GLM-5
Zhipu AI·
LLMsopen-weightcloud + localFrontier
Overview
744B MoE (40B active) open-weight model with DeepSeek Sparse Attention and strong agentic/frontend coding performance.
Capabilities and innovations
744B total / 40B active MoE200K contextAgentic workflowsFrontend coding (98% build success)MIT licenseDeepSeek Sparse AttentionSlime Async RL Framework98% Frontend Build Success RateStealth-Launched as Pony Alpha on OpenRouter
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| MMLU-Pro | 86.03% | unsourced |
- GPQA Diamond: not reported by the vendor
- Humanity’s Last Exam (no tools): not reported by the vendor
- SWE-bench Verified: not reported by the vendor
- SWE-bench Pro: not reported by the vendor
- MMLU: not reported by the vendor
- Terminal-Bench 2.x: not reported by the vendor
- MMMU-Pro: not reported by the vendor
Architecture and hardware
- Parameters
- 744B total, 40B active per token (MoE)
- Estimated VRAM at Q4
- ~428 GB, Frontier class
Reliability
- Hallucination rate (Vectara HHEM)
- 10.1% (lower is better)independent
- Agentic tool use (τ-bench)
- 82.1% (higher is better)third party
Links
More from Zhipu AI
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.