Claude Opus 5.5 · Legal Agent Benchmark(Opus 5 官方发布表所列 held-out set) · 附件证据(ev-op55-card-lab-heldout)

Claude Opus 5.5 的 Legal Agent Benchmark · Opus 5 官方发布表所列 held-out set 官方出处。见《Claude Opus 5.5 System Card》§8.14.2, p.209。证据 ev-op55-card-lab-heldout。

原文与定位

Claude Opus 5.5 · Legal Agent Benchmark(Opus 5 官方发布表所列 held-out set),System Card max effort (per-result benchmark harnesses)配置,All-pass rate 8.3%(具体成绩公布时间未确认)。见《Claude Opus 5.5 System Card》§8.14.2, p.209。 查看成绩条件

Claude Opus 5.5 · Legal Agent Benchmark(Opus 5 官方发布表所列 held-out set),System Card max effort (per-result benchmark harnesses)配置,Mean criterion-pass rate 91.2%(具体成绩公布时间未确认)。见《Claude Opus 5.5 System Card》§8.14.2, p.209。 查看成绩条件

Claude Opus 5.5 achieved an 8.3% all-pass rate and a 91.2% mean criterion-pass rate on the held-out set at max effort.
官方材料
Claude Opus 5.5 System Card · PDF 第 209 页
定位
附件 · §8.14.2, p.209
材料版本
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 · Legal Agent Benchmark(Opus 5 官方发布表所列 held-out set),System Card max effort (per-result benchmark harnesses)配置,All-pass rate 8.3%(具体成绩公布时间未确认);Claude Opus 5.5 · Legal Agent Benchmark(Opus 5 官方发布表所列 held-out set),System Card max effort (per-result benchmark harnesses)配置,Mean criterion-pass rate 91.2%(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)§8.14.2, p.209,https://www.anthropic.com/claude-opus-5-5-system-card#page=209。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5-5/ev-op55-card-lab-heldout/

关联成绩与条件

Claude Opus 5.5 · Legal Agent Benchmark 成绩与配置
指标与成绩配置与评测条件证据关系
All-pass rate8.3%原文 8.3% all-pass rate · 单位 %
公布 未确认
System Card max effort (per-result benchmark harnesses)
设置
System Card §8.1 default: adaptive thinking/max effort and default sampling settings unless a section says otherwise. Benchmark tools, evaluator, safeguards, fallback, and repetitions remain per-result conditions; this config represents the stated model effort, not harness equivalence.
未知项
Exact run time is not disclosed.、Per-benchmark tools, safeguards, and repetition counts are specified only where the source states them.
工具
工具条件未记录
推理预算
max
框架
未记录
协议
Harvey LAB held-out 120-task set; max effort; Artificial Analysis evaluation harness.
条件
Distinct from the public full LAB set; do not label as Harvey's public leaderboard score. Source-wide conditions: Harvey LAB 120-problem held-out set; independently reported by Artificial Analysis on its own harness; distinct from the public 2,010+ task set.

直接支持该成绩

在排名中查看此成绩
Mean criterion-pass rate91.2%原文 91.2% mean criterion-pass rate · 单位 %
公布 未确认
System Card max effort (per-result benchmark harnesses)
设置
System Card §8.1 default: adaptive thinking/max effort and default sampling settings unless a section says otherwise. Benchmark tools, evaluator, safeguards, fallback, and repetitions remain per-result conditions; this config represents the stated model effort, not harness equivalence.
未知项
Exact run time is not disclosed.、Per-benchmark tools, safeguards, and repetition counts are specified only where the source states them.
工具
工具条件未记录
推理预算
max
框架
未记录
协议
Harvey LAB held-out 120-task set; max effort; Artificial Analysis evaluation harness.
条件
Criterion-pass rate is not the all-pass rate; keep the two metrics separate. Source-wide conditions: Harvey LAB 120-problem held-out set; independently reported by Artificial Analysis on its own harness; distinct from the public 2,010+ task set.

直接支持该成绩

在排名中查看此成绩