SOURCE RECORD · obs_8d3ac2ffcfbc…

Artificial Analysis · 行业数据来源更新

实质变化收录中观察日期 2026-10-28（日期精度）修订 r2

摘要

行业指数更新：新增多家厂商（StepFun、Thinking Machines、NVIDIA 等）到厂商列表，并调整评估描述。

LLM 生成

LLM 摘要为机器生成，重要信息请回原文核对。

https://daily.maas.click/item/obs_8d3ac2ffcfbc155d11d20a6c37e83b3df1491205e71d0c0edecc0a95bd7e57eb/

此链接指向来源官方页面（非本站内容）。

以下为已保存的变化摘录

证据级别：来源差异（source_diff）——这是抓取到的来源页面变化，其中定价页文本变化不代表已验证的调价。

变更 3 处（旧 → 新）

Artificial Analysis Intelligence Index v4.3.2 incorporates 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1→Artificial Analysis Intelligence Index v4.3.2 incorporates 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, and AA-LCR v1.1
Intelligence, speed and cost of leading language models, based on our independent evaluations→Intelligence, speed, and cost of leading language models, based on our independent evaluations
Weighted average of AA-Omniscience-Decision, HLE-MultiChoice, When2Call and WildGuardTest · Higher is better→Weighted average of AA-Omniscience-Decision, HLE-MultiChoice, When2Call, and WildGuardTest · Higher is better

新增 2 行

AnthropicMetaKimiOpenAIGoogleSpaceXAIXiaomiAlibabaDeepSeekZ AIInclusionAIStepFunMiniMaxMistralInstitute of Foundation ModelsReflectionThinking Machines
StepFunThinking MachinesXiaomiOpenAIAnthropicMistralMetaInclusionAISpaceXAIKimiReflectionGoogleAlibabaZ AIMiniMaxNVIDIADeepSeek

删除 2 行

AnthropicMetaKimiOpenAIGoogleSpaceXAIXiaomiAlibabaDeepSeekZ AIStepFunMiniMaxMistralInstitute of Foundation ModelsReflectionThinking Machines
StepFunThinking MachinesXiaomiOpenAIAnthropicMistralMetaSpaceXAIKimiReflectionGoogleAlibabaZ AIMiniMaxNVIDIADeepSeek