Event ·Multi-source

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

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。

Current read

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。

11 sources66° AI heatLast updated 2026/10/28 08:10:08

Evidence

11 sources
Primary sourceTestingCatalog
View source
Related source 1Artificial Analysis
View source
Related source 2kimmonismus
View source
Related source 3The Rundown AI
View source
Related source 5Shubham Saboo
View source
Related source 6Tanishq Abraham (论文推介)
View source
Related source 7Ethan Mollick
View source
Related source 8Andrew Curran
View source
Related source 10VTV Công nghệ
View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.