Claude Opus 4.7 · Terminal-Bench(2.0;代理框架按协议区分) 69.4% · 附件证据(ev-op47-card-terminal)

Claude Opus 4.7 的 Terminal-Bench · 2.0;代理框架按协议区分 官方出处。发布表报告值 · 69.4%。见《Claude Opus 4.7 System Card》§8.3, PDF p.193。证据 ev-op47-card-terminal。

原文与定位

Claude Opus 4.7 · Terminal-Bench(2.0;代理框架按协议区分),发布表报告值配置,Mean reward 69.4%(具体成绩公布时间未确认)。见《Claude Opus 4.7 System Card》§8.3, PDF p.193。 查看成绩条件

Claude Opus 4.7 achieved 69.4% mean reward, averaged over 5 attempts for each one of the 89 unique tasks (for a total of 445 trials).
官方材料
Claude Opus 4.7 System Card · PDF 第 193 页
定位
附件 · §8.3, PDF p.193
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 · Terminal-Bench(2.0;代理框架按协议区分),发布表报告值配置,Mean reward 69.4%(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.)§8.3, PDF p.193,https://www.anthropic.com/claude-opus-4-7-system-card#page=193。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-4-7/ev-op47-card-terminal/

关联成绩与条件

Claude Opus 4.7 · Terminal-Bench 成绩与配置
指标与成绩配置与评测条件证据关系
Mean reward69.4%原文 69.4% · 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
Harbor scaffold; Terminus-2 harness; default parser
协议
Terminal-Bench 2.0; Harbor scaffold; Terminus-2 harness; default parser; thinking disabled; mean reward.
条件
89 unique tasks; five attempts per task, 445 trials total; isolated Kubernetes pods with benchmark resource limits and timeouts; production API endpoint.

直接支持该成绩

在排名中查看此成绩