MODEL HISTORY
DeepSeek V3 0324 指标历史
DeepSeek V3 0324 的公开评测事实历史，共 68 条观测、57 项指标；只记录来源变化，不插值、不合成本站总分。
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。
| 观测日期 | 基准 / 版本 | 指标 | 原始值 | 来源 | 状态 |
|---|---|---|---|---|---|
| Artificial Analysis intelligence component evaluationsv4.3.2 | AutomationBench-AA partial scorefraction | 0.3% | 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 Index | AA-Briefcase overall Eloelo | 66 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3.2 | CritPtfraction | 0.0% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3.2 | GDP.pdf all-passfraction | 1.6% | 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 Index | GDPval-AA v2elo | 56 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3.2 | Humanity's Last Examfraction | 4.7% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis capability indicesv4.3.2 | Intelligence Indexindex | 9.7 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3.2 | AA-LCR v1.1fraction | 40.7% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3.2 | AA-Omniscienceindex | -40.7 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3.2 | AA-Omniscience accuracyfraction | 24.3% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3.2 | AA-Omniscience hallucination ratefraction | 85.9% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3.2 | SciCodefraction | 39.0% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3.2 | Terminal-Bench v4.0fraction | 0.0% | 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 | Eloelo | 275 | Artificial 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 | Eloelo | 92 | Artificial 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 | AA-Briefcase overall Eloelo | 92 | Artificial 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 v2elo | 275 | Artificial 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 | Eloelo | 275 | Artificial 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 | Eloelo | 92 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AutomationBench-AA partial scorefraction | 0.3% | 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 Eloelo | 92 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | CritPtfraction | 0.0% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | GDP.pdf all-passfraction | 1.6% | 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 v2elo | 275 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | Humanity's Last Examfraction | 4.7% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis capability indicesv4.3 | Intelligence Indexindex | 9.7 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AA-LCR v1.1fraction | 40.7% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AA-Omniscienceindex | -40.7 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AA-Omniscience accuracyfraction | 24.3% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AA-Omniscience hallucination ratefraction | 85.9% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | SciCodefraction | 39.0% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | Terminal-Bench v4.0fraction | 0.0% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Agentic Indexindex | 1.6 | 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-AAelo | 326 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Humanity's Last Examfraction | 4.7% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Intelligence Indexindex | 15.2 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-LCRfraction | 41.3% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-Omniscienceindex | -40.7 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Tau Bankingfraction | 4.7% | 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-AAelo | 326 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 缓存读取价格 / 1M Tokenusd_per_1m_tokens | US$0.27 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 输入价格 / 1M Tokenusd_per_1m_tokens | US$0.27 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 输出价格 / 1M Tokenusd_per_1m_tokens | US$1.12 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Agentic Indexindex | 1.5 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 缓存读取价格 / 1M Tokenusd_per_1m_tokens | US$0.705 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis agentic capability indexvunversioned | agentic capability indexindex | 1.5 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis coding capability indexvunversioned | coding capability indexindex | 21.2 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis finance capability indexvunversioned | finance capability indexindex | 11.0 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis strategy capability indexvunversioned | strategy capability indexindex | 11.9 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis legal capability indexvunversioned | legal capability indexindex | 14.1 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis healthcare capability indexvunversioned | healthcare capability indexindex | 10.9 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis engineering capability indexvunversioned | engineering capability indexindex | 19.5 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis economics capability indexvunversioned | economics capability indexindex | 18.2 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Coding Indexindex | 21.2 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 上下文窗口tokens | 128,000 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | CritPtfraction | 0.0% | 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-AAelo | 314 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AA normalizedfraction | 0.0% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GPQA Diamondfraction | 65.5% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Humanity's Last Examfraction | 5.2% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 输入价格 / 1M Tokenusd_per_1m_tokens | US$0.705 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Intelligence Indexindex | 15.4 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-LCRfraction | 41.0% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-Omniscienceindex | -37.6 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 输出价格 / 1M Tokenusd_per_1m_tokens | US$1.285 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | SciCodefraction | 35.8% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Tau Bankingfraction | 4.5% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Terminal-Bench v2.1fraction | 13.9% | Artificial Analysis第三方评测 | 有效 |