Artificial Analysis 六项能力指数升级至 v2.0
Artificial Analysis 表示已将其六项 Capability Indexes 升级至 v2.0，与 Artificial Analysis Intelligence Index v5.0 的评测保持一致，并更强调非幻觉（Non-Hallucination）与智能体工具使用（Agentic Tool Use）。这些指数将 O*NET 职业任务映射到代表性基准，并按相关能力在职业中出现的频率进行加权，涵盖金融与会计、战略与运营、法律、医疗、工程与经济六个方向。报告所列改动包括升级 HLE 和 AA-Omniscience、从智能体知识工作中移除 GDPval-AA、为工程类新增基于 CritPt v2 和 Terminal-Bench-Science 0.1 的 Science 能力，以及在智能体编程中加入 FrontierCode 2.0。报告称 Claude Opus 5.5（max）在六项指数中均居首位。这些细节和排名结果均来自所提供的单一报告。
We’ve updated the six Artificial Analysis Capability Indexes to v2.0, aligning them with evaluations from the Artificial Analysis Intelligence Index v5.0 and placing greater emphasis on Non-Hallucination and Agentic Tool Use
The Capability Indexes map tasks from O*NET occupations to benchmarks that represent them, weighting each benchmark by how often its capability appears in that occupation. There are six indexes: Finance & Accounting, Strategy & Ops, Legal, Healthcare & Medical, Engineering, and Economics.
Key changes:
➤ Finance & Accounting: increased weight on Non-Hallucination, upgraded HLE to HLE-Diamond and AA-Omniscience to v1.1, removed GDPval-AA from Agentic Knowledge Work, and removed AA-LCR from Long-Context
➤ Strategy & Ops: increased weight on Agentic Tool Use, added Non-Hallucination and upgraded AA-Omniscience to v1.1, removed GDPval-AA from Agentic Knowledge Work, and removed AA-LCR from Long-Context
➤ Legal: increased weight on Non-Hallucination, upgraded HLE to HLE-Diamond and AA-Omniscience to v1.1, removed GDPval-AA from Agentic Knowledge Work, and removed AA-LCR from Long-Context
#Artificial Analysis#Claude Opus 5.5#GPT-6 Astra#Kimi K3.1 Pro#MiniMax-M3.1-Flash#DeepSeek V4.1 Flash#HLE-Diamond#AA-Omniscience#CritPt v2#Terminal-Bench-Science 0.1#FrontierCode 2.0#GDPval-AA