Claude Sonnet 4.6 · Multi-task Indic Language Understanding Benchmark(10 Indic languages plus English · overall average) 89.6% · 附件证据(ev46-milu)

Claude Sonnet 4.6 的 Multi-task Indic Language Understanding Benchmark · 10 Indic languages plus English · overall average 官方出处。Adaptive thinking, max effort · 89.6%。见《Claude Sonnet 4.6 System Card》§2.19.2 Table 2.19.2.A, PDF p.43。证据 ev46-milu。

原文与定位

Claude Sonnet 4.6 · Multi-task Indic Language Understanding Benchmark(10 Indic languages plus English · overall average),Adaptive thinking, max effort配置,Average accuracy 89.6%(具体成绩公布时间未确认)。见《Claude Sonnet 4.6 System Card》§2.19.2 Table 2.19.2.A, PDF p.43。 查看成绩条件

Average | Claude Sonnet 4.6: 89.6%; Average gap to English | Claude Sonnet 4.6: -2.3%; Worst gap to English | Claude Sonnet 4.6: -4.7%
官方材料
Claude Sonnet 4.6 System Card · PDF 第 43 页
定位
附件 · §2.19.2 Table 2.19.2.A, PDF p.43
材料版本
PDF with changelog dated 2026-03-06; 135 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 4.6 · Multi-task Indic Language Understanding Benchmark(10 Indic languages plus English · overall average),Adaptive thinking, max effort配置,Average accuracy 89.6%(具体成绩公布时间未确认)。官方出处 Claude Sonnet 4.6 System Card(附件,PDF with changelog dated 2026-03-06; 135 pages; collected 2026-11-10)§2.19.2 Table 2.19.2.A, PDF p.43,https://www.anthropic.com/claude-sonnet-4-6-system-card#page=43。Benchlog https://benchlog.lekshome.cc/evidence/claude-sonnet-4-6/ev46-milu/

关联成绩与条件

Claude Sonnet 4.6 · Multi-task Indic Language Understanding Benchmark 成绩与配置
指标与成绩配置与评测条件证据关系
Average accuracy89.6%原文 89.6% · 单位 %
公布 未确认
Adaptive thinking, max effort
设置
Adaptive thinking enabled; max effort; default temperature and top_p unless an evaluation specifies otherwise.
未知项
Context window is evaluation-dependent; Table 2.1.A states it does not exceed 1M tokens.
工具
工具条件未记录
推理预算
max
框架
未记录
协议
Provider defaults; structured JSON output; successfully parsed responses only.
条件
11 种语言整体均值,含英语;Adaptive thinking;Max effort。

直接支持该成绩

在排名中查看此成绩