Claude Opus 4.5 · Vending-Bench(2) $4,967.06 USD · 附件证据(ev-op45-card-vending)

Claude Opus 4.5 的 Vending-Bench · 2 官方出处。Vending-Bench 2, High effort · $4,967.06 USD。见《Claude Opus 4.5 System Card》PDF pp.29-30, §2.11 Vending-Bench 2。证据 ev-op45-card-vending。

原文与定位

Claude Opus 4.5 · Vending-Bench(2),Vending-Bench 2, High effort配置,Final bank balance $4,967.06 USD(具体成绩公布时间未确认)。见《Claude Opus 4.5 System Card》PDF pp.29-30, §2.11 Vending-Bench 2。 查看成绩条件

Claude Opus 4.5 achieved a final balance of $4,967.06.
官方材料
Claude Opus 4.5 System Card · PDF 第 30 页
定位
附件 · PDF pp.29-30, §2.11 Vending-Bench 2
材料版本
Current saved PDF/TXT: 本地留存副本 and .txt; cover November 2025, change log 2025-11-24; current binary is not established as launch-day bytes; fully reviewed 2026-11-16.
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 4.5 · Vending-Bench(2),Vending-Bench 2, High effort配置,Final bank balance $4,967.06 USD(具体成绩公布时间未确认)。官方出处 Claude Opus 4.5 System Card(附件,Current saved PDF/TXT: 本地留存副本 and .txt; cover November 2025, change log 2025-11-24; current binary is not established as launch-day bytes; fully reviewed 2026-11-16.)PDF pp.29-30, §2.11 Vending-Bench 2,https://www.anthropic.com/claude-opus-4-5-system-card#page=30。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-4-5/ev-op45-card-vending/

关联成绩与条件

Claude Opus 4.5 · Vending-Bench 成绩与配置
指标与成绩配置与评测条件证据关系
Final bank balance$4,967.06 USD原文 $4,967.06 · 单位 USD
公布 未确认
Vending-Bench 2, High effort
设置
High effort; 8,192 reasoning tokens per turn; benchmark-managed context, Claude context editing disabled.
未知项
Run count and sampling settings are not stated.
工具
工具条件未记录
推理预算
high · 思考预算 8,192 reasoning tokens per turn
框架
未记录
协议
Vending-Bench 2; one-year simulated vending machine business; $500 starting balance.
条件
High effort, 8,192 reasoning tokens per turn; the benchmark manages context and Claude context editing was disabled.

直接支持该成绩

在排名中查看此成绩