Claude Opus 4.7 · SWE-bench Multilingual(300 problems, 9 programming languages) 80.5% · 附件证据(ev-op47-card-swe-multilingual)

Claude Opus 4.7 的 SWE-bench Multilingual · 300 problems, 9 programming languages 官方出处。发布表报告值 · 80.5%。见《Claude Opus 4.7 System Card》Table 8.1.A and §8.2, PDF pp.191-192。证据 ev-op47-card-swe-multilingual。

原文与定位

Claude Opus 4.7 · SWE-bench Multilingual(300 problems, 9 programming languages),发布表报告值配置,Pass rate 80.5%(具体成绩公布时间未确认)。见《Claude Opus 4.7 System Card》Table 8.1.A and §8.2, PDF pp.191-192。 查看成绩条件

SWE-bench Multilingual extends the format to 300 problems across 9 programming languages. Opus 4.7 achieves 80.5%.
官方材料
Claude Opus 4.7 System Card · PDF 第 192 页
定位
附件 · Table 8.1.A and §8.2, PDF pp.191-192
材料版本
Current saved PDF/TXT: 本地留存副本 and current-opus-4-7-system-card.txt; 232 PDF pages; metadata created/modified 2026-04-16 22:11:48 China Standard Time. Full current-card review completed 2026-11-16; this file is not established as launch-day bytes.
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 Opus 4.7 · SWE-bench Multilingual(300 problems, 9 programming languages),发布表报告值配置,Pass rate 80.5%(具体成绩公布时间未确认)。官方出处 Claude Opus 4.7 System Card(附件,Current saved PDF/TXT: 本地留存副本 and current-opus-4-7-system-card.txt; 232 PDF pages; metadata created/modified 2026-04-16 22:11:48 China Standard Time. Full current-card review completed 2026-11-16; this file is not established as launch-day bytes.)Table 8.1.A and §8.2, PDF pp.191-192,https://www.anthropic.com/claude-opus-4-7-system-card#page=192。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-4-7/ev-op47-card-swe-multilingual/

关联成绩与条件

Claude Opus 4.7 · SWE-bench Multilingual 成绩与配置
指标与成绩配置与评测条件证据关系
Pass rate80.5%原文 80.5% · 单位 %
公布 未确认
发布表报告值
设置
System Card §8.1 standard configuration: adaptive thinking at max effort; default temperature/top_p; averaged over 5 trials. Context sizes are evaluation-dependent and do not exceed 1M tokens; retain all section-specific exceptions on their results.
未知项
Per-benchmark tools, context/token cap, resolution, trial count, harness and other exceptions are recorded on each result when stated.
工具
工具条件未记录
推理预算
max
框架
未记录
协议
SWE-bench Multilingual; 300 problems across 9 programming languages.
条件
All SWE-bench variants use the standard configuration with thinking blocks included; average over 5 trials.

直接支持该成绩

在排名中查看此成绩