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.
SOTA on SWE-Bench Pro (58.4): GLM-5.1 delivers significant leaps in coding and agentic performance.
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.
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.
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
The claims are about session length rather than single-shot accuracy, which is the axis that matters when an 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 → has to keep improving one artifact over hours instead of turns.
Read the full thread on X ↗
