Claude Opus 5.5 · SpatialBench Verified(Verified) 72% · 附件证据(ev-op55-card-latchbio)
Claude Opus 5.5 的 SpatialBench Verified · Verified 官方出处。System Card max effort (per-result benchmark harnesses) · 72%。见《Claude Opus 5.5 System Card》§8.17.2, p.217, Figure 8.17.8.A。证据 ev-op55-card-latchbio。
Claude Opus 5.5 · SpatialBench Verified(Verified),System Card max effort (per-result benchmark harnesses)配置,Score 72%(具体成绩公布时间未确认)。见《Claude Opus 5.5 System Card》§8.17.2, p.217, Figure 8.17.8.A。 查看成绩条件
On SpatialBench Verified, Claude Mythos 5.1 remains the strongest model at 77.6%, followed by Claude Opus 5.5 at 72.0% ... On SingleCellBench, Claude Mythos 5.1 at 61.8%, Claude Opus 5.5 at 61.2% and Claude Opus 5 at 60.5% 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 · SpatialBench Verified(Verified),System Card max effort (per-result benchmark harnesses)配置,Score 72%(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)§8.17.2, p.217, Figure 8.17.8.A,https://www.anthropic.com/claude-opus-5-5-system-card#page=217。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5-5/ev-op55-card-latchbio/
关联成绩与条件
Claude Opus 5.5 · SpatialBench Verified 成绩与配置
指标与成绩
配置与评测条件
证据关系
Score72%原文 72.0% · 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
允许工具
推理预算
max
框架
未记录
协议
SpatialBench Verified; 115 externally validated problems; bash and file editor with prespecified packages; five attempts per problem unless otherwise stated.
条件
Specialized bioinformatics capability result; not a CB risk score. Source-wide conditions: SpatialBench Verified: 115 externally validated problems; SingleCellBench: 195 single-cell RNA-sequencing problems; bash and file editor with prespecified packages.
Claude Opus 5.5 · SpatialBench Verified (Verified) 72% · Attachment evidence (ev-op55-card-latchbio)
Official source for SpatialBench Verified · Verified in Claude Opus 5.5. System Card max effort (per-result benchmark harnesses) · 72%. See “Claude Opus 5.5 System Card” at §8.17.2, p.217, Figure 8.17.8.A. Evidence ev-op55-card-latchbio.
Claude Opus 5.5 · SpatialBench Verified (Verified), configuration System Card max effort (per-result benchmark harnesses), Score 72% (exact score publication date unconfirmed). See “Claude Opus 5.5 System Card” at §8.17.2, p.217, Figure 8.17.8.A. View score conditions
On SpatialBench Verified, Claude Mythos 5.1 remains the strongest model at 77.6%, followed by Claude Opus 5.5 at 72.0% ... On SingleCellBench, Claude Mythos 5.1 at 61.8%, Claude Opus 5.5 at 61.2% and Claude Opus 5 at 60.5% 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 · SpatialBench Verified (Verified), configuration System Card max effort (per-result benchmark harnesses), Score 72% (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), §8.17.2, p.217, Figure 8.17.8.A, https://www.anthropic.com/claude-opus-5-5-system-card#page=217. Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5-5/ev-op55-card-latchbio/?lang=en
Related scores and conditions
Claude Opus 5.5 · SpatialBench Verified scores and configurations
Metric and score
Configuration and evaluation conditions
Evidence relation
Score72%Reported 72.0% · 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 allowed
Reasoning budget
max
Framework
not recorded
Protocol
SpatialBench Verified; 115 externally validated problems; bash and file editor with prespecified packages; five attempts per problem unless otherwise stated.
Conditions
Specialized bioinformatics capability result; not a CB risk score. Source-wide conditions: SpatialBench Verified: 115 externally validated problems; SingleCellBench: 195 single-cell RNA-sequencing problems; bash and file editor with prespecified packages.