AITOPAI热报
ModelsMulti-source

Artificial Analysis Intelligence Index v5 上线，Claude Opus 5.5 以 58 分居首

TestingCatalog@testingcatalog
Post· 11 sources
View the post
Why we picked it

Claude Opus 5.5 拿下 58 分登顶，GPT-6 Astra 只差 1 分，还新增了两个编程基准，选模型前可以看看这份榜单。

Artificial Analysis 发布 Intelligence Index v5，新增 2 个基准并升级 3 项，大部分数据基于私有数据集。新增基准包括 Cognition 的 FrontierCode 2.0 和 Terminal-Bench-Science。榜单上 Claude Opus 5.5 (max) 以 58 分领先，GPT-6 Astra (max) 得 57 分，GPT-6.1 Sol (max) 得 55 分。Anthropic 与 OpenAI 合计占据前五名，Gemini 4 Argon (high) 以 50 分排在其后，Claude Code 仍保持领先。

Original · TestingCatalog

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 👀

  • Artificial Analysis02:11原文
  • kimmonismus02:56原文
  • The Rundown AI10-26 18:32原文
  • IT之家10-26 23:26原文
  • Shubham Saboo10-27 03:01原文
  • Tanishq Abraham (论文推介)10-27 01:45原文
  • Ethan Mollick10-27 13:01原文
  • Andrew Curran10-27 18:14原文
  • theverge10-26 13:32原文
  • VTV Công nghệ10-26 14:45原文
#Claude Opus 5.5#GPT-6#Gemini 4#Artificial Analysis#基准测试

Keep reading

Recent stories with the same tag or section
ModelsUS vs ChinaMulti-source74°10:17
Chinese contentArtificial Analysis 发布 Intelligence Index v5，新增两个基准并引入私有测试集

模型评测榜 v5 版来了，60% 改用私有题防刷榜，Claude Opus 5.5 拿了第一，开源和闭源差距拉大到 12 分，选模型前可以看看。

#Artificial Analysis#Claude Opus 5.5#GPT-6#Kimi K3.1 Pro
Event
官方账号Artificial Analysis@ArtificialAnlys11 sourcesSource
ModelsBuildersMulti-sourceSelected06:23
Artificial Analysis launches Code2Video-AA video benchmark

The 300x spread in cost per task means the ranking alone is misleading: GPT-6.1 Sol delivers fourth place at 90% less cost than the leader, which changes which model is actually practical for batch video generation. Teams building automated marketing video pipelines can use the five-axis Elo breakdown to match models to their budget and quality needs, and the open-weights results give a concrete quality gap for self-hosting comparisons.

#Code2Video-AA#Claude Opus 5.5#GPT-6.1 Sol#video generation
Event
官方账号Artificial Analysis@ArtificialAnlys3 sourcesSource