MODEL HISTORY
GPT-5.5 (high) 指标历史
GPT-5.5 (high) 的公开评测事实历史,共 72 条观测、47 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 | 1372 | 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 | 1089 | 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 | 1089 | 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 | 1372 | 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 | 1372 | 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 | 1089 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AutomationBench-AA partial scorefraction | 44.3% | 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 | 1089 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | CritPtfraction | 25.4% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | GDP.pdf all-passfraction | 22.6% | 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 | 1372 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | Humanity's Last Examfraction | 45.0% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis capability indicesv4.3 | Intelligence Indexindex | 37.3 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AA-LCR v1.1fraction | 84.3% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AA-Omniscienceindex | 18.8 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AA-Omniscience accuracyfraction | 57.0% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | AA-Omniscience hallucination ratefraction | 89.1% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | SciCodefraction | 56.1% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.3 | Terminal-Bench v4.0fraction | 9.1% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 端到端响应时间seconds | 36.2 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 | 76.2 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 | 29.6 秒 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Agentic Indexindex | 45.9 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 端到端响应时间seconds | 28.2 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 | 1459 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AA normalizedfraction | 48.0% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Humanity's Last Examfraction | 45.0% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Intelligence Indexindex | 54.7 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-LCRfraction | 79.0% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-Omniscienceindex | 18.8 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 79.0 Token/s | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Tau Bankingfraction | 36.7% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 21.9 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 | 34.8 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 | 80.0 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 | 28.5 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seconds | 25.7 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 | 1467 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AA normalizedfraction | 48.4% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 73.8 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 | 18.9 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 | 27.5 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 | 74.8 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 | 20.8 秒 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Agentic Indexindex | 43.5 | 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$0.5 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis agentic capability indexvunversioned | agentic capability indexindex | 43.5 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis coding capability indexvunversioned | coding capability indexindex | 71.6 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis finance capability indexvunversioned | finance capability indexindex | 45.0 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis strategy capability indexvunversioned | strategy capability indexindex | 45.0 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis legal capability indexvunversioned | legal capability indexindex | 46.9 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis healthcare capability indexvunversioned | healthcare capability indexindex | 39.9 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis engineering capability indexvunversioned | engineering capability indexindex | 54.3 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis economics capability indexvunversioned | economics capability indexindex | 51.7 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Coding Indexindex | 71.6 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 上下文窗口tokens | 922,000 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | CritPtfraction | 25.4% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 端到端响应时间seconds | 37.3 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 | 1471 | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AA normalizedfraction | 48.6% | Artificial Analysis ↗第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GPQA Diamondfraction | 93.2% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Humanity's Last Examfraction | 43.0% | 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$5 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Intelligence Indexindex | 53.1 | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-LCRfraction | 73.3% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-Omniscienceindex | 18.4 | 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$30 | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 78.1 Token/s | Model Coordinate repository snapshots第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | SciCodefraction | 55.9% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Tau Bankingfraction | 29.5% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Terminal-Bench v2.1fraction | 79.4% | Artificial Analysis第三方评测 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 30.9 秒 | Model Coordinate repository snapshots第三方评测 | 有效 |