Claude Opus 5.5 · Toolathlon-Verified(June 2026 finalized release) · 附件证据(ev-op55-card-toolathlon)
Claude Opus 5.5 的 Toolathlon-Verified · June 2026 finalized release 官方出处。见《Claude Opus 5.5 System Card》§8.14.5, pp.210-211, Table 8.14.5.A。证据 ev-op55-card-toolathlon。
Claude Opus 5.5 · Toolathlon-Verified(June 2026 finalized release),Toolathlon-Verified max effort with safeguards配置,Pass@1 77.8%(具体成绩公布时间未确认)。见《Claude Opus 5.5 System Card》§8.14.5, pp.210-211, Table 8.14.5.A。 查看成绩条件
Claude Opus 5.5 · Toolathlon-Verified(June 2026 finalized release),Toolathlon-Verified max effort with safeguards配置,Pass@3 82.4%(具体成绩公布时间未确认)。见《Claude Opus 5.5 System Card》§8.14.5, pp.210-211, Table 8.14.5.A。 查看成绩条件
Claude Opus 5.5 · Toolathlon-Verified(June 2026 finalized release),Toolathlon-Verified max effort with safeguards配置,Pass³ 72.2%(具体成绩公布时间未确认)。见《Claude Opus 5.5 System Card》§8.14.5, pp.210-211, Table 8.14.5.A。 查看成绩条件
Claude Opus 5.5 · Toolathlon-Verified(June 2026 finalized release),Toolathlon-Verified max effort with safeguards配置,Average assistant turns 26.9 turns(具体成绩公布时间未确认)。见《Claude Opus 5.5 System Card》§8.14.5, pp.210-211, Table 8.14.5.A。 查看成绩条件
Claude Opus 5.5 | Pass@1 77.8 | Pass@3 82.4 | Pass³ 72.2 | Avg. turns 26.9.
官方当前 System Card;封面日期 2026-09-22;本地 PDF/TXT:本地留存副本、current-opus-5-5-system-card.txt;230 页全文核读;当前修订时间未知
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 5.5 · Toolathlon-Verified(June 2026 finalized release),Toolathlon-Verified max effort with safeguards配置,Pass@1 77.8%(具体成绩公布时间未确认);Claude Opus 5.5 · Toolathlon-Verified(June 2026 finalized release),Toolathlon-Verified max effort with safeguards配置,Pass@3 82.4%(具体成绩公布时间未确认);Claude Opus 5.5 · Toolathlon-Verified(June 2026 finalized release),Toolathlon-Verified max effort with safeguards配置,Pass³ 72.2%(具体成绩公布时间未确认);Claude Opus 5.5 · Toolathlon-Verified(June 2026 finalized release),Toolathlon-Verified max effort with safeguards配置,Average assistant turns 26.9 turns(具体成绩公布时间未确认)。官方出处 Claude Opus 5.5 System Card(附件,官方当前 System Card;封面日期 2026-09-22;本地 PDF/TXT:本地留存副本、current-opus-5-5-system-card.txt;230 页全文核读;当前修订时间未知)§8.14.5, pp.210-211, Table 8.14.5.A,https://www.anthropic.com/claude-opus-5-5-system-card#page=211。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5-5/ev-op55-card-toolathlon/
关联成绩与条件
Claude Opus 5.5 · Toolathlon-Verified 成绩与配置
指标与成绩
配置与评测条件
证据关系
Pass@177.8%原文 77.8% Pass@1 · 单位 %
公布 未确认
Toolathlon-Verified max effort with safeguards
设置
Adaptive thinking/max effort; production safety classifiers and sandbox-escape monitor enabled; three trials per task; all stopped trials counted as failures.
未知项
未另记
工具
工具条件未记录
推理预算
max
框架
未记录
协议
Toolathlon-Verified June 2026; 108 tasks; Pass@1 averaged over three trials per task; adaptive thinking/max effort.
条件
Production safety classifier and sandbox-escape monitor enabled; all stopped trials counted as failures. Source-wide conditions: Toolathlon-Verified June 2026; 108 tasks; three trials per task; adaptive thinking/max effort; safety classifiers enabled; one classifier stop and six sandbox-escape-monitor stops counted as failures.
Adaptive thinking/max effort; production safety classifiers and sandbox-escape monitor enabled; three trials per task; all stopped trials counted as failures.
