Claude Opus 4.7 · Terminal-Bench(2.0;代理框架按协议区分) 69.4% · 主文证据(ev-op47-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《Introducing Claude Opus 4.7》Terminal-Bench 2.0 行;本地留存副本 line 135。证据 ev-op47-terminal。
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《Introducing Claude Opus 4.7》Terminal-Bench 2.0 行;本地留存副本 line 135。 查看成绩条件
Terminal-Bench 2.0 — Opus 4.7: 69.4%; Terminus-2, thinking disabled, 5 attempts per task.
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 Introducing Claude Opus 4.7(主文,官方发布页;本地保存 HTML/TXT 与主表 PNG:本地留存副本、本地留存副本、本地留存副本;原文发布日期 2026-04-16,当前修订时间未知)Terminal-Bench 2.0 行;本地留存副本 line 135,https://www.anthropic.com/news/claude-opus-4-7#testing-claude-opus-47。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-4-7/ev-op47-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.
89 unique tasks; five attempts per task, 445 trials total; isolated Kubernetes pods with benchmark resource limits and timeouts; production API endpoint.
Claude Opus 4.7 · Terminal-Bench (2.0;代理框架按协议区分) 69.4% · Main text evidence (ev-op47-terminal)
Official source for Terminal-Bench · 2.0;代理框架按协议区分 in Claude Opus 4.7. 发布表报告值 · 69.4%. See “Introducing Claude Opus 4.7” at Terminal-Bench 2.0 行;本地留存副本 line 135. Evidence ev-op47-terminal.
Claude Opus 4.7 · Terminal-Bench (2.0;代理框架按协议区分), configuration 发布表报告值, Mean reward 69.4% (exact score publication date unconfirmed). See “Introducing Claude Opus 4.7” at Terminal-Bench 2.0 行;本地留存副本 line 135. View score conditions
Terminal-Bench 2.0 — Opus 4.7: 69.4%; Terminus-2, thinking disabled, 5 attempts per task.
Unconfirmed · Launch or later disclosure unconfirmed
Collected
Historical basis
No reliable historical version evidence available
Citation text
Claude Opus 4.7 · Terminal-Bench (2.0;代理框架按协议区分), configuration 发布表报告值, Mean reward 69.4% (exact score publication date unconfirmed). Official source: Introducing Claude Opus 4.7 (Main text, 官方发布页;本地保存 HTML/TXT 与主表 PNG:本地留存副本、本地留存副本、本地留存副本;原文发布日期 2026-04-16,当前修订时间未知), Terminal-Bench 2.0 行;本地留存副本 line 135, https://www.anthropic.com/news/claude-opus-4-7#testing-claude-opus-47. Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-4-7/ev-op47-terminal/?lang=en
Related scores and conditions
Claude Opus 4.7 · Terminal-Bench scores and configurations
Metric and score
Configuration and evaluation conditions
Evidence relation
Mean reward69.4%Reported 69.4% · Unit %
Published Unconfirmed
发布表报告值
Settings
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.
Unknowns
Per-benchmark tools, context/token cap, resolution, trial count, harness and other exceptions are recorded on each result when stated.
89 unique tasks; five attempts per task, 445 trials total; isolated Kubernetes pods with benchmark resource limits and timeouts; production API endpoint.