MODEL HISTORY
Claude Sonnet 5 (Adaptive Reasoning, Max Effort) 指标历史
Claude Sonnet 5 (Adaptive Reasoning, Max Effort) 的公开评测事实历史，共 31 条观测、28 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。相同值重复抓取不会制造新记录；只有数值、临时状态或移除状态发生变化时才追加。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。
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。
| 观测日期 | 基准 / 版本 | 指标 | 原始值 | 状态 |
|---|---|---|---|---|
| Artificial Analysis model aggregatevpublic-model-v1 | 端到端响应时间seconds | 197.8 秒 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 83.9 Token/s | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 191.9 秒 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Agentic Indexindex | 46.7 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 缓存读取价格 / 1M Tokenusd_per_1m_tokens | US$0.2 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 缓存写入价格 / 1M Tokenusd_per_1m_tokens | US$2.5 | 有效 | |
| Artificial Analysis agentic capability indexvunversioned | agentic capability indexindex | 46.7 | 有效 | |
| Artificial Analysis coding capability indexvunversioned | coding capability indexindex | 71.5 | 有效 | |
| Artificial Analysis finance capability indexvunversioned | finance capability indexindex | 43.9 | 有效 | |
| Artificial Analysis legal capability indexvunversioned | legal capability indexindex | 45.4 | 有效 | |
| Artificial Analysis healthcare capability indexvunversioned | healthcare capability indexindex | 40.9 | 有效 | |
| Artificial Analysis engineering capability indexvunversioned | engineering capability indexindex | 54.8 | 有效 | |
| Artificial Analysis economics capability indexvunversioned | economics capability indexindex | 52.4 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Coding Indexindex | 71.5 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 上下文窗口tokens | 1,000,000 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | CritPtfraction | 16.9% | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 端到端响应时间seconds | 185.8 秒 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AAelo | 1607 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AA normalizedfraction | 55.4% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GPQA Diamondfraction | 91.1% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Humanity's Last Examfraction | 39.6% | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 输入价格 / 1M Tokenusd_per_1m_tokens | US$2 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Intelligence Indexindex | 53.4 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-LCRfraction | 70.7% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-Omniscienceindex | 15.3 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 输出价格 / 1M Tokenusd_per_1m_tokens | US$10 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 74.3 Token/s | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | SciCodefraction | 53.6% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Tau Bankingfraction | 28.2% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Terminal-Bench v2.1fraction | 80.5% | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 179.0 秒 | 有效 |