Claude Opus 5 · Frontier-Bench(v0.1) · 附件证据(ev-op5-card-frontierbench-miniswe)
Claude Opus 5 的 Frontier-Bench · v0.1 官方出处。见《Claude Opus 5 System Card》System Card PDF pp.155-157, §8.5, FrontierBench v0.1 results。证据 ev-op5-card-frontierbench-miniswe。
Claude Opus 5 · Frontier-Bench(v0.1),FrontierBench v0.1 · mini-SWE-agent/GKE · Low effort配置,Score 25%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF pp.155-157, §8.5, FrontierBench v0.1 results。 查看成绩条件
Claude Opus 5 · Frontier-Bench(v0.1),FrontierBench v0.1 · mini-SWE-agent/GKE · High effort配置,Score 39%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF pp.155-157, §8.5, FrontierBench v0.1 results。 查看成绩条件
Claude Opus 5 · Frontier-Bench(v0.1),FrontierBench v0.1 · mini-SWE-agent/GKE · Xhigh effort配置,Score 44.4%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF pp.155-157, §8.5, FrontierBench v0.1 results。 查看成绩条件
Claude Opus 5 · Frontier-Bench(v0.1),FrontierBench v0.1 · mini-SWE-agent/GKE · Max effort配置,Score 43%(具体成绩公布时间未确认)。见《Claude Opus 5 System Card》System Card PDF pp.155-157, §8.5, FrontierBench v0.1 results。 查看成绩条件
Anthropic mini-SWE-agent on GKE: xhigh 44.4% mean reward; max 43%; high 39%; low 25%. Each figure is averaged over five attempts on each of 74 tasks. Opus 4.8 fallback is reported for classifier refusals.
附件 · System Card PDF pp.155-157, §8.5, FrontierBench v0.1 results
材料版本
Current saved PDF/TXT: 本地留存副本 and current-opus-5-system-card.txt; cover dated 2026-07-24; p.2 changelog records an update on 2026-08-19; later revision date, if any, 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 · Frontier-Bench(v0.1),FrontierBench v0.1 · mini-SWE-agent/GKE · Low effort配置,Score 25%(具体成绩公布时间未确认);Claude Opus 5 · Frontier-Bench(v0.1),FrontierBench v0.1 · mini-SWE-agent/GKE · High effort配置,Score 39%(具体成绩公布时间未确认);Claude Opus 5 · Frontier-Bench(v0.1),FrontierBench v0.1 · mini-SWE-agent/GKE · Xhigh effort配置,Score 44.4%(具体成绩公布时间未确认);Claude Opus 5 · Frontier-Bench(v0.1),FrontierBench v0.1 · mini-SWE-agent/GKE · Max effort配置,Score 43%(具体成绩公布时间未确认)。官方出处 Claude Opus 5 System Card(附件,Current saved PDF/TXT: 本地留存副本 and current-opus-5-system-card.txt; cover dated 2026-07-24; p.2 changelog records an update on 2026-08-19; later revision date, if any, unknown.)System Card PDF pp.155-157, §8.5, FrontierBench v0.1 results,https://www.anthropic.com/claude-opus-5-system-card#page=156。Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5/ev-op5-card-frontierbench-miniswe/
Anthropic-run mini-SWE-agent harness on GKE; mean reward over five attempts for each of 74 unique tasks; production safety classifiers were enabled. Refusals triggered fallback to Opus 4.8 in 4% of total trials. Explicit adaptive-thinking effort: low.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
工具
工具条件未记录
推理预算
low
框架
mini-SWE-agent harness
协议
FrontierBench v0.1; Anthropic mini-SWE-agent harness on GKE; mean reward over 74 tasks, five attempts each.
条件
Internal harness run separate from the Harbor Table 8.1.A row; max was reported as similar to xhigh and within noise. Safety classifiers/fallback were active.
FrontierBench v0.1 · mini-SWE-agent/GKE · High effort
设置
Anthropic-run mini-SWE-agent harness on GKE; mean reward over five attempts for each of 74 unique tasks; production safety classifiers were enabled. Refusals triggered fallback to Opus 4.8 in 4% of total trials. Explicit adaptive-thinking effort: high.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
工具
工具条件未记录
推理预算
high
框架
mini-SWE-agent harness
协议
FrontierBench v0.1; Anthropic mini-SWE-agent harness on GKE; mean reward over 74 tasks, five attempts each.
