Cursor

AI code editor with agents, CLI, cloud agents, web and iOS apps; plans now bundle Grok models and X features.

Where it ranks

Ranked by its own benchmark result where it has one; otherwise by the best model it offers.

Vendor: Anysphere (SpaceX/xAI)
Approach: Editors & extensions
Where it runs: Cloud only: needs the vendor’s service
Interface: Desktop app, Command line, Web app, Mobile app
Skill level: Beginner: works out of the box
Price: Free tier · from $8/mo
Pricing notes: Free (limited agent/chat); Plus $8/mo (Grok and Composer models only); Premium $30/mo adds cloud agents and third-party models (Claude, GPT, Gemini) at API list price, billed separately; Super $100; Ultra $200; Teams $30+/user/mo.
Source code: Closed source
Last verified: 18 Oct 2026

Price from cursor.com, 18 Oct 2026.

Benchmark	Result	Entry on the leaderboard	As of	Source
Terminal-Bench 2.1	79.3%	`Cursor CLI + Grok 4.5` reasoning effort: high; rank 9 of 22 entries; raw accuracy 79.33 ± 2.86 (95% CI half-width); entry date 2026-07-08; agent org: Cursor; read via the site's leaderboard-read API (page is client-rendered)	18 Oct 2026	tbench.ai
Terminal-Bench 3.0	15.7%	`Cursor CLI + Grok 4.5` reasoning effort: xhigh; rank 9 of 12 entries; raw accuracy 15.68 ± 2.88 (95% CI half-width); entry date 2026-07-15; agent org: Cursor; read via the site's leaderboard-read API (page is client-rendered)	18 Oct 2026	tbench.ai