial Analysis Intelligence Index v5, featuring 2 new benchmarks and 3 upgrades. For the first time, the majority of the…

First reported Oct 28, 2026, 02:11 UTC

Source reports

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… — @ArtificialAnlys (X), Oct 28, 2026, 02:11 UTC
🔥最新！Artificial Analysis刚官宣Intelligence Index v5，基准大升级来了！ 🔹60%评测首次用私有数据集，饱和题彻底滚蛋 🔹新增真实编码（FrontierCode 2.0）+科学Agent（Terminal-Bench-Science）任务 🔹Claude Opus 5.5以58分领跑，GPT-6 Astra 57紧咬，Anthropic/OpenAI包揽前五 🔹开源差距从3分暴增到12分，Kimi K3.1 Pro未发布已46，已发布开源仅32 🔹成本差超13倍，高分不一定贵；Progress… — @NFT_Chen (X), Oct 28, 2026, 03:21 UTC
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… — @testingcatalog (X), Oct 28, 2026, 08:10 UTC

Excerpts are quoted from the linked sources, which own their text.