Claude Opus 4.7 · CharXiv Reasoning(Validation split),CharXiv Reasoning,无工具配置,Accuracy 82.1%(具体成绩公布时间未确认)。见《Introducing Claude Opus 4.7》CharXiv Reasoning 行。 查看成绩条件
Claude Opus 4.7 · CharXiv Reasoning(Validation split),CharXiv Reasoning,Python工具配置,Accuracy 91%(具体成绩公布时间未确认)。见《Introducing Claude Opus 4.7》CharXiv Reasoning 行。 查看成绩条件
CharXiv Reasoning — Opus 4.7: 82.1% no tools; 91.0% with tools.
Claude Opus 4.7 · CharXiv Reasoning(Validation split),CharXiv Reasoning,无工具配置,Accuracy 82.1%(具体成绩公布时间未确认);Claude Opus 4.7 · CharXiv Reasoning(Validation split),CharXiv Reasoning,Python工具配置,Accuracy 91%(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)CharXiv Reasoning 行,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-charxiv/
关联成绩与条件
Claude Opus 4.7 · CharXiv Reasoning 成绩与配置
指标与成绩
配置与评测条件
证据关系
Accuracy82.1%原文 82.1% · 单位 %
公布 未确认
CharXiv Reasoning,无工具
设置
Adaptive thinking, max effort, default sampling; 1,000 validation questions; 5-run average; current maximum image resolution (2576px single dimension, 3.75MP total).
未知项
未另记
工具
禁止工具
推理预算
max
框架
未记录
协议
CharXiv Reasoning; validation split; no tools; adaptive thinking; max effort.
条件
1,000 questions; average over five runs; current image limit up to 2576px on one dimension and 3.75MP total.
Claude Opus 4.7 · CharXiv Reasoning (Validation split) · Main text evidence (ev-op47-charxiv)
Official source for CharXiv Reasoning · Validation split in Claude Opus 4.7. See “Introducing Claude Opus 4.7” at CharXiv Reasoning 行. Evidence ev-op47-charxiv.
Claude Opus 4.7 · CharXiv Reasoning (Validation split), configuration CharXiv Reasoning,无工具, Accuracy 82.1% (exact score publication date unconfirmed). See “Introducing Claude Opus 4.7” at CharXiv Reasoning 行. View score conditions
Claude Opus 4.7 · CharXiv Reasoning (Validation split), configuration CharXiv Reasoning,Python工具, Accuracy 91% (exact score publication date unconfirmed). See “Introducing Claude Opus 4.7” at CharXiv Reasoning 行. View score conditions
CharXiv Reasoning — Opus 4.7: 82.1% no tools; 91.0% with tools.
Unconfirmed · Launch or later disclosure unconfirmed
Collected
Historical basis
No reliable historical version evidence available
Citation text
Claude Opus 4.7 · CharXiv Reasoning (Validation split), configuration CharXiv Reasoning,无工具, Accuracy 82.1% (exact score publication date unconfirmed); Claude Opus 4.7 · CharXiv Reasoning (Validation split), configuration CharXiv Reasoning,Python工具, Accuracy 91% (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), CharXiv Reasoning 行, 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-charxiv/?lang=en
Related scores and conditions
Claude Opus 4.7 · CharXiv Reasoning scores and configurations
Metric and score
Configuration and evaluation conditions
Evidence relation
Accuracy82.1%Reported 82.1% · Unit %
Published Unconfirmed
CharXiv Reasoning,无工具
Settings
Adaptive thinking, max effort, default sampling; 1,000 validation questions; 5-run average; current maximum image resolution (2576px single dimension, 3.75MP total).
Unknowns
none recorded
Tools
Tools forbidden
Reasoning budget
max
Framework
not recorded
Protocol
CharXiv Reasoning; validation split; no tools; adaptive thinking; max effort.
Conditions
1,000 questions; average over five runs; current image limit up to 2576px on one dimension and 3.75MP total.