The @cursor_ai team shipped Composer 2 and now Composer 2.5 on the same Kimi K2.5 base model. Performance benchmarks are📈. Frontier quality…

The @cursor_ai team shipped Composer 2 and now Composer 2.5 on the same Kimi K2.5 base model. Performance benchmarks are📈. Frontier quality and open-source economics. 85% of the compute powering these gains came from RL. Fireworks powers the RL rollouts. Learn more about rollouts here: http://fireworks.ai/training-rl-rollouts Introducing Composer 2.5, our most powerful model yet. It's more intelligent, better at sustained work on long-running tasks, and more reliable at following complex instructions. For the next week, we’re doubling the included usage of the model.

Source: Fireworks AI (X) | 2026-05-18