MODEL HISTORY

Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) 指标历史

Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) 的公开评测事实历史,共 45 条观测、26 项指标;只记录来源变化,不插值、不合成本站总分。

数据快照:2026-09-12T01:07:04.072Z查看原始来源 ↗
历史观测45仅在事实变化时追加
指标数量26不同量纲保持分离
后续变更19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2026/09/12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。

Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) 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 Openness Indexvsource-unversionedModel availabilitypoints4.0Artificial Analysis ↗第三方评测有效
Artificial Analysis Openness Indexvsource-unversionedModel transparencypoints5.5Artificial Analysis ↗第三方评测有效
Artificial Analysis Openness Indexvsource-unversionedOpenness Indexindex52.8Artificial Analysis ↗第三方评测有效
Artificial Analysis Openness Indexvsource-unversionedPosttraining data accesspoints1.0Artificial Analysis ↗第三方评测有效
Artificial Analysis Openness Indexvsource-unversionedPosttraining data licensepoints1.0Artificial Analysis ↗第三方评测有效
Artificial Analysis Openness Indexvsource-unversionedPretraining data accesspoints1.0Artificial Analysis ↗第三方评测有效
Artificial Analysis Openness Indexvsource-unversionedPretraining data licensepoints0.0Artificial 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 evaluationsv4.3Humanity's Last Examfraction7.4%Artificial Analysis ↗第三方评测有效
Artificial Analysis capability indicesv4.3Intelligence Indexindex7.5Artificial Analysis ↗第三方评测临时 / 估算
Artificial Analysis intelligence component evaluationsv4.3AA-Omniscienceindex-44.9Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3AA-Omniscience accuracyfraction20.1%Artificial Analysis ↗第三方评测有效
Artificial Analysis intelligence component evaluationsv4.3AA-Omniscience hallucination ratefraction81.2%Artificial Analysis ↗第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1端到端响应时间seconds50.1 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1生成速度tokens_per_second52.4 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seconds40.5 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seconds50.0 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1Humanity's Last Examfraction7.4%Artificial Analysis第三方评测有效
Artificial Analysis capability indicesvpublic-model-v1Intelligence Indexindex8.9Artificial Analysis第三方评测临时 / 估算
Artificial Analysis intelligence component evaluationsv4.1AA-LCRfraction7.7%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1AA-Omniscienceindex-44.9Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1生成速度tokens_per_second52.5 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seconds40.5 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seconds49.6 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1生成速度tokens_per_second52.9 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seconds40.1 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seconds49.9 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1生成速度tokens_per_second52.6 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seconds40.4 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seconds49.8 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1生成速度tokens_per_second52.7 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seconds40.3 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1上下文窗口tokens128,000Model 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 model aggregatevpublic-model-v1端到端响应时间seconds49.5 秒Model Coordinate repository snapshots第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1GPQA Diamondfraction72.8%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1Humanity's Last Examfraction8.1%Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1输入价格 / 1M Tokenusd_per_1m_tokensUS$0.6Model Coordinate repository snapshots第三方评测有效
Artificial Analysis capability indicesvpublic-model-v1Intelligence Indexindex9.1Artificial Analysis第三方评测临时 / 估算
Artificial Analysis intelligence component evaluationsv4.1AA-LCRfraction7.3%Artificial Analysis第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1AA-Omniscienceindex-45.5Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1输出价格 / 1M Tokenusd_per_1m_tokensUS$1.8Model Coordinate repository snapshots第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1生成速度tokens_per_second53.0 Token/sModel Coordinate repository snapshots第三方评测有效
Artificial Analysis intelligence component evaluationsv4.1SciCodefraction34.7%Artificial Analysis第三方评测有效
Artificial Analysis model aggregatevpublic-model-v1首个回答 Token 等待seconds40.1 秒Model Coordinate repository snapshots第三方评测有效