GLM-5.3
Zhipu AI·
Overview
Open-weight release of Z.ai's GLM-5.3 flagship: a 753B MoE activating ~40B parameters per token with a 1M-token context, architecturally identical to GLM-5.2 — the capability gain is post-training only. Weights landed on Hugging Face on 2026-08-28, fourteen days after launch, once Z.ai's safety review completed — but under a bespoke GLM-5.3 License instead of the MIT license GLM-5.2 shipped under: use, modification, distribution, sublicensing, sale, deployment and fine-tuning are all permitted, but a company with more than $10B aggregate revenue over any 12 consecutive months must pass a Z.ai security review before hosting the model commercially. Individual users and smaller companies are unaffected. The official checkpoint is FP8 (~743 GB of weights) and needs an 8-GPU H100/H200-class node; vLLM and SGLang serve it directly.
Capabilities and innovations
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| Terminal-Bench 3.0 | 28.3% | vendor Terminal-Bench 3.0 28.3 — Z.ai-reported in the GLM-5.3 launch comparison table, mirrored from the cloud entry (zhipu-3). Figures taken from launch coverage; the primary table at docs.z.ai was not reachable from the build environment for direct verification. Do not compare against the terminal_bench column: 3.0 is a harder generation on a different scale. |
- GPQA Diamond: independent evaluation pending — Z.ai published no GPQA table for this release; Vals AI and Artificial Analysis had no GLM-5.3 entry as of 2026-08-31.
- Humanity’s Last Exam (no tools): not reported by the vendor — Z.ai reports HLE with tools only, which is not comparable to the no-tools HLE used here (same handling as the GLM-5.2 entry).
- SWE-bench Pro: not reported by the vendor — Z.ai reports DeepSWE v1.1 (66.9, GLM-5.2: 46.2) instead of SWE-bench Pro.
- MMLU-Pro: independent evaluation pending — Not in Z.ai's table; Vals AI had no GLM-5.3 entry as of 2026-08-31.
- Terminal-Bench 2.x: not reported by the vendor — Z.ai reports Terminal-Bench 3.0 only, a harder benchmark generation than the 2.x values in this column — GLM-5.2 scores 4.6 on 3.0 versus 77.9 on 2.1. That score is recorded on its own axis in terminal_bench_3; putting it here would read as a regression.
- MMMU-Pro: not reported by the vendor
Architecture and hardware
- Parameters
- 753B total, 40B active per token (MoE)
- Estimated VRAM at Q4
- ~433 GB, Frontier class
- Quantization formats
- FP8
- Recommended runtime
- vLLM
- License
- GLM-5.3 License (custom, revenue-tiered)
Links
More from Zhipu AI
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.