{"slug": "z-ai-ships-glm-5-3-without-retraining-the-base-model-better-at-complex-coding", "title": "Z.ai Ships GLM-5.3 Without Retraining the Base Model: Better at Complex Coding and Long-Horizon Tasks", "summary": "Z.ai released GLM-5.3 on August 14, 2026, reusing the 743B GLM-5.2 base model unchanged and achieving gains solely through scaled post-training. Terminal-Bench 3.0 scores rose from 4.6 to 28.3, DeepSWE v1.1 from 46.2 to 66.9, and CyberGym reached 84.5%, with ExploitBench more than doubling to 54.4%. Weights are expected in about two weeks.", "body_md": "Z.ai released GLM-5.3 on August 14, 2026. The model reuses the 743B GLM-5.2 base unchanged. Every reported gain comes from scaled post-training: more long-horizon task environments, more environment types, longer training. Terminal-Bench 3.0 moves from 4.6 to 28.3, and DeepSWE v1.1 from 46.2 to 66.9. Cybersecurity moved further than Z.ai says it planned, with CyberGym at 84.5% and ExploitBench more than doubling to 54.4%. Weights arrive in about two weeks.\n\nThe post [Z.ai Ships GLM-5.3 Without Retraining the Base Model: Better at Complex Coding and Long-Horizon Tasks](https://www.marktechpost.com/2026/08/14/z-ai-ships-glm-5-3-without-retraining-the-base-model-better-at-complex-coding-and-long-horizon-tasks/) appeared first on [MarkTechPost](https://www.marktechpost.com).", "url": "https://wpnews.pro/news/z-ai-ships-glm-5-3-without-retraining-the-base-model-better-at-complex-coding", "canonical_source": "https://www.marktechpost.com/2026/08/14/z-ai-ships-glm-5-3-without-retraining-the-base-model-better-at-complex-coding-and-long-horizon-tasks/", "published_at": "2026-08-14 08:03:22+00:00", "updated_at": "2026-08-14 08:11:40.321403+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research"], "entities": ["Z.ai", "GLM-5.3", "GLM-5.2", "Terminal-Bench 3.0", "DeepSWE v1.1", "CyberGym", "ExploitBench", "MarkTechPost"], "alternates": {"html": "https://wpnews.pro/news/z-ai-ships-glm-5-3-without-retraining-the-base-model-better-at-complex-coding", "markdown": "https://wpnews.pro/news/z-ai-ships-glm-5-3-without-retraining-the-base-model-better-at-complex-coding.md", "text": "https://wpnews.pro/news/z-ai-ships-glm-5-3-without-retraining-the-base-model-better-at-complex-coding.txt", "jsonld": "https://wpnews.pro/news/z-ai-ships-glm-5-3-without-retraining-the-base-model-better-at-complex-coding.jsonld"}}