Claude Sonnet 5.5 · Multi-task Indic Language Understanding Benchmark(10 Indic languages plus English · overall average) 91.6% · 附件证据(safety-e55-milu)
Claude Sonnet 5.5 的 Multi-task Indic Language Understanding Benchmark · 10 Indic languages plus English · overall average 官方出处。Adaptive thinking, max effort · 91.6%。见《Claude Sonnet 5.5 System Card》PDF p.140, Section 8.16.2 and Figure 8.16.2.A。证据 safety-e55-milu。
原文与定位
Claude Sonnet 5.5 · Multi-task Indic Language Understanding Benchmark(10 Indic languages plus English · overall average),Adaptive thinking, max effort配置,Average accuracy 91.6%(具体成绩公布时间未确认)。见《Claude Sonnet 5.5 System Card》PDF p.140, Section 8.16.2 and Figure 8.16.2.A。 查看成绩条件
On MILU, Claude Sonnet 5.5 achieved an average accuracy of 91.6% across 11 languages, behind Claude Opus 5.5 at 93.1% and Claude Fable 5.1 at 93.0%, and ahead of Claude Sonnet 5 at 89.3%.
- 官方材料
- Claude Sonnet 5.5 System Card · PDF 第 140 页
- 定位
- 附件 · PDF p.140, Section 8.16.2 and Figure 8.16.2.A
- 材料版本
- PDF cover dated 2026-09-28; 148 pages; collected 2026-11-10
- 版本公布
- 未确认
- 披露时间
- 未确认 · 首发/后补未确认
- 采集时间
- 历史依据
- 暂无可靠历史版本依据
引用文本
Claude Sonnet 5.5 · Multi-task Indic Language Understanding Benchmark(10 Indic languages plus English · overall average),Adaptive thinking, max effort配置,Average accuracy 91.6%(具体成绩公布时间未确认)。官方出处 Claude Sonnet 5.5 System Card(附件,PDF cover dated 2026-09-28; 148 pages; collected 2026-11-10)PDF p.140, Section 8.16.2 and Figure 8.16.2.A,https://www.anthropic.com/claude-sonnet-5-5-system-card#page=140。Benchlog https://benchlog.lekshome.cc/evidence/claude-sonnet-5-5/safety-e55-milu/
关联成绩与条件
| 指标与成绩 | 配置与评测条件 | 证据关系 |
|---|---|---|
| Average accuracy91.6%原文 91.6% · 单位 % 公布 未确认 | Adaptive thinking, max effort
| 直接支持该成绩 在排名中查看此成绩 |