Claude Sonnet 5 · OfficeQA(Full set) 73.3% · 附件证据(ev5-officeqa)

Claude Sonnet 5 的 OfficeQA · Full set 官方出处。Standard configuration: adaptive thinking, max effort · 73.3%。见《Claude Sonnet 5 System Card》§8.11.1, PDF p.131。证据 ev5-officeqa。

原文与定位

Claude Sonnet 5 · OfficeQA(Full set),Standard configuration: adaptive thinking, max effort配置,Exact-match accuracy 73.3%(具体成绩公布时间未确认)。见《Claude Sonnet 5 System Card》§8.11.1, PDF p.131。 查看成绩条件

Claude Sonnet 5 achieves 73.3% on OfficeQA and 59.4% on OfficeQA Pro, improving over Claude Sonnet 4.6 (68.7% and 53.4%).
官方材料
Claude Sonnet 5 System Card · PDF 第 131 页
定位
附件 · §8.11.1, PDF p.131
材料版本
PDF with changelog dated 2026-07-10; 146 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 · OfficeQA(Full set),Standard configuration: adaptive thinking, max effort配置,Exact-match accuracy 73.3%(具体成绩公布时间未确认)。官方出处 Claude Sonnet 5 System Card(附件,PDF with changelog dated 2026-07-10; 146 pages; collected 2026-11-10)§8.11.1, PDF p.131,https://www.anthropic.com/claude-sonnet-5-system-card#page=131。Benchlog https://benchlog.lekshome.cc/evidence/claude-sonnet-5/ev5-officeqa/

关联成绩与条件

Claude Sonnet 5 · OfficeQA 成绩与配置
指标与成绩配置与评测条件证据关系
Exact-match accuracy73.3%原文 73.3% · 单位 %
公布 未确认
Standard configuration: adaptive thinking, max effort
设置
Adaptive thinking at max effort; default temperature and top_p; five-trial averages unless otherwise stated.
未知项
Context-window size is evaluation-dependent; standard configuration is 1M tokens.
工具
允许工具
推理预算
max
框架
未记录
协议
OfficeQA exact-match accuracy; mean of five trials.
条件
Agentic evaluation with extracted-text documents and code execution. Episodes reaching per-turn output limit before a final answer are incorrect; about 9–15% do so. Raw-PDF harnesses yield lower scores and are not directly comparable.

直接支持该成绩

在排名中查看此成绩