reasoning_effort 未逐项注明、评测使用官方 API 还是本地权重未注明、精度/量化及 serving 版本未注明
工具
工具条件未记录
推理预算
输出上限 65536 tokens
框架
Claude Code 2.1.207
协议
Terminal Bench 2.1; official model card says Claude Code 2.1.207, temperature=1.0, top_p=1, max_new_tokens=65536 and 6-hour timeout. Metric choice is not given.
条件
GLM-5.3-Flash; figure provides no unit or metric label; API/weight precision and reasoning effort unspecified.
GLM-5.3-Flash · Terminal-Bench · 2.1;GLM 官方图仅列数值,具体 score / mean reward 指标未注明 · Scores and configurations
GLM-5.3-Flash record for Terminal-Bench · 2.1;GLM 官方图仅列数值,具体 score / mean reward 指标未注明. 1 score record for this release, including 1 exact value (may include historical records). Includes 2 source locations.
reasoning_effort 未逐项注明、评测使用官方 API 还是本地权重未注明、精度/量化及 serving 版本未注明
Tools
Tool access not recorded
Reasoning budget
Output limit 65536 tokens
Framework
Claude Code 2.1.207
Protocol
Terminal Bench 2.1; official model card says Claude Code 2.1.207, temperature=1.0, top_p=1, max_new_tokens=65536 and 6-hour timeout. Metric choice is not given.
Conditions
GLM-5.3-Flash; figure provides no unit or metric label; API/weight precision and reasoning effort unspecified.