Agentic-Coding

Claude Opus 5
Anthropic's flagship model for deep agentic coding — built for long-horizon autonomous runs, multi-file refactors, and finishing what it …
Models
Claude Sonnet 5
Anthropic's daily-driver coding model — near-Opus quality on coding and agentic work at roughly half the cost.
Models
GLM-5.2
Z.ai's MIT-licensed, 1M-token open-weight model — beats GPT-5.5 on FrontierSWE at a fraction of the cost, with full weights to self-host.
Models
Grok 4.6
xAI's frontier model for coding and agentic work, paired with Grok Build — their own open-source coding agent and terminal UI.
Models
Kimi K2.7 Code
Moonshot AI's coding-specialized model — deep thinking-mode reasoning over long agentic sessions, at a fraction of frontier US pricing.
Models