Claude Opus 5.5 · Protein Design Library Ranking(Prioritization of protein designs for experimental testing) 56% · 附件证据(ev-op55-card-protein-library-ranking)
Claude Opus 5.5 的 Protein Design Library Ranking · Prioritization of protein designs for experimental testing 官方出处。System Card max effort (per-result benchmark harnesses) · 56%。见《Claude Opus 5.5 System Card》§8.17.5, pp.218-219, Figure 8.17.8.A。证据 ev-op55-card-protein-library-ranking。
Claude Opus 5.5 · Protein Design Library Ranking(Prioritization of protein designs for experimental testing),System Card max effort (per-result benchmark harnesses)配置,Score 56%(具体成绩公布时间未确认)。见《Claude Opus 5.5 System Card》§8.17.5, pp.218-219, Figure 8.17.8.A。 查看成绩条件
Claude Opus 5.5 achieved 60.2% ... Claude Mythos 5.1 at 56.9% and Claude Opus 5.5 at 56.0% were level.
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 · Protein Design Library Ranking(Prioritization of protein designs for experimental testing),System Card max effort (per-result benchmark harnesses)配置,Score 56%(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)§8.17.5, pp.218-219, Figure 8.17.8.A,https://www.anthropic.com/claude-opus-5-5-system-card#page=219。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5-5/ev-op55-card-protein-library-ranking/
关联成绩与条件
Claude Opus 5.5 · Protein Design Library Ranking 成绩与配置
指标与成绩
配置与评测条件
证据关系
Score56%原文 56.0% · 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
禁止工具
推理预算
max
框架
未记录
协议
Protein Design Library Ranking; 83 problems; no tools; three attempts per problem; chance-normalized average precision.
条件
Current 83-problem task set and grader were revised; not comparable to earlier Mythos system-card values. Source-wide conditions: Sequence Generation: 336 design briefs, no tools, one attempt per problem. Library Ranking: 83 problems, no tools, three attempts per problem; current task set and grader differ from an earlier system-card version.
Claude Opus 5.5 · Protein Design Library Ranking (Prioritization of protein designs for experimental testing) 56% · Attachment evidence (ev-op55-card-protein-library-ranking)
Official source for Protein Design Library Ranking · Prioritization of protein designs for experimental testing in Claude Opus 5.5. System Card max effort (per-result benchmark harnesses) · 56%. See “Claude Opus 5.5 System Card” at §8.17.5, pp.218-219, Figure 8.17.8.A. Evidence ev-op55-card-protein-library-ranking.
Claude Opus 5.5 · Protein Design Library Ranking (Prioritization of protein designs for experimental testing), configuration System Card max effort (per-result benchmark harnesses), Score 56% (exact score publication date unconfirmed). See “Claude Opus 5.5 System Card” at §8.17.5, pp.218-219, Figure 8.17.8.A. View score conditions
Claude Opus 5.5 achieved 60.2% ... Claude Mythos 5.1 at 56.9% and Claude Opus 5.5 at 56.0% were level.
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 · Protein Design Library Ranking (Prioritization of protein designs for experimental testing), configuration System Card max effort (per-result benchmark harnesses), Score 56% (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), §8.17.5, pp.218-219, Figure 8.17.8.A, https://www.anthropic.com/claude-opus-5-5-system-card#page=219. Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5-5/ev-op55-card-protein-library-ranking/?lang=en
Related scores and conditions
Claude Opus 5.5 · Protein Design Library Ranking scores and configurations
Metric and score
Configuration and evaluation conditions
Evidence relation
Score56%Reported 56.0% · Unit %
Published Unconfirmed
System Card max effort (per-result benchmark harnesses)
Settings
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.
Unknowns
Exact run time is not disclosed.、Per-benchmark tools, safeguards, and repetition counts are specified only where the source states them.
Tools
Tools forbidden
Reasoning budget
max
Framework
not recorded
Protocol
Protein Design Library Ranking; 83 problems; no tools; three attempts per problem; chance-normalized average precision.
Conditions
Current 83-problem task set and grader were revised; not comparable to earlier Mythos system-card values. Source-wide conditions: Sequence Generation: 336 design briefs, no tools, one attempt per problem. Library Ranking: 83 problems, no tools, three attempts per problem; current task set and grader differ from an earlier system-card version.