Claude Opus 5.5 · OSWorld(2.1, 82-task offline no-internet subset, partial score) · 附件证据(ev-op55-osworld-offline-card)
Claude Opus 5.5 的 OSWorld · 2.1, 82-task offline no-internet subset, partial score 官方出处。见《Claude Haiku 5.5 System Card (Opus 5.5 OSWorld offline comparison)》Page 128, §8.9.3 OSWorld 2.1 offline subset。证据 ev-op55-osworld-offline-card。
原文与定位
Claude Opus 5.5 · OSWorld(2.1, 82-task offline no-internet subset, partial score),OSWorld 2.1 offline subset配置,Partial score 87.2%(具体成绩公布时间未确认)。见《Claude Haiku 5.5 System Card (Opus 5.5 OSWorld offline comparison)》Page 128, §8.9.3 OSWorld 2.1 offline subset。 查看成绩条件
Claude Opus 5.5 · OSWorld(2.1, 82-task offline no-internet subset, partial score),OSWorld 2.1 offline subset配置,Strict pass rate 53.2%(具体成绩公布时间未确认)。见《Claude Haiku 5.5 System Card (Opus 5.5 OSWorld offline comparison)》Page 128, §8.9.3 OSWorld 2.1 offline subset。 查看成绩条件
On the official offline subset (82 of 108 tasks, no internet access), Claude Opus 5.5 scored 87.2% partial and 53.2% strict pass.
- 官方材料
- Claude Haiku 5.5 System Card (Opus 5.5 OSWorld offline comparison) · PDF 第 128 页
- 定位
- 附件 · Page 128, §8.9.3 OSWorld 2.1 offline subset
- 材料版本
- Official current System Card, cover dated 2026-10-07; current PDF/TXT saved at 本地留存副本 and .txt; full pp.1-144 read across Singer/Boyle reviews, with 63 safety figure pages visually checked; current revision date unknown.
- 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 · OSWorld(2.1, 82-task offline no-internet subset, partial score),OSWorld 2.1 offline subset配置,Partial score 87.2%(具体成绩公布时间未确认);Claude Opus 5.5 · OSWorld(2.1, 82-task offline no-internet subset, partial score),OSWorld 2.1 offline subset配置,Strict pass rate 53.2%(具体成绩公布时间未确认)。官方出处 Claude Haiku 5.5 System Card (Opus 5.5 OSWorld offline comparison)(附件,Official current System Card, cover dated 2026-10-07; current PDF/TXT saved at 本地留存副本 and .txt; full pp.1-144 read across Singer/Boyle reviews, with 63 safety figure pages visually checked; current revision date unknown.)Page 128, §8.9.3 OSWorld 2.1 offline subset,https://www.anthropic.com/claude-haiku-5-5-system-card#page=128。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5-5/ev-op55-osworld-offline-card/
关联成绩与条件
| 指标与成绩 | 配置与评测条件 | 证据关系 |
|---|---|---|
| Partial score87.2%原文 87.2% partial (offline subset) · 单位 % 公布 未确认 | OSWorld 2.1 offline subset
| 直接支持该成绩 在排名中查看此成绩 |
| Strict pass rate53.2%原文 53.2% strict pass (offline subset) · 单位 % 公布 未确认 | OSWorld 2.1 offline subset
| 直接支持该成绩 在排名中查看此成绩 |