Home Model series GLM GLM-5 GLM-5 · Terminal-Bench · GLM-5固定v2报告/模型卡;2.0 · Original question set · Scores and configurations GLM-5 · Terminal-Bench · GLM-5固定v2报告/模型卡;2.0 · Original question set · Scores and configurations GLM-5 record for Terminal-Bench · GLM-5固定v2报告/模型卡;2.0 · Original question set. 2 score records for this release, including 2 exact values (may include historical records). Includes 4 source locations.
Scores and evaluation conditions GLM-5 · Terminal-Bench scores and configurations Metric and score Configuration and evaluation conditions Sources Reported score 56.2 Reported 56.2 · Unit not specified Published Unconfirmed
GLM-5 · 报告与固定模型卡 Settings 最终后训练GLM-5;各行scaffold、解码与工具条件分别见protocol,未将工具或来源另立为推理档位。 Unknowns 来源未逐项明确思考开关、reasoning effort、服务精度与完整题集修订。、Tool-Decathlon报告39.2与固定卡38.0均保留;BrowseComp上下文管理的正文与附录方法描述不一致。 Tools Tool access not recorded Reasoning budget Output limit 8192 tokens Framework Terminus-2 Protocol Terminus 2 scaffold; timeout 2h; temperature 0.7; top_p 1.0; max_new_tokens 8192; 128K context; 16 CPUs and 32 GB RAM. Thinking mode and reasoning effort are not stated. Conditions Terminus 2 scaffold; timeout 2h; temperature 0.7; top_p 1.0; max_new_tokens 8192; 128K context; 16 CPUs and 32 GB RAM. Thinking mode and reasoning effort are not stated. View this score in rankings Reported score 56.2 Reported 56.2 · Unit not specified Published Unconfirmed
GLM-5 · 报告与固定模型卡 Settings 最终后训练GLM-5;各行scaffold、解码与工具条件分别见protocol,未将工具或来源另立为推理档位。 Unknowns 来源未逐项明确思考开关、reasoning effort、服务精度与完整题集修订。、Tool-Decathlon报告39.2与固定卡38.0均保留;BrowseComp上下文管理的正文与附录方法描述不一致。 Tools Tool access not recorded Reasoning budget Output limit 65536 tokens Framework Claude Code 2.1.14 Protocol Claude Code 2.1.14 scaffold; think mode, default effort; temperature 1.0; top_p 0.95; max_new_tokens 65536; wall-clock limits removed; CPU and memory limits retained; scores averaged over 5 runs. Conditions Claude Code 2.1.14 scaffold; think mode, default effort; temperature 1.0; top_p 0.95; max_new_tokens 65536; wall-clock limits removed; CPU and memory limits retained; scores averaged over 5 runs. View this score in rankings
Benchmark versions and metrics Aliases Terminal-Bench
Reported score · Unit not specified · Ranking direction unconfirmed