GLM-5.2 Announced: New Model for Long-Horizon Tasks

Architecture for 1M Context IndexShare for DSA MTP with IndexShare and KVShare Efficiently Serving 1M Context Length slime for Agentic RL RL for Long-Horizon Task with Anti-hacking Full Benchmark Table Getting started with GLM-5.

Architecture for 1M Context IndexShare for DSA MTP with IndexShare and KVShare Efficiently Serving 1M Context Length slime for Agentic RL RL for Long-Horizon Task with Anti-hacking Full Benchmark Table Getting started with GLM-5.2 Use GLM-5.2 with GLM Coding Plan Chat with GLM-5…

On SWE-Marathon , an ultra-long-horizon software engineering benchmark covering tasks such as building compilers, optimizing kernels, and developing production-grade services, GLM-5.2 still has room to grow, trailing Opus 4.8 by 13% while remaining second only to the Opus series…