MiniMax Code Goes Open Source: Performance Beats Codex & Claude
MiniMax Code is now open on GitHub, offering faster, cheaper AI coding with 76.7% success—outperforming Codex and Claude Code.
MiniMax opens the source code of MiniMax Code.
The head of development and research at the company, Ronnie, announced the project's publication on GitHub with the words:
"Created together with developers. Now it is being created openly. See you on GitHub."
That is, MiniMax Code was initially created together with developers, and now the product itself is being moved to open development.
This is especially interesting against the backdrop of the company's recent tests. On the same model and a set of 30 tasks, MiniMax Code achieved 76.7% successful completions versus 66.7% in Codex and 63.3% in Claude Code.
The average execution time was 4 minutes 33 seconds versus 6 minutes 43 seconds in Codex and 9 minutes 38 seconds in Claude Code.
The cost per run — $1.83 versus $3.47 in Codex and $18.34 in Claude Code.
Now it will be possible to see how this wrapper is built and what gives it such a difference.
Comments
Weekly digest
The best of vibe coding, AI agents and open source — once a week, no spam.
Related articles
All articlesGLM-5.3 Flash Released: Zhipu's New AI Model Beats GLM-5.2
Zhipu officially releases GLM-5.3 Flash, scoring 84.3 on Terminal-Bench, outperforming GLM-5.2 at 10x lower cost. Open weights, MIT license, 1M context.
Cline Desktop Launches AI Agent Workspace for macOS & Windows
Cline Desktop offers an open‑source AI workspace with parallel agents, task scheduling, checkpoints, branching, and a plugin marketplace, now on macOS and Windows.
Moonshot Releases KIMI K3: The World's Largest Open-Source Model
Moonshot unveils KIMI K3, a 2.8 trillion parameter MoE model with a 1M token context window, outperforming major models in knowledge-based tasks.