MODEL HISTORY
GPT-5.6 Luna (Non-reasoning) 指标历史
GPT-5.6 Luna (Non-reasoning) 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 | 3.2 秒 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 193.3 Token/s | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 0.6 秒 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Agentic Indexindex | 22.0 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 缓存读取价格 / 1M Tokenusd_per_1m_tokens | US$0.1 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 缓存写入价格 / 1M Tokenusd_per_1m_tokens | US$1.25 | 有效 | |
| Artificial Analysis agentic capability indexvunversioned | agentic capability indexindex | 22.0 | 有效 | |
| Artificial Analysis coding capability indexvunversioned | coding capability indexindex | 39.3 | 有效 | |
| Artificial Analysis finance capability indexvunversioned | finance capability indexindex | 21.1 | 有效 | |
| Artificial Analysis legal capability indexvunversioned | legal capability indexindex | 21.6 | 有效 | |
| Artificial Analysis healthcare capability indexvunversioned | healthcare capability indexindex | 20.3 | 有效 | |
| Artificial Analysis engineering capability indexvunversioned | engineering capability indexindex | 31.3 | 有效 | |
| Artificial Analysis economics capability indexvunversioned | economics capability indexindex | 25.3 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Coding Indexindex | 39.3 | 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 | 0.3% | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 端到端响应时间seconds | 3.1 秒 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AAelo | 1068 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AA normalizedfraction | 28.4% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GPQA Diamondfraction | 64.5% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Humanity's Last Examfraction | 6.7% | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 输入价格 / 1M Tokenusd_per_1m_tokens | US$1 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Intelligence Indexindex | 26.6 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-LCRfraction | 36.3% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-Omniscienceindex | -25.1 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 输出价格 / 1M Tokenusd_per_1m_tokens | US$6 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 生成速度tokens_per_second | 202.9 Token/s | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | SciCodefraction | 39.9% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Tau Bankingfraction | 9.1% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Terminal-Bench v2.1fraction | 39.0% | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 首个回答 Token 等待seconds | 0.6 秒 | 有效 |