Changes from previous version
Adds reasoning tokens, self-summarization when context fills, and stronger scores on hard coding benchmarks versus Composer 1 while staying interactive for day-to-day use.
Release Summary
Thinking agentic coding model from Cursor with 20x scaled RL on the Composer 1 base, self-summarization for long tasks, and adaptive depth (minimal thinking on easy prompts, extended reasoning on hard ones).
Timeline
February 8, 2026
Composer 1.5 released
Cursor releases Composer 1.5 as its default interactive coding model with thinking and RL scaling beyond Composer 1.