Cursor releases Composer 2.5 coding model
Cursor released Composer 2.5, claiming up to 10x higher efficiency on long coding tasks; the model is further trained on Moonshot’s Kimi K2.5 and uses text feedback for 100k-token-scale trajectories.
Why it matters: Cursor shipped Composer 2.5, using text-feedback training to handle 100k-token long trajectories, with the company claiming up to 10x efficiency on complex coding over hundreds of steps.