Home Model series GLM GLM-5.2 GLM-5.2 · SWE-bench Pro · GLM-5.2模型卡;Pro · Scores and configurations GLM-5.2 · SWE-bench Pro · GLM-5.2模型卡;Pro · Scores and configurations GLM-5.2 record for SWE-bench Pro · GLM-5.2模型卡;Pro. 1 score record for this release, including 1 exact value (may include historical records). Includes 2 source locations.
Scores and evaluation conditions GLM-5.2 · SWE-bench Pro scores and configurations Metric and score Configuration and evaluation conditions Sources Reported score 62.1 Reported 62.1 · Unit not specified Published Unconfirmed
GLM-5.2 · 档位未注明 Settings 官方模型卡目标列;逐行scaffold、工具、采样及预算条件见protocol。未由默认模式或推荐解码设置推断实际推理档位。 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 32k tokens Framework OpenHands Protocol OpenHands with tailored instruction prompt; temperature=1; top_p=1; max_new_tokens=32k; 400K context. Conditions GLM-5.2; effort, serving endpoint and precision not stated. 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 SWE-bench Pro
Reported score · Unit not specified · Ranking direction unconfirmed