MODEL HISTORY

Claude Opus 5 (Adaptive Reasoning, High Effort) 指标历史

Claude Opus 5 (Adaptive Reasoning, High Effort) 的公开评测事实历史,共 57 条观测、40 项指标;只记录来源变化,不插值、不合成本站总分。

数据快照:2026-09-18T01:47:51.386Z查看原始来源 ↗
历史观测57仅在事实变化时追加
指标数量40不同量纲保持分离
后续变更17初始观测不计作变更
首次收录2026/07/25本站可追溯起点
最近观测2026/09/18不是模型发布日期

怎样理解这份历史

每条记录对应来源快照中的一个原始指标。同一口径下相同值重复抓取不会制造新记录;数值、临时状态或来源状态变化时追加,核实后的方法版本另立指标身份。首个快照是本站的可追溯起点,不代表该指标第一次对外发布。当前模型来源为 Artificial Analysis。

Index、Elo、百分比等单位不能互相相减,也不会在这里合成为“综合总分”。

GDPval-AA 与 AA-Briefcase 的实时 Elo 现按裁判协议 v4.3.1 单独记录;旧记录的版本、值与日期保留,未区分裁判的旧值仅作历史参考。Intelligence Index 仍为 v4.3,官方用于指数的 Elo 贡献在模型加入时固定,不能用当前实时 Elo 重算指数。核对方法说明 ↗

APPEND-ONLY FACTS

观测记录

按观测时间倒序;同日多项指标分别保留。

Claude Opus 5 (Adaptive Reasoning, High Effort) 的公开评测事实历史
观测日期基准 / 版本指标原始值来源状态
Artificial Analysis GDPval-AA任务 v2 · 裁判 v4.3.1实时 Elo · 裁判协议 v4.3.1Eloelo1629Artificial Analysis ↗第三方评测有效
Artificial Analysis AA-Briefcase来源未标任务版本 · 裁判 v4.3.1实时 Elo · 裁判协议 v4.3.1Eloelo1557Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3.1实时 Elo · 裁判协议 v4.3.1AA-Briefcase overall Eloelo1557Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3.1实时 Elo · 裁判协议 v4.3.1GDPval-AA v2elo1629Artificial Analysis ↗第三方评测有效
Artificial Analysis GDPval-AAv2历史参考 · 原记录未区分当前裁判协议,不作跨协议能力变化比较Eloelo1629Artificial Analysis ↗第三方评测有效
Artificial Analysis AA-Briefcasevsource-unversioned历史参考 · 原记录未区分当前裁判协议,不作跨协议能力变化比较Eloelo1557Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3AutomationBench-AA partial scorefraction53.6%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3历史参考 · 原记录未区分当前裁判协议,不作跨协议能力变化比较AA-Briefcase overall Eloelo1557Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3CritPtfraction28.3%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3GDP.pdf all-passfraction19.6%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3历史参考 · 原记录未区分当前裁判协议,不作跨协议能力变化比较GDPval-AA v2elo1629Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3Humanity's Last Examfraction52.8%Artificial Analysis ↗第三方评测有效
Artificial Analysis capability indicesv4.3Intelligence Indexindex48.2Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3AA-LCR v1.1fraction79.0%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3AA-Omniscienceindex33.7Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3AA-Omniscience accuracyfraction58.9%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3AA-Omniscience hallucination ratefraction61.2%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3SciCodefraction55.4%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3Terminal-Bench v4.0fraction46.0%Artificial Analysis ↗第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1端到端响应时间seconds27.7 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1生成速度tokens_per_second54.4 Token/sModel Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1首个回答 Token 等待seconds18.5 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis capability indicesvpublic-model-v1Agentic Indexindex56.1Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1端到端响应时间seconds26.1 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1历史参考 · 原记录未区分当前裁判协议,不作跨协议能力变化比较GDPval-AAelo1719Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1GDPval-AA normalizedfraction60.9%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1Humanity's Last Examfraction52.8%Artificial Analysis第三方评测有效
Artificial Analysis capability indicesvpublic-model-v1Intelligence Indexindex61.5Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1AA-LCRfraction76.3%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1AA-Omniscienceindex33.7Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1生成速度tokens_per_second55.8 Token/sModel Coordinate repository snapshots第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1Tau Bankingfraction44.7%Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1首个回答 Token 等待seconds17.1 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1端到端响应时间seconds30.0 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1生成速度tokens_per_second54.8 Token/sModel Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1首个回答 Token 等待seconds20.9 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis capability indicesvpublic-model-v1Agentic Indexindex52.1Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1缓存读取价格 / 1M Tokenusd_per_1m_tokensUS$0.5Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1缓存写入价格 / 1M Tokenusd_per_1m_tokensUS$6.25Model Coordinate repository snapshots第三方评测有效
Artificial Analysis capability indicesvpublic-model-v1Coding Indexindex76.5Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1上下文窗口tokens1,000,000Model Coordinate repository snapshots第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1CritPtfraction28.3%Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1端到端响应时间seconds33.4 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1历史参考 · 原记录未区分当前裁判协议,不作跨协议能力变化比较GDPval-AAelo1741Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1GDPval-AA normalizedfraction62.0%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1GPQA Diamondfraction93.7%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1Humanity's Last Examfraction50.7%Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1输入价格 / 1M Tokenusd_per_1m_tokensUS$5Model Coordinate repository snapshots第三方评测有效
Artificial Analysis capability indicesvpublic-model-v1Intelligence Indexindex58.9Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1AA-LCRfraction67.0%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1AA-Omniscienceindex28.1Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1输出价格 / 1M Tokenusd_per_1m_tokensUS$25Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1生成速度tokens_per_second59.4 Token/sModel Coordinate repository snapshots第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1SciCodefraction54.3%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1Tau Bankingfraction32.8%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1Terminal-Bench v2.1fraction87.6%Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1首个回答 Token 等待seconds24.9 秒Model Coordinate repository snapshots第三方评测有效