Public KG record
GLM-5.3
Recorded overview
GLM-5.3 uses the same base model as GLM-5.2 — every gain comes from post-training. Compared with GLM-5.2, it is much better at complex coding and long-horizon tasks
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Benchmarks: BF16召回率为65.6%，覆盖25/32个漏洞
- Benchmarks: AWQ INT4召回率为61.5%，覆盖23/32个漏洞
- Benchmarks: 在内部 Binary Exploitation benchmark 中完成控制流劫持评测
- Benchmarks: SemiAnalysis AgentX
- Benchmarks: 使用 SemiAnalysis AgentX 评测智能体请求混合负载
- Benchmarks: 在 GB200 NVL72 上进行服务性能基准测试
- Benchmarks: 基准测试运行成本与 Gemini 4 Argon 接近
- Benchmarks: Terminal-Bench 2.1 得分 83.9
Evidence coverage
The KG currently records 11 known information dimensions and has 8 undocumented dimensions, linked to 17 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Z.ai — releases
- Zhipu AI / GLM — develops
- Hugging Face Inference Providers — supports
- Altar-1 — based on
- Clairic — outperforms