Introducing GLM-5: From Vibe Coding to Agentic Engineering
GLM-5 is built for complex systems engineering and long-horizon agentic tasks. Compared to GLM-4.5, it scales from 355B params (32B active) to 744B (40B active), with pre-training data growing from 23T to 28.5T tokens.
Try it now: https://t.co/WCqWT0raFJ
Weights: https://t.co/DteNDHjSEh
Tech Blog: https://t.co/Wxn5ARTJxH
OpenRouter (Previously Pony Alpha): https://t.co/7Khf64Lxg6
Rolling out from Coding Plan Max users:
On our internal evaluation suite CC-Bench-V2, GLM-5 significantly outperforms GLM-4.7 across frontend, backend, and long-horizon tasks, narrowing the gap with Claude Opus 4.5.
On Vending Bench 2, GLM-5 ranks #1 among open-source models, finishing with a final account balance of $4,432. It approaches Claude Opus 4.5, demonstrating strong long-term planning and resource management.
For GLM Coding Plan subscribers: Due to limited compute capacity, we’re rolling out GLM-5 to Coding Plan users gradually.
- Max plan users: You can enable GLM-5 now by updating the model name to "GLM-5" (e.g. in ~/.claude/settings.json for Claude Code).
- Other plan tiers: Support will be added progressively as the rollout expands.
- Quota note: Requests to GLM-5 consume more plan quota than GLM-4.7.
pretraining — The first, biggest phase of building a model: training it on enormous amounts of text so it learns language, facts, and reasoning in general.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition → for a 744B parameter, 40B active model that Z.ai ranks first among open-source entries on Vending Bench 2 give teams a self-hostable option for long-horizon AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → work, at the cost of higher plan quota burn than GLM-4.7.
Read the full thread on X ↗
