Home Model series GLM GLM-4.7 GLM-4.7 · Terminal-Bench · GLM-4.7模型卡;2.0 · Scores and configurations GLM-4.7 · Terminal-Bench · GLM-4.7模型卡;2.0 · Scores and configurations GLM-4.7 record for Terminal-Bench · GLM-4.7模型卡;2.0. 1 score record for this release, including 1 exact value (may include historical records). Includes 2 source locations.
Scores and evaluation conditions GLM-4.7 · Terminal-Bench scores and configurations Metric and score Configuration and evaluation conditions Sources Reported score 41 Reported 41.0 · Unit not specified Published Unconfirmed
GLM-4.7 · thinking Settings 官方模型卡目标列;逐行scaffold、工具、采样及预算条件见protocol。行内明确标注think/Preserved Thinking。 Unknowns 未逐项说明的指标单位、题集修订、服务精度和运行次数保持未知。 Tools Tool access not recorded Reasoning budget Output limit 16384 tokens Framework not recorded Protocol temperature=0.7; top-p=1.0; max new tokens=16384. Metric, unit and scaffold are not stated. Conditions GLM-4.7; source states 41%, but does not identify pass-rate versus mean-reward metric. 2026-11-18按完整模型卡修正单位、指标/题集或协议标注,数字不变。 View this score in rankings
Benchmark versions and metrics Aliases Terminal Bench 2.0
Reported score · Unit not specified · Ranking direction unconfirmed