GLM-5.2
Long-horizon agentic engineering, repository-scale refactors, multi-hour autonomous coding, cross-file/long-chain tasks, frontend coding (best-in-class among open models), tool use, and competition math.
Empirical Evaluation Results
Architectural Profile & Capabilities
Long-horizon agentic engineering, repository-scale refactors, multi-hour autonomous coding, cross-file/long-chain tasks, frontend coding (best-in-class among open models), tool use, and competition math. The strongest open-weight coding/agent model available — trails only Claude Opus 4.8, at ~1/6th the cost. MoE 744B/40B-active, MIT-licensed open weights. Dual reasoning-effort modes (`high` / `max`). Released Jun 13, 2026. *Superseded by GLM-5.3.*
Sparse Mixture-of-Experts routing: activates only a subset of parameter experts per token, delivering frontier-level intelligence with exceptional efficiency.
Recommended Workloads & Primary Use Cases
Calls to GLM-5.2 are routed through strict Zero Data Retention inference channels. Prompts and outputs are never stored, indexed, or monitored by Z.ai.
More Models from Z.ai
Compare other engines available in this laboratory.
Zhipu AI's 320B/18B-active multimodal MoE model featuring hybrid linear attention, 1.31M context, and top-tier agentic coding efficiency.
Z.ai's most capable model (released Aug 14, 2026).
GLM-5.1 is a high-performance foundation model engineered by Z.ai, accessible with Zero Data Retention on ARMES.