未知项
未另记
工具
工具条件未记录
推理预算
max
框架
未记录
协议
Toolathlon-Verified June 2026; 108 tasks; at least one of three trials correct; adaptive thinking/max effort.
条件
Production safety classifier and sandbox-escape monitor enabled; all stopped trials counted as failures. Source-wide conditions: Toolathlon-Verified June 2026; 108 tasks; three trials per task; adaptive thinking/max effort; safety classifiers enabled; one classifier stop and six sandbox-escape-monitor stops counted as failures.
Adaptive thinking/max effort; production safety classifiers and sandbox-escape monitor enabled; three trials per task; all stopped trials counted as failures.
未知项
未另记
工具
工具条件未记录
推理预算
max
框架
未记录
协议
Toolathlon-Verified June 2026; 108 tasks; all three trials correct; adaptive thinking/max effort.
条件
Production safety classifier and sandbox-escape monitor enabled; all stopped trials counted as failures. Source-wide conditions: Toolathlon-Verified June 2026; 108 tasks; three trials per task; adaptive thinking/max effort; safety classifiers enabled; one classifier stop and six sandbox-escape-monitor stops counted as failures.
Average assistant turns26.9 turns原文 26.9 turns · 单位 turns
公布 未确认
Toolathlon-Verified max effort with safeguards
设置
Adaptive thinking/max effort; production safety classifiers and sandbox-escape monitor enabled; three trials per task; all stopped trials counted as failures.
未知项
未另记
工具
工具条件未记录
推理预算
max
框架
未记录
协议
Toolathlon-Verified June 2026; average assistant turns per trajectory across 108 tasks and three trials.
条件
Trajectory length is a separate reported metric, not a success rate. Source-wide conditions: Toolathlon-Verified June 2026; 108 tasks; three trials per task; adaptive thinking/max effort; safety classifiers enabled; one classifier stop and six sandbox-escape-monitor stops counted as failures.
Claude Opus 5.5 · Toolathlon-Verified (June 2026 finalized release) · Attachment evidence (ev-op55-card-toolathlon)
Official source for Toolathlon-Verified · June 2026 finalized release in Claude Opus 5.5. See “Claude Opus 5.5 System Card” at §8.14.5, pp.210-211, Table 8.14.5.A. Evidence ev-op55-card-toolathlon.
Claude Opus 5.5 · Toolathlon-Verified (June 2026 finalized release), configuration Toolathlon-Verified max effort with safeguards, Pass@1 77.8% (exact score publication date unconfirmed). See “Claude Opus 5.5 System Card” at §8.14.5, pp.210-211, Table 8.14.5.A. View score conditions
Claude Opus 5.5 · Toolathlon-Verified (June 2026 finalized release), configuration Toolathlon-Verified max effort with safeguards, Pass@3 82.4% (exact score publication date unconfirmed). See “Claude Opus 5.5 System Card” at §8.14.5, pp.210-211, Table 8.14.5.A. View score conditions
Claude Opus 5.5 · Toolathlon-Verified (June 2026 finalized release), configuration Toolathlon-Verified max effort with safeguards, Pass³ 72.2% (exact score publication date unconfirmed). See “Claude Opus 5.5 System Card” at §8.14.5, pp.210-211, Table 8.14.5.A. View score conditions
Claude Opus 5.5 · Toolathlon-Verified (June 2026 finalized release), configuration Toolathlon-Verified max effort with safeguards, Average assistant turns 26.9 turns (exact score publication date unconfirmed). See “Claude Opus 5.5 System Card” at §8.14.5, pp.210-211, Table 8.14.5.A. View score conditions
Claude Opus 5.5 | Pass@1 77.8 | Pass@3 82.4 | Pass³ 72.2 | Avg. turns 26.9.
