Event ·Multi-source

Artificial Analysis 六大职业能力指数升级至 v2.0,Claude Opus 5.5 全部第一

Artificial Analysis 将 Finance & Accounting、Strategy & Ops、Legal、Healthcare & Medical、Engineering、Economics 六个 Capability Indexes 更新到 v2.0,与 Intelligence Index v5.0 对齐。各指数普遍上调 Non-Hallucination 和 Agentic Tool Use 的权重,HLE 升级为 HLE-Diamond,AA-Omniscience 升到 v1.1。Engineering 新增 Science 能力,来源是 CritPt v2 (Hard Subset) 和 Terminal-Bench-Science 0.1。结果方面,Claude Opus 5.5 (max) 在全部六个指数排名第一,GPT-6 Astra (max) 在其中三个指数居次席。开源模型中 Kimi K3.1 Pro 在六个指数均领先,排名在第 5 到第 8 名之间。

Current read

选模型别只看综合榜单了,这份 v2.0 按会计、法律、医疗等六个职业分别排名,Claude Opus 5.5 全部第一,开源里 Kimi K3.1 Pro 最强。

11 sources58° AI heatLast updated 2026/11/4 00:47:06

Evidence

11 sources
Primary sourceArtificial Analysis
View source
Related source 1rohanpaul_ai
View source
Related source 5shao__meng
View source
Related source 6Bindu Reddy
View source
Related source 8marktechpost
View source
Related source 9Gorden Sun
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.