条件
Internal harness run separate from the Harbor Table 8.1.A row; max was reported as similar to xhigh and within noise. Safety classifiers/fallback were active.
Anthropic-run mini-SWE-agent harness on GKE; mean reward over five attempts for each of 74 unique tasks; production safety classifiers were enabled. Refusals triggered fallback to Opus 4.8 in 4% of total trials. Explicit adaptive-thinking effort: xhigh.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
工具
工具条件未记录
推理预算
xhigh
框架
mini-SWE-agent harness
协议
FrontierBench v0.1; Anthropic mini-SWE-agent harness on GKE; mean reward over 74 tasks, five attempts each.
条件
Internal harness run separate from the Harbor Table 8.1.A row; max was reported as similar to xhigh and within noise. Safety classifiers/fallback were active.
FrontierBench v0.1 · mini-SWE-agent/GKE · Max effort
设置
Anthropic-run mini-SWE-agent harness on GKE; mean reward over five attempts for each of 74 unique tasks; production safety classifiers were enabled. Refusals triggered fallback to Opus 4.8 in 4% of total trials. Explicit adaptive-thinking effort: max.
未知项
The card does not state any additional sampling parameters beyond the cited evaluation description.
工具
工具条件未记录
推理预算
max
框架
mini-SWE-agent harness
协议
FrontierBench v0.1; Anthropic mini-SWE-agent harness on GKE; mean reward over 74 tasks, five attempts each.
条件
Internal harness run separate from the Harbor Table 8.1.A row; max was reported as similar to xhigh and within noise. Safety classifiers/fallback were active.
Claude Opus 5 · Frontier-Bench (v0.1) · Attachment evidence (ev-op5-card-frontierbench-miniswe)
Official source for Frontier-Bench · v0.1 in Claude Opus 5. See “Claude Opus 5 System Card” at System Card PDF pp.155-157, §8.5, FrontierBench v0.1 results. Evidence ev-op5-card-frontierbench-miniswe.
Claude Opus 5 · Frontier-Bench (v0.1), configuration FrontierBench v0.1 · mini-SWE-agent/GKE · Low effort, Score 25% (exact score publication date unconfirmed). See “Claude Opus 5 System Card” at System Card PDF pp.155-157, §8.5, FrontierBench v0.1 results. View score conditions
Claude Opus 5 · Frontier-Bench (v0.1), configuration FrontierBench v0.1 · mini-SWE-agent/GKE · High effort, Score 39% (exact score publication date unconfirmed). See “Claude Opus 5 System Card” at System Card PDF pp.155-157, §8.5, FrontierBench v0.1 results. View score conditions
Claude Opus 5 · Frontier-Bench (v0.1), configuration FrontierBench v0.1 · mini-SWE-agent/GKE · Xhigh effort, Score 44.4% (exact score publication date unconfirmed). See “Claude Opus 5 System Card” at System Card PDF pp.155-157, §8.5, FrontierBench v0.1 results. View score conditions
Claude Opus 5 · Frontier-Bench (v0.1), configuration FrontierBench v0.1 · mini-SWE-agent/GKE · Max effort, Score 43% (exact score publication date unconfirmed). See “Claude Opus 5 System Card” at System Card PDF pp.155-157, §8.5, FrontierBench v0.1 results. View score conditions
Anthropic mini-SWE-agent on GKE: xhigh 44.4% mean reward; max 43%; high 39%; low 25%. Each figure is averaged over five attempts on each of 74 tasks. Opus 4.8 fallback is reported for classifier refusals.
Attachment · System Card PDF pp.155-157, §8.5, FrontierBench v0.1 results
Material version
Current saved PDF/TXT: 本地留存副本 and current-opus-5-system-card.txt; cover dated 2026-07-24; p.2 changelog records an update on 2026-08-19; later revision date, if any, unknown.
