Claude Fable 5.2 登顶智能指数
据 Hacker News 援引 Artificial Analysis 的信息，Claude Fable 5.2 在 Intelligence Index v5.0.1 中获得 65 分，被描述为目前最高分。该综合指数包含九项评测，覆盖知识工作、编程、科学和通用知识。报道还称该模型拥有 100 万 token 上下文窗口，支持文本和图像输入，模型权重不公开。
该基准结果将 Claude Fable 5.2 列为 Artificial Analysis 当前综合排名的首位，为 AI 从业者比较模型能力提供了新参考。
Intelligence Updated
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v5.0.1 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1
No publicly available API
Artificial Analysis Intelligence Index v5.0.1 includes: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1. SeeIntelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Artificial Analysis Intelligence Index v5.0.1 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1
#Claude Fable 5.2#Anthropic#Artificial Analysis Intelligence Index