GLM-5.3

Z.ai's agentic coding and cybersecurity successor to GLM-5.2. It uses the same base model — a 753B-class MoE with a 1M-token context — and attributes every gain to one month of scaled post-training across more numerous, diverse, and longer-horizon task environments. The training stack combines IndexShare for long-context processing, SAO with compaction for long-horizon RL, and the open-source slime framework; new scheduling, caching, and workload-aware configurations improved end-to-end RL throughput by more than 2.3×.

Z.ai reports large gains over GLM-5.2 on complex work: Terminal-Bench 3.0 rises from 4.6 to 28.3, DeepSWE v1.1 from 46.2 to 66.9, and Agents' Last Exam from 23.8 to 28.5. Cybersecurity environments produced especially steep improvements: 84.5% on CyberGym, 54.4% on ExploitBench (versus 24.4%), and 105/130 completed ExploitGym tasks under normalized two-/six-hour budgets (versus 29/39). The API requires thinking and offers low, high, and max reasoning effort; Z.ai said at launch that model weights would follow in two weeks, so no public checkpoint or license was available on release day.