ProgramBench (Almost Solved) · GLM-5.3模型卡;Almost Solved · 测试定义与成绩

ProgramBench (Almost Solved) · GLM-5.3模型卡;Almost Solved 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 ProgramBench (Almost Solved)

  • 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

The card says reasoning_effort defaults to max and recommends keeping that default for benchmark reproduction. No benchmark-specific protocol is stated.

ProgramBench (Almost Solved) · GLM-5.3模型卡;Almost Solved · Reported score · The card says reasoning_effort defaults to max and recommends keeping that default for benchmark reproduction. No benchmark-specific protocol is stated.
模型与配置成绩记录与证据
GLM-5.3Max19

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)