Claude Opus 5.5 · SWE-bench Multimodal(Multimodal) 61.4% · 附件证据(ev-op55-card-swe-multimodal)
Claude Opus 5.5 的 SWE-bench Multimodal · Multimodal 官方出处。System Card max effort (per-result benchmark harnesses) · 61.4%。见《Claude Opus 5.5 System Card》§8.2, p.175。证据 ev-op55-card-swe-multimodal。
Claude Opus 5.5 · SWE-bench Multimodal(Multimodal),System Card max effort (per-result benchmark harnesses)配置,Pass rate 61.4%(具体成绩公布时间未确认)。见《Claude Opus 5.5 System Card》§8.2, p.175。 查看成绩条件
SWE-bench Pro ... Claude Opus 5.5 achieved 89.9%. SWE-bench Multilingual ... Opus 5.5 achieved 93.9%. SWE-bench Multimodal ... Opus 5.5 achieved 61.4%.
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 · SWE-bench Multimodal(Multimodal),System Card max effort (per-result benchmark harnesses)配置,Pass rate 61.4%(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)§8.2, p.175,https://www.anthropic.com/claude-opus-5-5-system-card#page=175。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5-5/ev-op55-card-swe-multimodal/
关联成绩与条件
Claude Opus 5.5 · SWE-bench Multimodal 成绩与配置
指标与成绩
配置与评测条件
证据关系
Pass rate61.4%原文 61.4% · 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
Visual issue context including screenshots and design mockups; five trials averaged.
条件
Exact task count, tools and run date are not stated. Source-wide conditions: Each score is averaged over five trials; Multilingual has 300 problems across nine languages.
Claude Opus 5.5 · SWE-bench Multimodal (Multimodal) 61.4% · Attachment evidence (ev-op55-card-swe-multimodal)
Official source for SWE-bench Multimodal · Multimodal in Claude Opus 5.5. System Card max effort (per-result benchmark harnesses) · 61.4%. See “Claude Opus 5.5 System Card” at §8.2, p.175. Evidence ev-op55-card-swe-multimodal.
Claude Opus 5.5 · SWE-bench Multimodal (Multimodal), configuration System Card max effort (per-result benchmark harnesses), Pass rate 61.4% (exact score publication date unconfirmed). See “Claude Opus 5.5 System Card” at §8.2, p.175. View score conditions
SWE-bench Pro ... Claude Opus 5.5 achieved 89.9%. SWE-bench Multilingual ... Opus 5.5 achieved 93.9%. SWE-bench Multimodal ... Opus 5.5 achieved 61.4%.
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 · SWE-bench Multimodal (Multimodal), configuration System Card max effort (per-result benchmark harnesses), Pass rate 61.4% (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), §8.2, p.175, https://www.anthropic.com/claude-opus-5-5-system-card#page=175. Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5-5/ev-op55-card-swe-multimodal/?lang=en
Related scores and conditions
Claude Opus 5.5 · SWE-bench Multimodal scores and configurations
Metric and score
Configuration and evaluation conditions
Evidence relation
Pass rate61.4%Reported 61.4% · 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
Tool access not recorded
Reasoning budget
max
Framework
not recorded
Protocol
Visual issue context including screenshots and design mockups; five trials averaged.
Conditions
Exact task count, tools and run date are not stated. Source-wide conditions: Each score is averaged over five trials; Multilingual has 300 problems across nine languages.