GLM 5
2525°
Run this model
Offers / Ads
Z.ai | 204,800 token context | $1.00/M input, $3.20/M output. GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.
Guides for this model
Best local LLM by use case (October 2026): the right open model for every job
How much VRAM do I actually need for local AI?
Open weights vs open source vs API-only: what you are actually allowed to do
What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)
Captain's notes
Notes from 2026-10-13
GLM-5 is Z.ai's flagship open-weights model, a 744B-parameter sparse MoE (40B active) built specifically for complex systems engineering and long-horizon agentic work. It scales up from GLM-4.5 with more parameters, more pre-training data, and an asynchronous RL infrastructure called slime that makes post-training more efficient. If your work involves building and running multi-step agent pipelines or large-scale backend systems, this is the open-weights model to benchmark first.
Known for
- Top-tier open-source scores on SWE-bench Verified and SWE-bench Multilingual
- Strong agentic and terminal task performance, competitive with frontier closed models
- 744B total / 40B active MoE architecture keeps inference costs manageable
- 204,800-token context window with DeepSeek Sparse Attention preserving long-context quality
- Iterative self-correction and autonomous execution beyond single-shot code generation
Watch out for
- At 744B parameters, self-hosting demands serious hardware; most users will hit the API instead.
- Licence terms are not detailed here — check the Hugging Face repository before any commercial deployment.
- Output pricing at $1.92/M tokens is not cheap for high-volume agentic loops that generate long traces.
Prompts to try
Design a distributed task queue
Design a production-ready distributed task queue in Python using Redis. Include a worker process with retry logic and exponential backoff, a dead-letter queue for failed jobs, and a simple producer API. Show the full file structure, each file's code, and explain the key architectural decisions.
Debug a concurrency bug
I have a Go HTTP server that occasionally returns stale data under load. Multiple goroutines read and write a shared map without synchronization. Identify the race condition, explain why it causes the symptom, rewrite the relevant section using sync.RWMutex, and add a test that would have caught this.
Plan a multi-step agent
You are building an agent that monitors a GitHub repository, detects when a new issue is labeled 'bug', reproduces the bug in a sandbox, proposes a fix, opens a pull request, and notifies a Slack channel. Break this into discrete agent steps, identify the tools each step needs, and flag where human approval should be required.
Compare with
- GLM 5.3 FlashXAPI-only model1,048,576 token context · $0.37/M input, $1.25/M output
- GLM 5V TurboAPI-only model202,752 token context · $1.20/M input, $4.00/M output
- GLM 5 TurboAPI-only model202,752 token context · $1.20/M input, $4.00/M output
- GLM 5.3 PrimeAPI-only model1,000,000 token context · $2.80/M input, $8.80/M output
More text models from z-ai
Questions people ask
- Is GLM-5 open weights and can I run it locally?
- Yes, the weights are published on Hugging Face at zai-org/GLM-5. At 744B parameters with 40B active, you will need substantial hardware to run it locally — consult the VRAM and quantization guides before attempting a self-hosted setup.
- What does GLM-5 cost and what is the context window?
- Via the Z.ai API, GLM-5 is priced at $0.60 per million input tokens and $1.92 per million output tokens, with a 204,800-token context window.
- How does GLM-5 differ from GLM-4.5 or GLM-4.7?
- GLM-5 scales from GLM-4.5's 355B parameters (32B active) to 744B (40B active) and increases pre-training data from 23T to 28.5T tokens; it also adds DeepSeek Sparse Attention and the slime asynchronous RL infrastructure, delivering measurable gains on coding, reasoning, and agentic benchmarks over both predecessors.
Captain's verdictThe strongest open-weights option for serious agentic and systems-engineering work, provided you can absorb the infrastructure or the output token bill.
Model card on Hugging Face
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
How this score adds up
This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
GLM 5 is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153