GLM-4.6 · CC-Bench · V1.1; 74 real-world coding tests in Claude Code; exact task release unspecified · 成绩与配置

GLM-4.6 的 CC-Bench · V1.1; 74 real-world coding tests in Claude Code; exact task release unspecified 记录。本次发布有 12 条成绩记录,含 12 条精确值(可含历史记录),附 12 条来源定位。

成绩与评测条件

GLM-4.6 · CC-Bench 成绩与配置
指标与成绩配置与评测条件出处
Win rate48.6%原文 48.6% · 单位 %
公布
GLM-4.6 official chart configuration
设置
GLM-4.6; chart column is not labelled w/ Tools. Model serving, effort and precision are not disclosed.
未知项
Effort and serving endpoint are unknown.、Chart values have no printed units.
工具
工具条件未记录
推理预算
未记录
框架
Claude Code
协议
CC-Bench V1.1; official docs describe 74 real-world coding tests in the Claude Code environment; comparison against Claude Sonnet 4.
条件
GLM-4.6; task-level harness details and serving precision are not stated in the chart.
在排名中查看此成绩
Tie rate9.5%原文 9.5% · 单位 %
公布
GLM-4.6 official chart configuration
设置
GLM-4.6; chart column is not labelled w/ Tools. Model serving, effort and precision are not disclosed.
未知项
Effort and serving endpoint are unknown.、Chart values have no printed units.
工具
工具条件未记录
推理预算
未记录
框架
Claude Code
协议
CC-Bench V1.1; official docs describe 74 real-world coding tests in the Claude Code environment; comparison against Claude Sonnet 4.
条件
GLM-4.6; task-level harness details and serving precision are not stated in the chart.
在排名中查看此成绩
Loss rate41.9%原文 41.9% · 单位 %
公布
GLM-4.6 official chart configuration
设置
GLM-4.6; chart column is not labelled w/ Tools. Model serving, effort and precision are not disclosed.
未知项
Effort and serving endpoint are unknown.、Chart values have no printed units.
工具
工具条件未记录
推理预算
未记录
框架
Claude Code
协议
CC-Bench V1.1; official docs describe 74 real-world coding tests in the Claude Code environment; comparison against Claude Sonnet 4.
条件
GLM-4.6; task-level harness details and serving precision are not stated in the chart.
在排名中查看此成绩
Win rate50%原文 50% · 单位 %
公布
GLM-4.6 official chart configuration
设置
GLM-4.6; chart column is not labelled w/ Tools. Model serving, effort and precision are not disclosed.
未知项
Effort and serving endpoint are unknown.、Chart values have no printed units.
工具
工具条件未记录
推理预算
未记录
框架
Claude Code
协议
CC-Bench V1.1; official docs describe 74 real-world coding tests in the Claude Code environment; comparison against GLM-4.5.
条件
GLM-4.6; task-level harness details and serving precision are not stated in the chart.
在排名中查看此成绩
Tie rate13.5%原文 13.5% · 单位 %
公布
GLM-4.6 official chart configuration
设置
GLM-4.6; chart column is not labelled w/ Tools. Model serving, effort and precision are not disclosed.
未知项
Effort and serving endpoint are unknown.、Chart values have no printed units.
工具
工具条件未记录
推理预算
未记录
框架
Claude Code
协议
CC-Bench V1.1; official docs describe 74 real-world coding tests in the Claude Code environment; comparison against GLM-4.5.
条件
GLM-4.6; task-level harness details and serving precision are not stated in the chart.
在排名中查看此成绩
Loss rate36.5%原文 36.5% · 单位 %
公布
GLM-4.6 official chart configuration
设置
GLM-4.6; chart column is not labelled w/ Tools. Model serving, effort and precision are not disclosed.
未知项
Effort and serving endpoint are unknown.、Chart values have no printed units.
工具
工具条件未记录
推理预算
未记录
框架
Claude Code
协议
CC-Bench V1.1; official docs describe 74 real-world coding tests in the Claude Code environment; comparison against GLM-4.5.
条件