官方当前 System Card;封面日期 2026-09-22;本地 PDF/TXT:本地留存副本、current-opus-5-5-system-card.txt;230 页全文核读;当前修订时间未知
Version published
Unconfirmed
Disclosure date
Unconfirmed · Launch or later disclosure unconfirmed
Collected
Historical basis
No reliable historical version evidence available
Citation text
Claude Opus 5.5 · Toolathlon-Verified (June 2026 finalized release), configuration Toolathlon-Verified max effort with safeguards, Pass@1 77.8% (exact score publication date unconfirmed); Claude Opus 5.5 · Toolathlon-Verified (June 2026 finalized release), configuration Toolathlon-Verified max effort with safeguards, Pass@3 82.4% (exact score publication date unconfirmed); Claude Opus 5.5 · Toolathlon-Verified (June 2026 finalized release), configuration Toolathlon-Verified max effort with safeguards, Pass³ 72.2% (exact score publication date unconfirmed); Claude Opus 5.5 · Toolathlon-Verified (June 2026 finalized release), configuration Toolathlon-Verified max effort with safeguards, Average assistant turns 26.9 turns (exact score publication date unconfirmed). Official source: Claude Opus 5.5 System Card (Attachment, 官方当前 System Card;封面日期 2026-09-22;本地 PDF/TXT:本地留存副本、current-opus-5-5-system-card.txt;230 页全文核读;当前修订时间未知), §8.14.5, pp.210-211, Table 8.14.5.A, https://www.anthropic.com/claude-opus-5-5-system-card#page=211. Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5-5/ev-op55-card-toolathlon/?lang=en
Related scores and conditions
Claude Opus 5.5 · Toolathlon-Verified scores and configurations
Metric and score
Configuration and evaluation conditions
Evidence relation
Pass@177.8%Reported 77.8% Pass@1 · Unit %
Published Unconfirmed
Toolathlon-Verified max effort with safeguards
Settings
Adaptive thinking/max effort; production safety classifiers and sandbox-escape monitor enabled; three trials per task; all stopped trials counted as failures.
Unknowns
none recorded
Tools
Tool access not recorded
Reasoning budget
max
Framework
not recorded
Protocol
Toolathlon-Verified June 2026; 108 tasks; Pass@1 averaged over three trials per task; adaptive thinking/max effort.
Conditions
Production safety classifier and sandbox-escape monitor enabled; all stopped trials counted as failures. Source-wide conditions: Toolathlon-Verified June 2026; 108 tasks; three trials per task; adaptive thinking/max effort; safety classifiers enabled; one classifier stop and six sandbox-escape-monitor stops counted as failures.
Adaptive thinking/max effort; production safety classifiers and sandbox-escape monitor enabled; three trials per task; all stopped trials counted as failures.
Unknowns
none recorded
Tools
Tool access not recorded
Reasoning budget
max
Framework
not recorded
Protocol
Toolathlon-Verified June 2026; 108 tasks; at least one of three trials correct; adaptive thinking/max effort.
Conditions
Production safety classifier and sandbox-escape monitor enabled; all stopped trials counted as failures. Source-wide conditions: Toolathlon-Verified June 2026; 108 tasks; three trials per task; adaptive thinking/max effort; safety classifiers enabled; one classifier stop and six sandbox-escape-monitor stops counted as failures.
Adaptive thinking/max effort; production safety classifiers and sandbox-escape monitor enabled; three trials per task; all stopped trials counted as failures.
Unknowns
none recorded
Tools
Tool access not recorded
Reasoning budget
max
Framework
not recorded
Protocol
Toolathlon-Verified June 2026; 108 tasks; all three trials correct; adaptive thinking/max effort.
Conditions
Production safety classifier and sandbox-escape monitor enabled; all stopped trials counted as failures. Source-wide conditions: Toolathlon-Verified June 2026; 108 tasks; three trials per task; adaptive thinking/max effort; safety classifiers enabled; one classifier stop and six sandbox-escape-monitor stops counted as failures.
Average assistant turns26.9 turnsReported 26.9 turns · Unit turns
Published Unconfirmed
Toolathlon-Verified max effort with safeguards
Settings
Adaptive thinking/max effort; production safety classifiers and sandbox-escape monitor enabled; three trials per task; all stopped trials counted as failures.
Unknowns
none recorded
Tools
Tool access not recorded
Reasoning budget
max
Framework
not recorded
Protocol
Toolathlon-Verified June 2026; average assistant turns per trajectory across 108 tasks and three trials.
Conditions
Trajectory length is a separate reported metric, not a success rate. Source-wide conditions: Toolathlon-Verified June 2026; 108 tasks; three trials per task; adaptive thinking/max effort; safety classifiers enabled; one classifier stop and six sandbox-escape-monitor stops counted as failures.