Claude Sonnet 5 · FrontierCode(v1) · 附件证据(ev5-frontiercode-chart)
Claude Sonnet 5 的 FrontierCode · v1 官方出处。见《Claude Sonnet 5 System Card》§8.4 Figure 8.4.A, PDF p.118, orange Claude Sonnet 5 series labels。证据 ev5-frontiercode-chart。
Claude Sonnet 5 · FrontierCode(v1),Low effort (figure label)配置,Score 18.1%(具体成绩公布时间未确认)。见《Claude Sonnet 5 System Card》§8.4 Figure 8.4.A, PDF p.118, orange Claude Sonnet 5 series labels。 查看成绩条件
Claude Sonnet 5 · FrontierCode(v1),Medium effort (figure label)配置,Score 26.6%(具体成绩公布时间未确认)。见《Claude Sonnet 5 System Card》§8.4 Figure 8.4.A, PDF p.118, orange Claude Sonnet 5 series labels。 查看成绩条件
Claude Sonnet 5 · FrontierCode(v1),High effort (figure label)配置,Score 28.9%(具体成绩公布时间未确认)。见《Claude Sonnet 5 System Card》§8.4 Figure 8.4.A, PDF p.118, orange Claude Sonnet 5 series labels。 查看成绩条件
Claude Sonnet 5 · FrontierCode(v1),Xhigh effort (figure label)配置,Score 34%(具体成绩公布时间未确认)。见《Claude Sonnet 5 System Card》§8.4 Figure 8.4.A, PDF p.118, orange Claude Sonnet 5 series labels。 查看成绩条件
Claude Sonnet 5 · FrontierCode(v1),Max effort (figure label)配置,Score 38.8%(具体成绩公布时间未确认)。见《Claude Sonnet 5 System Card》§8.4 Figure 8.4.A, PDF p.118, orange Claude Sonnet 5 series labels。 查看成绩条件
low 18.1%; med 26.6%; high 28.9%; xhigh 34.0%; max 38.8%
附件 · §8.4 Figure 8.4.A, PDF p.118, orange Claude Sonnet 5 series labels
材料版本
PDF with changelog dated 2026-07-10; 146 pages; collected 2026-11-10
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 Sonnet 5 · FrontierCode(v1),Low effort (figure label)配置,Score 18.1%(具体成绩公布时间未确认);Claude Sonnet 5 · FrontierCode(v1),Medium effort (figure label)配置,Score 26.6%(具体成绩公布时间未确认);Claude Sonnet 5 · FrontierCode(v1),High effort (figure label)配置,Score 28.9%(具体成绩公布时间未确认);Claude Sonnet 5 · FrontierCode(v1),Xhigh effort (figure label)配置,Score 34%(具体成绩公布时间未确认);Claude Sonnet 5 · FrontierCode(v1),Max effort (figure label)配置,Score 38.8%(具体成绩公布时间未确认)。官方出处 Claude Sonnet 5 System Card(附件,PDF with changelog dated 2026-07-10; 146 pages; collected 2026-11-10)§8.4 Figure 8.4.A, PDF p.118, orange Claude Sonnet 5 series labels,https://www.anthropic.com/claude-sonnet-5-system-card#page=118。Benchlog https://benchlog.lekshome.cc/evidence/claude-sonnet-5/ev5-frontiercode-chart/
关联成绩与条件
Claude Sonnet 5 · FrontierCode 成绩与配置
指标与成绩
配置与评测条件
证据关系
Score18.1%原文 18.1% · 单位 %
公布 未确认
Low effort (figure label)
设置
The figure labels this run as low effort; it does not provide a complete generation configuration.
未知项
Sampling parameters, token limits, and tool setup are not fully stated for the cited chart point.
工具
工具条件未记录
推理预算
low
框架
未记录
协议
FrontierCode v1; Figure 8.4.A plots score by effort setting and average cost per task.
条件
Low effort as labeled. The figure caption says costs were recomputed from Cognition's published per-task token splits at API list rates; other sampling and context settings are not stated.