GLM-4.6; task-level harness details and serving precision are not stated in the chart.
在排名中查看此成绩
Win rate56.8%原文 56.8% · 单位 %
公布
GLM-4.6 official chart configuration
设置
GLM-4.6; chart column is not labelled w/ Tools. Model serving, effort and precision are not disclosed.
未知项
Effort and serving endpoint are unknown.、Chart values have no printed units.
工具
工具条件未记录
推理预算
未记录
框架
Claude Code
协议
CC-Bench V1.1; official docs describe 74 real-world coding tests in the Claude Code environment; comparison against Kimi-K2-0905.
条件
GLM-4.6; task-level harness details and serving precision are not stated in the chart.
在排名中查看此成绩
Tie rate28.3%原文 28.3% · 单位 %
公布
GLM-4.6 official chart configuration
设置
GLM-4.6; chart column is not labelled w/ Tools. Model serving, effort and precision are not disclosed.
未知项
Effort and serving endpoint are unknown.、Chart values have no printed units.
工具
工具条件未记录
推理预算
未记录
框架
Claude Code
协议
CC-Bench V1.1; official docs describe 74 real-world coding tests in the Claude Code environment; comparison against Kimi-K2-0905.
条件
GLM-4.6; task-level harness details and serving precision are not stated in the chart.
在排名中查看此成绩
Loss rate14.9%原文 14.9% · 单位 %
公布
GLM-4.6 official chart configuration
设置
GLM-4.6; chart column is not labelled w/ Tools. Model serving, effort and precision are not disclosed.
未知项
Effort and serving endpoint are unknown.、Chart values have no printed units.
工具
工具条件未记录
推理预算
未记录
框架
Claude Code
协议
CC-Bench V1.1; official docs describe 74 real-world coding tests in the Claude Code environment; comparison against Kimi-K2-0905.
条件
GLM-4.6; task-level harness details and serving precision are not stated in the chart.
在排名中查看此成绩
Win rate64.9%原文 64.9% · 单位 %
公布
GLM-4.6 official chart configuration
设置
GLM-4.6; chart column is not labelled w/ Tools. Model serving, effort and precision are not disclosed.
未知项
Effort and serving endpoint are unknown.、Chart values have no printed units.
工具
工具条件未记录
推理预算
未记录
框架
Claude Code
协议
CC-Bench V1.1; official docs describe 74 real-world coding tests in the Claude Code environment; comparison against DeepSeek-V3.1-Terminus.
条件
GLM-4.6; task-level harness details and serving precision are not stated in the chart.
在排名中查看此成绩
Tie rate8.1%原文 8.1% · 单位 %
公布
GLM-4.6 official chart configuration
设置
GLM-4.6; chart column is not labelled w/ Tools. Model serving, effort and precision are not disclosed.
未知项
Effort and serving endpoint are unknown.、Chart values have no printed units.
工具
工具条件未记录
推理预算
未记录
框架
Claude Code
协议
CC-Bench V1.1; official docs describe 74 real-world coding tests in the Claude Code environment; comparison against DeepSeek-V3.1-Terminus.
条件
GLM-4.6; task-level harness details and serving precision are not stated in the chart.
在排名中查看此成绩
Loss rate27%原文 27% · 单位 %
公布
GLM-4.6 official chart configuration
设置
GLM-4.6; chart column is not labelled w/ Tools. Model serving, effort and precision are not disclosed.
未知项
Effort and serving endpoint are unknown.、Chart values have no printed units.
工具
工具条件未记录
推理预算
未记录
框架
Claude Code
协议
CC-Bench V1.1; official docs describe 74 real-world coding tests in the Claude Code environment; comparison against DeepSeek-V3.1-Terminus.
条件
GLM-4.6; task-level harness details and serving precision are not stated in the chart.
在排名中查看此成绩

出处与披露

测试版本与指标

别名 CC-Bench V1.1

  • Win rate · % · 越高越好
  • Tie rate · % · 排序方向未确认
  • Loss rate · % · 越低越好