MODEL HISTORY
Motif 3 (Beta) 指标历史
Motif 3 (Beta) 的公开评测事实历史,共 21 条观测、21 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 capability indicesvpublic-model-v1 | Agentic Indexindex | 34.9 | 有效 | |
| Artificial Analysis agentic capability indexvunversioned | agentic capability indexindex | 34.9 | 有效 | |
| Artificial Analysis coding capability indexvunversioned | coding capability indexindex | 62.0 | 有效 | |
| Artificial Analysis finance capability indexvunversioned | finance capability indexindex | 33.0 | 有效 | |
| Artificial Analysis legal capability indexvunversioned | legal capability indexindex | 32.6 | 有效 | |
| Artificial Analysis healthcare capability indexvunversioned | healthcare capability indexindex | 32.2 | 有效 | |
| Artificial Analysis engineering capability indexvunversioned | engineering capability indexindex | 44.6 | 有效 | |
| Artificial Analysis economics capability indexvunversioned | economics capability indexindex | 43.0 | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Coding Indexindex | 62.0 | 有效 | |
| Artificial Analysis model aggregatevpublic-model-v1 | 上下文窗口tokens | 262,144 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | CritPtfraction | 6.0% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AAelo | 1259 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GDPval-AA normalizedfraction | 38.0% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | GPQA Diamondfraction | 86.9% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Humanity's Last Examfraction | 38.2% | 有效 | |
| Artificial Analysis capability indicesvpublic-model-v1 | Intelligence Indexindex | 44.1 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-LCRfraction | 61.3% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | AA-Omniscienceindex | -17.3 | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | SciCodefraction | 44.3% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Tau Bankingfraction | 28.9% | 有效 | |
| Artificial Analysis intelligence component evaluationsv4.1 | Terminal-Bench v2.1fraction | 70.8% | 有效 |