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 · Frontier-Bench (v0.1), configuration FrontierBench v0.1 · mini-SWE-agent/GKE · Low effort, Score 25% (exact score publication date unconfirmed); Claude Opus 5 · Frontier-Bench (v0.1), configuration FrontierBench v0.1 · mini-SWE-agent/GKE · High effort, Score 39% (exact score publication date unconfirmed); Claude Opus 5 · Frontier-Bench (v0.1), configuration FrontierBench v0.1 · mini-SWE-agent/GKE · Xhigh effort, Score 44.4% (exact score publication date unconfirmed); Claude Opus 5 · Frontier-Bench (v0.1), configuration FrontierBench v0.1 · mini-SWE-agent/GKE · Max effort, Score 43% (exact score publication date unconfirmed). Official source: Claude Opus 5 System Card (Attachment, Current saved PDF/TXT: 本地留存副本 and current-opus-5-system-card.txt; cover dated 2026-07-24; p.2 changelog records an update on 2026-08-19; later revision date, if any, unknown.), System Card PDF pp.155-157, §8.5, FrontierBench v0.1 results, https://www.anthropic.com/claude-opus-5-system-card#page=156. Benchlog https://benchlog.lekshome.cc/evidence/claude-opus-5/ev-op5-card-frontierbench-miniswe/?lang=en
Related scores and conditions
Claude Opus 5 · Frontier-Bench scores and configurations
Anthropic-run mini-SWE-agent harness on GKE; mean reward over five attempts for each of 74 unique tasks; production safety classifiers were enabled. Refusals triggered fallback to Opus 4.8 in 4% of total trials. Explicit adaptive-thinking effort: low.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.
Tools
Tool access not recorded
Reasoning budget
low
Framework
mini-SWE-agent harness
Protocol
FrontierBench v0.1; Anthropic mini-SWE-agent harness on GKE; mean reward over 74 tasks, five attempts each.
Conditions
Internal harness run separate from the Harbor Table 8.1.A row; max was reported as similar to xhigh and within noise. Safety classifiers/fallback were active.
FrontierBench v0.1 · mini-SWE-agent/GKE · High effort
Settings
Anthropic-run mini-SWE-agent harness on GKE; mean reward over five attempts for each of 74 unique tasks; production safety classifiers were enabled. Refusals triggered fallback to Opus 4.8 in 4% of total trials. Explicit adaptive-thinking effort: high.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.
Tools
Tool access not recorded
Reasoning budget
high
Framework
mini-SWE-agent harness
Protocol
FrontierBench v0.1; Anthropic mini-SWE-agent harness on GKE; mean reward over 74 tasks, five attempts each.
Conditions
Internal harness run separate from the Harbor Table 8.1.A row; max was reported as similar to xhigh and within noise. Safety classifiers/fallback were active.
Anthropic-run mini-SWE-agent harness on GKE; mean reward over five attempts for each of 74 unique tasks; production safety classifiers were enabled. Refusals triggered fallback to Opus 4.8 in 4% of total trials. Explicit adaptive-thinking effort: xhigh.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.
Tools
Tool access not recorded
Reasoning budget
xhigh
Framework
mini-SWE-agent harness
Protocol
FrontierBench v0.1; Anthropic mini-SWE-agent harness on GKE; mean reward over 74 tasks, five attempts each.
Conditions
Internal harness run separate from the Harbor Table 8.1.A row; max was reported as similar to xhigh and within noise. Safety classifiers/fallback were active.
FrontierBench v0.1 · mini-SWE-agent/GKE · Max effort
Settings
Anthropic-run mini-SWE-agent harness on GKE; mean reward over five attempts for each of 74 unique tasks; production safety classifiers were enabled. Refusals triggered fallback to Opus 4.8 in 4% of total trials. Explicit adaptive-thinking effort: max.
Unknowns
The card does not state any additional sampling parameters beyond the cited evaluation description.
Tools
Tool access not recorded
Reasoning budget
max
Framework
mini-SWE-agent harness
Protocol
FrontierBench v0.1; Anthropic mini-SWE-agent harness on GKE; mean reward over 74 tasks, five attempts each.
Conditions
Internal harness run separate from the Harbor Table 8.1.A row; max was reported as similar to xhigh and within noise. Safety classifiers/fallback were active.