Home Model series GLM GLM-5 GLM-5 · CC-Bench-V2 · GLM-5固定v2报告/模型卡;v2 · React · Scores and configurations GLM-5 · CC-Bench-V2 · GLM-5固定v2报告/模型卡;v2 · React · Scores and configurations GLM-5 record for CC-Bench-V2 · GLM-5固定v2报告/模型卡;v2 · React. 3 score records for this release, including 3 exact values (may include historical records). Includes 3 source locations.
Scores and evaluation conditions GLM-5 · CC-Bench-V2 scores and configurations Metric and score Configuration and evaluation conditions Sources ISR 34.6 Reported 34.6 · 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 not recorded Framework not recorded Protocol Frontend Instance Success Rate for React projects. Conditions Frontend Instance Success Rate for React projects. React View this score in rankings CSR 71 Reported 71 · 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 not recorded Framework not recorded Protocol Frontend Check-item Success Rate for React projects. Conditions Frontend Check-item Success Rate for React projects. React View this score in rankings BSR 100 Reported 100 · 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 not recorded Framework not recorded Protocol Build Success Rate for React projects. Conditions Build Success Rate for React projects. React View this score in rankings
Benchmark versions and metrics Aliases CC-Bench-V2
ISR · Unit not specified · Higher is better CSR · Unit not specified · Higher is better BSR · Unit not specified · Higher is better