MODEL HISTORY

JT-4.1 Flash 236B A21B 指标历史

JT-4.1 Flash 236B A21B 的公开评测事实历史,共 48 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:2026-09-20T01:21:54.000Z查看原始来源 ↗
历史观测48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8初始观测不计作变更
首次收录2026/07/21本站可追溯起点
最近观测2026/09/20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”。

本页含 AA Intelligence Index v4.3.2 的完整方法观测。该版本对 GDPval-AA v2.1 与 AA-Briefcase v1.1 的 Elo 拟合使用 Crowd-BT;旧 v4.3 与 v4.3.1 点位仍保留各自版本、值与日期,不能将跨版本差额解释成模型能力变化。查看当前方法边界 →

本页还含来源记录为裁判协议 v4.3.1 的独立实时 Elo 历史。它是当时的单项榜单协议,不被当前完整 Index v4.3.2 重标;未区分裁判协议的更早 Elo 仅作历史参考。Intelligence Index 中的 Elo 贡献在模型加入时固定,不能用独立实时 Elo 重算指数。核对 AA 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。

JT-4.1 Flash 236B A21B 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 intelligence component evaluationsv4.3.2CritPtfraction0.0%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3.2当前完整方法 v4.3.2 · Crowd-BT Elo;不由实时 Elo 重算 Intelligence IndexGDPval-AA v2elo1114Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3.2Humanity's Last Examfraction17.8%Artificial Analysis ↗第三方评测有效
Artificial Analysis capability indicesv4.3.2Intelligence Indexindex27.3Artificial Analysis ↗第三方评测临时 / 估算
Artificial Analysis intelligence component evaluationsv4.3.2AA-LCR v1.1fraction71.3%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3.2AA-Omniscienceindex-8.8Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3.2AA-Omniscience accuracyfraction24.3%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3.2AA-Omniscience hallucination ratefraction43.7%Artificial Analysis ↗第三方评测有效
Artificial Analysis GDPval-AA任务 v2 · 裁判 v4.3.1历史参考 · 裁判协议 v4.3.1;不与当前完整方法 v4.3.2 跨协议比较Eloelo1193Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3.1历史参考 · 裁判协议 v4.3.1;不与当前完整方法 v4.3.2 跨协议比较GDPval-AA v2elo1193Artificial 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Eloelo1193Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3CritPtfraction0.0%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 v2elo1193Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3Humanity's Last Examfraction17.8%Artificial Analysis ↗第三方评测有效
Artificial Analysis capability indicesv4.3Intelligence Indexindex27.3Artificial Analysis ↗第三方评测临时 / 估算
Artificial Analysis intelligence component evaluationsv4.3AA-LCR v1.1fraction71.3%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3AA-Omniscienceindex-8.8Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3AA-Omniscience accuracyfraction24.3%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3AA-Omniscience hallucination ratefraction43.7%Artificial Analysis ↗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-AAelo1264Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1GDPval-AA normalizedfraction38.2%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1Humanity's Last Examfraction17.8%Artificial Analysis第三方评测有效
Artificial Analysis capability indicesvpublic-model-v1Intelligence Indexindex39.9Artificial Analysis第三方评测临时 / 估算
Artificial Analysis intelligence component evaluationsv4.1AA-LCRfraction70.3%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1AA-Omniscienceindex-8.8Artificial Analysis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-AAelo1266Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1GDPval-AA normalizedfraction38.3%Artificial Analysis ↗第三方评测有效
Artificial Analysis capability indicesvpublic-model-v1Agentic Indexindex34.9Artificial Analysis第三方评测有效
Artificial Analysis agentic capability indexvunversionedagentic capability indexindex34.9Artificial Analysis第三方评测有效
Artificial Analysis coding capability indexvunversionedcoding capability indexindex52.4Artificial Analysis第三方评测有效
Artificial Analysis finance capability indexvunversionedfinance capability indexindex30.0Artificial Analysis第三方评测有效
Artificial Analysis legal capability indexvunversionedlegal capability indexindex29.9Artificial Analysis第三方评测有效
Artificial Analysis healthcare capability indexvunversionedhealthcare capability indexindex28.6Artificial Analysis第三方评测有效
Artificial Analysis engineering capability indexvunversionedengineering capability indexindex40.0Artificial Analysis第三方评测有效
Artificial Analysis economics capability indexvunversionedeconomics capability indexindex36.6Artificial Analysis第三方评测有效
Artificial Analysis capability indicesvpublic-model-v1Coding Indexindex52.4Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1上下文窗口tokens256,000Model Coordinate repository snapshots第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1CritPtfraction0.0%Artificial Analysis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-AAelo1265Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1GDPval-AA normalizedfraction38.2%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1GPQA Diamondfraction84.5%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1Humanity's Last Examfraction16.1%Artificial Analysis第三方评测有效
Artificial Analysis capability indicesvpublic-model-v1Intelligence Indexindex38.8Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1AA-LCRfraction58.7%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1AA-Omniscienceindex-10.1Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1SciCodefraction38.2%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1Tau Bankingfraction28.0%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1Terminal-Bench v2.1fraction59.6%Artificial Analysis第三方评测有效