Cursor has for the first time introduced what it claims is a competitive coding model, alongside the 2.0 version of its integrated development environment (IDE) with a new feature that allows running tasks with multiple agents in parallel.
The company’s flagship product is an IDE modeled after Visual Studio Code in many respects, but with a strong emphasis on vibe coding and heavier direct integration of large language model-based tools in the interface and workflow. Since its introduction, Cursor has supported models developed by other companies such as OpenAI, Google, and Anthropic. However, while it has trialed its own built-in models, they weren’t competitive with the big frontier models.
It’s a different story now, according to the company’s claims about Composer. Built with reinforcement learning and a mixture-of-experts architecture, Composer is dubbed by Cursor “a frontier model that is 4x faster than similarly intelligent models”—a significant claim when you consider what it’s competing with.
The emphasis seems to be on speed. In a benchmark chart displaying Cursor’s internal Cursor-Bench for intelligence and tokens per second for speed, Composer underperforms compared to the “best frontier” and outperforms top-tier open models and speed-oriented frontier models in intelligence. However, it vastly outpaces its competitors in speed.