Best AI for coding
Choosing an AI for coding right now? Here's how the open options we've looked at stack up — and who each is really for. These are first-look assessments; we flag where we've gone hands-on.
Ranked by how broadly each fits real coding work — not by a benchmark number.
- 01
The most directly a coding model: a 753B open-weight flagship built for coding and agentic work, with a 1M-token context and both self-host and a hosted Z.ai API. First-look — vendor benchmarks, not yet hands-on.
Zhipu AI (Z.ai) - 02
Not a model — the open control center that RUNS coding agents (including GLM-5.2, Claude Code, Codex). Reach for it when you want autonomous, multi-step coding workflows you self-host. First-look.
All-Hands-AI - 03
A tiny 3B open reasoning model that punches above its size on code benchmarks and runs on a single GPU. The niche pick when you need something small and self-hostable for focused code reasoning. First-look.
Weibo AI