aiexpert
Home / News / Brief
Research · Aug 20, 2026, 10:35 PM · 3 sources

Z.ai releases GLM-5.3: same base model as GLM-5.2, but post-training alone lifts coding 6×, leads on CyberGym

Z.ai released GLM-5.3 on August 14, 2026, reusing the same 743-billion-parameter Mixture-of-Experts base model as June's GLM-5.2. Every reported performance gain comes from scaled post-training alone, a direct test of whether a frozen base can be pushed substantially further through extended reinforcement learning. The model shows largest jumps on coding and long-horizon tasks: Terminal-Bench 3.0 moves from 4.6 to 28.3 (6×), DeepSWE v1.1 from 46.2 to 66.9, and Agents' Last Exam from 23.8 to 28.5, all vendor-reported with full harness documentation.

The surprising result is cybersecurity: GLM-5.3 reaches 84.5% on CyberGym, a vulnerability-discovery benchmark, edging out Claude Fable 5 (83.8%) and GPT-5.6 Sol (83.6%). Z.ai intentionally trained on vulnerability data to improve bug-finding, but the model reportedly developed multi-stage attack-chain reasoning at scale—behavior the company frames as emergent rather than targeted. On cost-per-task, GLM-5.3 scores 31.4% on Z.ai's internal Code Bench at ~50K output tokens, versus Opus 4.8's 29.5% at ~120K tokens, pointing to significant inference efficiency gains alongside capability jumps.

For researchers and teams building long-horizon agentic systems, GLM-5.3's trajectory signals that post-training scaling and environment diversity can move fixed bases further than architects expected, particularly on tasks that reward sustained reasoning and iterative refinement. Open weights are promised ~August 28, 2026 (two weeks post-launch) after safety evaluation, meaning independent verification via Terminal-Bench and public reproducibility is still pending. The observation that parameter count tells only one part of the scaling story—matching it with post-training compute, data volume, and task horizon—challenges the industry's fixation on model size as the primary capability signal.

Sources

Everything this brief rests on
  1. 01 Primary source latent.space
  2. 02 [AINews] Death of Params: Z.ai CEO Jie Tang on GLM 5.3 and the new Post-training Scaling Law latent.space “GLM-5.3's big jumps come solely from RL on long horizon environments: The environments now cover a much broader range of production workflows, with tasks designed around how engineering and research work is actually carried out in practice.”
  3. 03 GLM-5.3: Post-Training Alone Rebuilt the Coding Ladder digitalapplied.com “Terminal-Bench 3.0 moves from 4.6 to 28.3 against GLM-5.2. DeepSWE v1.1 moves from 46.2 to 66.9. Agents' Last Exam (CLI) moves from 23.8 to 28.5. On CyberGym GLM-5.3 scores 84.5%, ahead of Claude Fable 5 (83.8%) and GPT-5.6 Sol (83.6%).”