MODEL HISTORY
Kimi K2.6 指标历史
Kimi K2.6 的公开评测事实历史，共 84 条观测、54 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”。
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。
| 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 v4.3.1 | Eloelo | 1096 | 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实时 Elo · 裁判协议 v4.3.1 | Eloelo | 824 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3.1实时 Elo · 裁判协议 v4.3.1 | AA-Briefcase overall Eloelo | 824 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3.1实时 Elo · 裁判协议 v4.3.1 | GDPval-AA v2elo | 1096 | 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 | 824 | 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 | 1096 | 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 | 824 | 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 | 1096 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis capability indicesv4.3 | Intelligence Indexindex | 27.5 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | Terminal-Bench v4.0fraction | 0.5% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis Openness Indexvsource-unversioned | Model availabilitypoints | 4.0 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis Openness Indexvsource-unversioned | Model transparencypoints | 2.0 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis Openness Indexvsource-unversioned | Openness Indexindex | 33.3 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis Openness Indexvsource-unversioned | Posttraining data accesspoints | 0.0 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis Openness Indexvsource-unversioned | Posttraining data licensepoints | 0.0 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis Openness Indexvsource-unversioned | Pretraining data accesspoints | 0.0 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis Openness Indexvsource-unversioned | Pretraining data licensepoints | 0.0 | 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 | 1115 | 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 | 820 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AutomationBench-AA partial scorefraction | 13.0% | 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 | AA-Briefcase overall Eloelo | 820 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | CritPtfraction | 8.0% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | GDP.pdf all-passfraction | 13.0% | 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 v2elo | 1115 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | Humanity's Last Examfraction | 37.5% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis capability indicesv4.3 | Intelligence Indexindex | 31.3 | Artificial Analysis ↗第三方评测 | 临时 / 估算 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AA-LCR v1.1fraction | 81.0% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AA-Omniscienceindex | 5.3 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AA-Omniscience accuracyfraction | 32.6% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AA-Omniscience hallucination ratefraction | 40.5% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | SciCodefraction | 51.5% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 端到端响应时间seconds | 130.7 秒 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 38.7 Token/s | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 117.8 秒 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Agentic Indexindex | 31.2 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 端到端响应时间seconds | 126.0 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-AAelo | 1191 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AA normalizedfraction | 34.5% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Humanity's Last Examfraction | 37.5% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Intelligence Indexindex | 45.1 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-LCRfraction | 76.7% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-Omniscienceindex | 5.3 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 40.2 Token/s | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Tau Bankingfraction | 23.3% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 113.6 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seconds | 115.8 秒 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 43.9 Token/s | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 104.4 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seconds | 158.9 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-AAelo | 1188 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AA normalizedfraction | 34.4% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 31.7 Token/s | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 143.2 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seconds | 104.5 秒 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 48.7 Token/s | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 94.3 秒 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Agentic Indexindex | 30.3 | 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$0.16 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis agentic capability indexvunversioned | agentic capability indexindex | 30.3 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis coding capability indexvunversioned | coding capability indexindex | 61.8 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis finance capability indexvunversioned | finance capability indexindex | 34.9 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis strategy capability indexvunversioned | strategy capability indexindex | 32.1 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis legal capability indexvunversioned | legal capability indexindex | 35.3 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis healthcare capability indexvunversioned | healthcare capability indexindex | 33.2 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis engineering capability indexvunversioned | engineering capability indexindex | 47.2 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis economics capability indexvunversioned | economics capability indexindex | 46.7 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Coding Indexindex | 61.8 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 上下文窗口tokens | 256,000 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | CritPtfraction | 8.0% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 端到端响应时间seconds | 99.1 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-AAelo | 1189 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AA normalizedfraction | 34.5% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GPQA Diamondfraction | 91.1% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Humanity's Last Examfraction | 35.9% | 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$0.95 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Intelligence Indexindex | 44.2 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-LCRfraction | 69.7% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-Omniscienceindex | 6.4 | 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$4 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 51.4 Token/s | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | SciCodefraction | 53.5% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Tau Bankingfraction | 20.6% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Terminal-Bench v2.1fraction | 65.9% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 89.4 秒 | Model Coordinate repository snapshots第三方评测 | 有效 |