Terminal-Bench · GLM-5.3模型卡;3.0 · 测试定义与成绩

Terminal-Bench · GLM-5.3模型卡;3.0 收录 1 次模型发布的评测披露或成绩。

测试版本与指标

别名 Terminal Bench 3.0

  • Reported score · 单位未标注 · 排序方向未确认

各系列最新模型 · 公布成绩

常规展示范围。排名按指标与评测协议分组,已记录的工具、预算及框架分别展示。条件未说明的组保留公布值供查证。

Reported score

工具条件未记录 / max · 输出上限 128K tokens / Claude Code 2.1.207 · The card says reasoning_effort defaults to max and recommends keeping that default for benchmark reproduction. **Terminal-Bench 3.0**: We evaluate Terminal-Bench-3 tasks with the Claude Code 2.1.207 harness (reasoning effort=max, 400K context, and 128K maximum output), reporting avg@3 over three rollouts per task. Each rollout runs in an isolated container built from the task's official image, and is capped at 600 agent turns with a 10-hour timeout. Tool Search is disabled, and the artifacts each agent produces are scored by the task's official separate verifier.

Terminal-Bench · GLM-5.3模型卡;3.0 · Reported score · 工具条件未记录 / max · 输出上限 128K tokens / Claude Code 2.1.207 · The card says reasoning_effort defaults to max and recommends keeping that default for benchmark reproduction. **Terminal-Bench 3.0**: We evaluate Terminal-Bench-3 tasks with the Claude Code 2.1.207 harness (reasoning effort=max, 400K context, and 128K maximum output), reporting avg@3 over three rollouts per task. Each rollout runs in an isolated container built from the task's official image, and is capped at 600 agent turns with a 10-hour timeout. Tool Search is disabled, and the artifacts each agent produces are scored by the task's official separate verifier.
模型与配置成绩记录与证据
GLM-5.3Max28.3

历史记录 · 1 次发布

  • GLM-5.3本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)