GLM-4.7 · Humanity's Last Exam(Release/task set unspecified; percentage explicitly stated in GLM-4.7 prose) 42.8% · 主文证据(ev-glm-4-7-hle-unversioned)

GLM-4.7 的 Humanity's Last Exam · Release/task set unspecified; percentage explicitly stated in GLM-4.7 prose 官方出处。GLM-4.7 official reported setting · 42.8%。见《GLM-4.7 | Z.AI Docs》Introducing GLM-4.7, HLE sentence。证据 ev-glm-4-7-hle-unversioned。

原文与定位

GLM-4.7 · Humanity's Last Exam(Release/task set unspecified; percentage explicitly stated in GLM-4.7 prose),GLM-4.7 official reported setting配置,Reported percentage score 42.8%(具体成绩公布时间未确认)。见《GLM-4.7 | Z.AI Docs》Introducing GLM-4.7, HLE sentence。 查看成绩条件

* **Enhanced reasoning capabilities**: Significantly improved mathematical and reasoning skills, achieving 42.8% on the HLE (“Human Last Exam”) benchmark—a 41% increase over GLM-4.6 and surpassing GPT-5.1
官方材料
GLM-4.7 | Z.AI Docs · 定位到章节
定位
主文 · Introducing GLM-4.7, HLE sentence
材料版本
Current official GLM-4.7 page; benchmark result paragraphs checked; collected 2026-11-17.
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

GLM-4.7 · Humanity's Last Exam(Release/task set unspecified; percentage explicitly stated in GLM-4.7 prose),GLM-4.7 official reported setting配置,Reported percentage score 42.8%(具体成绩公布时间未确认)。官方出处 GLM-4.7 | Z.AI Docs(主文,Current official GLM-4.7 page; benchmark result paragraphs checked; collected 2026-11-17.)Introducing GLM-4.7, HLE sentence,https://docs.z.ai/guides/llm/glm-4.7#introducing-glm-4-7。Benchlog https://benchlog.lekshome.cc/evidence/glm-4-7/ev-glm-4-7-hle-unversioned/

关联成绩与条件

GLM-4.7 · Humanity's Last Exam 成绩与配置
指标与成绩配置与评测条件证据关系
Reported percentage score42.8%原文 42.8% · 单位 %
公布 未确认
GLM-4.7 official reported setting
设置
GLM-4.7; per-benchmark protocol and precision are recorded only where the official source states them.
未知项
Reasoning effort and serving precision are not stated for these summary results.
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
未说明
条件
GLM-4.7; task version and tool use are not specified.

直接支持该成绩

在排名中查看此成绩