The figure labels this run as med effort; it does not provide a complete generation configuration.
未知项
Sampling parameters, token limits, and tool setup are not fully stated for the cited chart point.
工具
工具条件未记录
推理预算
med
框架
未记录
协议
FrontierCode v1; Figure 8.4.A plots score by effort setting and average cost per task.
条件
Med effort as labeled. The figure caption says costs were recomputed from Cognition's published per-task token splits at API list rates; other sampling and context settings are not stated.
The figure labels this run as high effort; it does not provide a complete generation configuration.
未知项
Sampling parameters, token limits, and tool setup are not fully stated for the cited chart point.
工具
工具条件未记录
推理预算
high
框架
未记录
协议
FrontierCode v1; Figure 8.4.A plots score by effort setting and average cost per task.
条件
High effort as labeled. The figure caption says costs were recomputed from Cognition's published per-task token splits at API list rates; other sampling and context settings are not stated.
The figure labels this run as xhigh effort; it does not provide a complete generation configuration.
未知项
Sampling parameters, token limits, and tool setup are not fully stated for the cited chart point.
工具
工具条件未记录
推理预算
xhigh
框架
未记录
协议
FrontierCode v1; Figure 8.4.A plots score by effort setting and average cost per task.
条件
Xhigh effort as labeled. The figure caption says costs were recomputed from Cognition's published per-task token splits at API list rates; other sampling and context settings are not stated.
The figure labels this run as max effort; it does not provide a complete generation configuration.
未知项
Sampling parameters, token limits, and tool setup are not fully stated for the cited chart point.
工具
工具条件未记录
推理预算
max
框架
未记录
协议
FrontierCode v1; Figure 8.4.A plots score by effort setting and average cost per task.
条件
Max effort as labeled. The figure caption says costs were recomputed from Cognition's published per-task token splits at API list rates; other sampling and context settings are not stated.
Claude Sonnet 5 · FrontierCode (v1) · Attachment evidence (ev5-frontiercode-chart)
Official source for FrontierCode · v1 in Claude Sonnet 5. See “Claude Sonnet 5 System Card” at §8.4 Figure 8.4.A, PDF p.118, orange Claude Sonnet 5 series labels. Evidence ev5-frontiercode-chart.
Claude Sonnet 5 · FrontierCode (v1), configuration Low effort (figure label), Score 18.1% (exact score publication date unconfirmed). See “Claude Sonnet 5 System Card” at §8.4 Figure 8.4.A, PDF p.118, orange Claude Sonnet 5 series labels. View score conditions
Claude Sonnet 5 · FrontierCode (v1), configuration Medium effort (figure label), Score 26.6% (exact score publication date unconfirmed). See “Claude Sonnet 5 System Card” at §8.4 Figure 8.4.A, PDF p.118, orange Claude Sonnet 5 series labels. View score conditions
Claude Sonnet 5 · FrontierCode (v1), configuration High effort (figure label), Score 28.9% (exact score publication date unconfirmed). See “Claude Sonnet 5 System Card” at §8.4 Figure 8.4.A, PDF p.118, orange Claude Sonnet 5 series labels. View score conditions
Claude Sonnet 5 · FrontierCode (v1), configuration Xhigh effort (figure label), Score 34% (exact score publication date unconfirmed). See “Claude Sonnet 5 System Card” at §8.4 Figure 8.4.A, PDF p.118, orange Claude Sonnet 5 series labels. View score conditions
Claude Sonnet 5 · FrontierCode (v1), configuration Max effort (figure label), Score 38.8% (exact score publication date unconfirmed). See “Claude Sonnet 5 System Card” at §8.4 Figure 8.4.A, PDF p.118, orange Claude Sonnet 5 series labels. View score conditions
low 18.1%; med 26.6%; high 28.9%; xhigh 34.0%; max 38.8%
Attachment · §8.4 Figure 8.4.A, PDF p.118, orange Claude Sonnet 5 series labels
Material version
PDF with changelog dated 2026-07-10; 146 pages; collected 2026-11-10
Version published
Unconfirmed
Disclosure date
Unconfirmed · Launch or later disclosure unconfirmed
Collected
Historical basis
No reliable historical version evidence available
Citation text
