GLM-5.3 · CyberGym · GLM-5.3模型卡;unknown · 成绩与配置

GLM-5.3 的 CyberGym · GLM-5.3模型卡;unknown 记录。本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录),附 1 条来源定位。

成绩与评测条件

GLM-5.3 · CyberGym 成绩与配置
指标与成绩配置与评测条件出处
pass-at-184.5原文 **84.5** · 单位 未标注
公布 未确认
GLM-5.3 · max
设置
官方模型卡目标列;逐行scaffold、工具、采样及预算条件见protocol。来源把benchmark复现明确绑定max或行内明确reasoning_effort=max。
未知项
未逐项说明的指标单位、题集修订、服务精度和运行次数保持未知。
工具
允许工具
推理预算
max · 输出上限 128000 tokens
框架
Claude Code 2.1.207
协议
The card says reasoning_effort defaults to max and recommends keeping that default for benchmark reproduction. **CyberGym**: We evaluate GLM-5.3 in Claude Code 2.1.207 (max reasoning effort, no web tools with `temperature=1.0`, `top_p=1.0`, `max_new_tokens=128000`). All evaluations are under unlimited timeout per task and results are single-run Pass@1 over 1,507 tasks. To simulate real-world usage scenarios, we place the agent inside the task container. We also remove all Git-related information and apply a domain whitelist (allowing only essential domains such as pypi.org and deb.debian.org for basic tool installation) to prevent the agent from cheating.
条件
GLM-5.3目标列;The card says reasoning_effort defaults to max and recommends keeping that default for benchmark reproduction. **CyberGym**: We evaluate GLM-5.3 in Claude Code 2.1.207 (max reasoning effort, no web tools with `temperature=1.0`, `top_p=1.0`, `max_new_tokens=128000`). All evaluations are under unlimited timeout per task and results are single-run Pass@1 over 1,507 tasks. To simulate real-world usage scenarios, we place the agent inside the task container. We also remove all Git-related information and apply a domain whitelist (allowing only essential domains such as pypi.org and deb.debian.org for basic tool installation) to prevent the agent from cheating. 安全、内部子项或跨测试聚合仅保留原始披露,不进入常规展示。
在排名中查看此成绩

出处与披露

测试版本与指标

别名 CyberGym

  • pass-at-1 · 单位未标注 · 越高越好