Home Model series GLM GLM-5.3 GLM-5.3 · FrontierSWE · Release/version unspecified in GLM-5.3 card · Scores and configurations GLM-5.3 · FrontierSWE · Release/version unspecified in GLM-5.3 card · Scores and configurations GLM-5.3 record for FrontierSWE · Release/version unspecified in GLM-5.3 card. 1 score record for this release, including 1 exact value (may include historical records). Includes 2 source locations.
Scores and evaluation conditions GLM-5.3 · FrontierSWE scores and configurations Metric and score Configuration and evaluation conditions Sources Dominance score; unit unspecified in GLM source 78.1 Reported 78.1 · Unit not specified Published Unconfirmed
GLM-5.3 reasoning_effort=max Settings Terminal-Bench 3.0 与 Agents' Last Exam (CLI) 方法说明明确标注 max;其余服务及权重配置未注明。 Unknowns 评测使用官方 API 还是本地权重未注明、精度/量化与 serving 版本未注明 Tools Tool access not recorded Reasoning budget max · Output limit 128K tokens Framework not recorded Protocol Proximal evaluation; 1M context; max effort; 128K maximum output; dominance score reported as of 2026-08-14. Conditions GLM-5.3; benchmark release and unit unspecified in source. View this score in rankings
Benchmark versions and metrics Aliases FrontierSWE
Dominance score; unit unspecified in GLM source · Unit not specified · Ranking direction unconfirmed