Agents

GLM-5.1 gives teams a stronger model for coding, tool use, and sustained agent performance on Together AI. Learn more: http://www.together.a…

GLM-5.1 is Z.ai's post-training upgrade to GLM-5, now available on Together AI, delivering a 28% coding performance improvement through a refined reinforcement learning pipeline while retaining the...

DGX agentx-post
agentstogether-ai--x

GLM-5.1 is Z.ai's post-training upgrade to GLM-5, now available on Together AI, delivering a 28% coding performance improvement through a refined reinforcement learning pipeline while retaining the same 754B parameter (40B activated) MoE architecture with a 200K context window. The model supports thinking mode, tool calling, and structured JSON output for agentic engineering workflows, and is compatible with popular coding agent frameworks including Claude Code, Kilo Code, Cline, and Roo Code. It achieves state-of-the-art results on SWE-Bench Pro and is distinguished by its ability to sustain high performance across long-horizon agentic tasks — iterating over hundreds of rounds and thousands of tool calls without plateauing.

Related

Source: agents

Loading related sources…