Claude Sonnet 5 · FrontierCode (v1), configuration Low effort (figure label), Score 18.1% (exact score publication date unconfirmed); Claude Sonnet 5 · FrontierCode (v1), configuration Medium effort (figure label), Score 26.6% (exact score publication date unconfirmed); Claude Sonnet 5 · FrontierCode (v1), configuration High effort (figure label), Score 28.9% (exact score publication date unconfirmed); Claude Sonnet 5 · FrontierCode (v1), configuration Xhigh effort (figure label), Score 34% (exact score publication date unconfirmed); Claude Sonnet 5 · FrontierCode (v1), configuration Max effort (figure label), Score 38.8% (exact score publication date unconfirmed). Official source: Claude Sonnet 5 System Card (Attachment, PDF with changelog dated 2026-07-10; 146 pages; collected 2026-11-10), §8.4 Figure 8.4.A, PDF p.118, orange Claude Sonnet 5 series labels, https://www.anthropic.com/claude-sonnet-5-system-card#page=118. Benchlog https://benchlog.lekshome.cc/evidence/claude-sonnet-5/ev5-frontiercode-chart/?lang=en
Related scores and conditions
Claude Sonnet 5 · FrontierCode scores and configurations
Metric and score
Configuration and evaluation conditions
Evidence relation
Score18.1%Reported 18.1% · Unit %
Published Unconfirmed
Low effort (figure label)
Settings
The figure labels this run as low effort; it does not provide a complete generation configuration.
Unknowns
Sampling parameters, token limits, and tool setup are not fully stated for the cited chart point.
Tools
Tool access not recorded
Reasoning budget
low
Framework
not recorded
Protocol
FrontierCode v1; Figure 8.4.A plots score by effort setting and average cost per task.
Conditions
Low effort as labeled. The figure caption says costs were recomputed from Cognition's published per-task token splits at API list rates; other sampling and context settings are not stated.
The figure labels this run as med effort; it does not provide a complete generation configuration.
Unknowns
Sampling parameters, token limits, and tool setup are not fully stated for the cited chart point.
Tools
Tool access not recorded
Reasoning budget
med
Framework
not recorded
Protocol
FrontierCode v1; Figure 8.4.A plots score by effort setting and average cost per task.
Conditions
Med effort as labeled. The figure caption says costs were recomputed from Cognition's published per-task token splits at API list rates; other sampling and context settings are not stated.
The figure labels this run as high effort; it does not provide a complete generation configuration.
Unknowns
Sampling parameters, token limits, and tool setup are not fully stated for the cited chart point.
Tools
Tool access not recorded
Reasoning budget
high
Framework
not recorded
Protocol
FrontierCode v1; Figure 8.4.A plots score by effort setting and average cost per task.
Conditions
High effort as labeled. The figure caption says costs were recomputed from Cognition's published per-task token splits at API list rates; other sampling and context settings are not stated.
The figure labels this run as xhigh effort; it does not provide a complete generation configuration.
Unknowns
Sampling parameters, token limits, and tool setup are not fully stated for the cited chart point.
Tools
Tool access not recorded
Reasoning budget
xhigh
Framework
not recorded
Protocol
FrontierCode v1; Figure 8.4.A plots score by effort setting and average cost per task.
Conditions
Xhigh effort as labeled. The figure caption says costs were recomputed from Cognition's published per-task token splits at API list rates; other sampling and context settings are not stated.
The figure labels this run as max effort; it does not provide a complete generation configuration.
Unknowns
Sampling parameters, token limits, and tool setup are not fully stated for the cited chart point.
Tools
Tool access not recorded
Reasoning budget
max
Framework
not recorded
Protocol
FrontierCode v1; Figure 8.4.A plots score by effort setting and average cost per task.
Conditions
Max effort as labeled. The figure caption says costs were recomputed from Cognition's published per-task token splits at API list rates; other sampling and context settings are not stated.