The best model for Cursor right now is GPT-5.6 Sol, with a 77.4 Artificial Analysis Coding Index; GPT-5.6 Terra (76.7) and Claude Fable 5 (76.5) follow. Cursor leans on fast agentic edits and long files — weight speed and context alongside the coding score, and mind per-token price if you bring your own key.
Ranked by the Artificial Analysis Coding Index, filtered to models with the tool-calling support agentic editors require. Speed, context and price are shown per row — cursor leans on fast agentic edits and long files — weight speed and context alongside the coding score, and mind per-token price if you bring your own key.
GPT-5.6 Sol leads on the Coding Index (77.4) among models with the tool-calling support Cursor requires. Cursor leans on fast agentic edits and long files — weight speed and context alongside the coding score, and mind per-token price if you bring your own key.
GPT-5.6 Terra (76.7 coding, $2.50/M) and Kimi K3 (76.2 coding, $3.00/M) give most of the leader's capability at a lower per-token price.