GLM-5.1 pushes open weights toward eight-hour autonomous runs
- Source
- x.com
- Date
Introducing GLM-5.1: The Next Level of Open Source - Top-Tier Performance: #1 in open source and #3 globally across SWE-Bench Pro, Terminal-Bench, and NL2Repo. - Built for Long-Horizon Tasks: Runs autonomously for 8 hours, refining strategies through thousands of iterations. Blog: https://t.co/hmyDe4Nel3 Weights: https://t.co/CuUjXcPKJD API: https://t.co/fz6reja4fb Coding Plan: https://t.co/Nk8Y98HNhU Coming to https://t.co/WCqWT0qCQb in the next few days.
Building a Linux Desktop from Scratch Using a self-review loop, GLM-5.1 spent 8 hours autonomously refining features, styling, and interactions to build a functional desktop environment.
Vector-DB-Bench: 6x Performance Boost In high-performance database optimization, GLM-5.1 reached 21.5k QPS over 600+ iterations and 6,000+ tool calls. This is 6x the performance of a standard 50-turn session.
Context
Z.ai's GLM-5.1 release highlights a coding model that can keep revising its approach over extended runs. In a reported database-optimization experiment, the model completed more than 600 iterations and 6,000 tool calls, producing a system that handled 21,500 queries per second. The release thread says that was six times the performance reached in a standard 50-turn session.
The comparison concerns the speed of the database being optimized, rather than the model's own response speed. The model card describes the working loop as running experiments, reading results and revising strategies. The reported benefit comes from using additional runtime for repeated optimization of the same task.
- SWE-bench — The standard benchmark for AI coding agents: real GitHub issues from real repositories, scored by whether the agent's patch passes the project's own tests.
postWe’re sharing how GLM-5.3 helped build and optimize the inference infrastructure serving GLM-5.3-Flash.- postGLM-5 lands in Zhipu's Coding Plan Pro as pricing shifts
articleZ.ai details GLM-5.3's leap in exploit analysis and staged release
postGLM-5.3 API launches for coding and cybersecurity agentic tasks
Checking sign-in…
Loading comments…