NL2Repo · GLM-5.3模型卡;unknown · 测试定义与成绩

NL2Repo · GLM-5.3模型卡;unknown 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 NL2Repo

  • 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 / 输出上限 64k tokens / 框架未记录 · The card says reasoning_effort defaults to max and recommends keeping that default for benchmark reproduction. **NL2Repo**: We evaluated NL2Repo with `temperature=1.0`, `top_p=1.0`, and `max_new_tokens=64k` under 1M context. To prevent hacking, we use rule-based and a LLM-based judgement to prevent malicious behaviors (e.g., unauthorized pip or curl operations).

NL2Repo · GLM-5.3模型卡;unknown · Reported score · 工具条件未记录 / 输出上限 64k tokens / 框架未记录 · The card says reasoning_effort defaults to max and recommends keeping that default for benchmark reproduction. **NL2Repo**: We evaluated NL2Repo with `temperature=1.0`, `top_p=1.0`, and `max_new_tokens=64k` under 1M context. To prevent hacking, we use rule-based and a LLM-based judgement to prevent malicious behaviors (e.g., unauthorized pip or curl operations).
模型与配置成绩记录与证据
GLM-5.3Max58

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)