GLM-4.6 · Terminal-Bench(2.0; GLM source does not name score/mean-reward metric) 40.5 · 附件证据(ev-glm-4-6-terminal-bench)
GLM-4.6 的 Terminal-Bench · 2.0; GLM source does not name score/mean-reward metric 官方出处。GLM-4.6 official chart configuration · 40.5。见《LLM Performance Evaluation: Agentic, Reasoning and Coding》LLM Performance Evaluation chart, Terminal-Bench row; GLM-4.6 column。证据 ev-glm-4-6-terminal-bench。
原文与定位
GLM-4.6 · Terminal-Bench(2.0; GLM source does not name score/mean-reward metric),GLM-4.6 official chart configuration配置,Reported score; metric/unit unspecified in GLM source 40.5(具体成绩公布时间未确认)。见《LLM Performance Evaluation: Agentic, Reasoning and Coding》LLM Performance Evaluation chart, Terminal-Bench row; GLM-4.6 column。 查看成绩条件
40.5
- 官方材料
- LLM Performance Evaluation: Agentic, Reasoning and Coding
- 定位
- 附件 · LLM Performance Evaluation chart, Terminal-Bench row; GLM-4.6 column
- 材料版本
- Official embedded chart downloaded as 本地留存副本 and visually read; exact score labels, 8 benchmark names and w/Tools annotations checked.
- 版本公布
- 未确认
- 披露时间
- 未确认 · 首发/后补未确认
- 采集时间
- 历史依据
- 暂无可靠历史版本依据
引用文本
GLM-4.6 · Terminal-Bench(2.0; GLM source does not name score/mean-reward metric),GLM-4.6 official chart configuration配置,Reported score; metric/unit unspecified in GLM source 40.5(具体成绩公布时间未确认)。官方出处 LLM Performance Evaluation: Agentic, Reasoning and Coding(附件,Official embedded chart downloaded as 本地留存副本 and visually read; exact score labels, 8 benchmark names and w/Tools annotations checked.)LLM Performance Evaluation chart, Terminal-Bench row; GLM-4.6 column,https://cdn.bigmodel.cn/markdown/1759214269399glm-4.6-1.png?attname=glm-4.6-1.png。Benchlog https://benchlog.lekshome.cc/evidence/glm-4-6/ev-glm-4-6-terminal-bench/
关联成绩与条件
| 指标与成绩 | 配置与评测条件 | 证据关系 |
|---|---|---|
| Reported score; metric/unit unspecified in GLM source40.5原文 40.5 · 单位 未标注 公布 未确认 | GLM-4.6 official chart configuration
| 直接支持该成绩 在排名中查看此成绩 |