Model Detail
GLM-5
—GLM-5 is a large language model with 376.9B parameters released by zai-org. The model is registered under the text-generation pipeline tag on Hugging Face, and supports text->text inputs, distributed under the permissive mit license.
GLM-5 reports a Chatbot Arena ELO of 1,456 across 12,177 votes. On task-specific evaluations the model scores 72.8% resolved on SWE-Bench.
GLM-5 is priced at $0.95/M input tokens and $3.15/M output tokens. Pricing in this range is the working middle of the API market — neither the cheapest nor the most expensive option per token, so cost-fit is usually a function of how much output you generate.
GLM-5 ships with 376.9B parameters. Total weight footprint is approximately 753.9 GB, which is the relevant figure when planning local-inference VRAM. The mit license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
GLM-5 is best fit for general-purpose chat and instruction-following workloads. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Validating Hybrid-State Cache Recovery for GLM-5.3-Flash with vLLM and LMCache
arXiv:2609.15030v1 Announce Type: cross Abstract: External cache transfers can succeed while a hybrid language model resumes from an inconsistent state. We examine the full 45-layer GLM-5.3-Flash model, using the RedHatAI/ GLM-5.3-Flash-NVFP4 quantized checkpoint with vLLM and LMCache under four-way
GLM-5.2: Built for Long-Horizon Tasks
AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
arXiv:2604.02947v1 Announce Type: new Abstract: Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into concrete actions. T
