MODEL HISTORY

Devstral Small (May '25) 指标历史

Devstral Small (May '25) 的公开评测事实历史,共 19 条观测、15 项指标;只记录来源变化,不插值、不合成本站总分。

数据快照:2026-09-09T14:00:04.717Z查看原始来源 ↗
历史观测19仅在事实变化时追加
指标数量15不同量纲保持分离
后续变更4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2026/09/09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”。

APPEND-ONLY FACTS

观测记录

按观测时间倒序;同日多项指标分别保留。

Devstral Small (May '25) 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 evaluationsv4.3CritPtfraction0.0%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3Humanity's Last Examfraction4.0%Artificial Analysis ↗第三方评测有效
Artificial Analysis capability indicesv4.3Intelligence Indexindex8.7Artificial Analysis ↗第三方评测临时 / 估算
Artificial Analysis intelligence component evaluationsv4.3AA-LCR v1.1fraction32.0%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3AA-Omniscienceindex-56.8Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3AA-Omniscience accuracyfraction15.9%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3AA-Omniscience hallucination ratefraction86.4%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1Humanity's Last Examfraction4.0%Artificial Analysis第三方评测有效
Artificial Analysis capability indicesvpublic-model-v1Intelligence Indexindex11.8Artificial Analysis第三方评测临时 / 估算
Artificial Analysis intelligence component evaluationsv4.1AA-LCRfraction30.3%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1AA-Omniscienceindex-56.8Artificial 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 evaluationsv4.1GPQA Diamondfraction43.4%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1Humanity's Last Examfraction4.0%Artificial Analysis第三方评测有效
Artificial Analysis capability indicesvpublic-model-v1Intelligence Indexindex11.8Artificial Analysis第三方评测临时 / 估算
Artificial Analysis intelligence component evaluationsv4.1AA-LCRfraction26.7%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1AA-Omniscienceindex-57.0Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1SciCodefraction24.5%Artificial Analysis第三方评测有效