SWE-Marathon (v1.1) · GLM-5.3模型卡;v1.1 · 测试定义与成绩

SWE-Marathon (v1.1) · GLM-5.3模型卡;v1.1 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 SWE-Marathon (v1.1)

  • 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 128000 tokens / Claude Code 2.1.207 · The card says reasoning_effort defaults to max and recommends keeping that default for benchmark reproduction. **SWE-Marathon**: We evaluate GLM-5.3 using Claude Code 2.1.207 with maximum effort level, `temperature = 1.0`, `top_p = 0.95`, `max_new_tokens = 128000`, and a 1M-token context window. For `strip-clone`, the original anti-cheat checks used overly broad import detection that could reject valid implementations. We removed the affected checks and performed llm-based inspection instead to avoid false positives. For `parameter-golf` and `trimul-cuda`, changes to the NVIDIA wheels caused the Docker image builds to fail, so we added `--extra-index-url https://pypi.org/simple` to restore successful builds.

SWE-Marathon (v1.1) · GLM-5.3模型卡;v1.1 · Reported score · 工具条件未记录 / max · 输出上限 128000 tokens / Claude Code 2.1.207 · The card says reasoning_effort defaults to max and recommends keeping that default for benchmark reproduction. **SWE-Marathon**: We evaluate GLM-5.3 using Claude Code 2.1.207 with maximum effort level, `temperature = 1.0`, `top_p = 0.95`, `max_new_tokens = 128000`, and a 1M-token context window. For `strip-clone`, the original anti-cheat checks used overly broad import detection that could reject valid implementations. We removed the affected checks and performed llm-based inspection instead to avoid false positives. For `parameter-golf` and `trimul-cuda`, changes to the NVIDIA wheels caused the Docker image builds to fail, so we added `--extra-index-url https://pypi.org/simple` to restore successful builds.
模型与配置成绩记录与证据
GLM-5.3Max42.5

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)