Expired50% confidenceFactExact time
Cursor's Composer 2 is trained based on Kimi 2.5, which is a Mixture-of-Experts model with 1 trillion parameters and 30 billion active parameters.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Cursor Composer2 Training Revealed: A Complete Guide to Distributed Reinforcement Learning Engineering
bilibili豚工智能6/6/2026
Related Claims
VerifiedThe Cursor team officially released its self-developed programming model Composer 2.5, trained on the Kimi K2.5 open-source checkpoint.77% similarUnverifiedCursor used RLHF (Reinforcement Learning from Human Feedback) training on the open-source Kimi K2 model using data from real user programming interactions to produce Composer 2.5.72% similarUnverifiedCursor performed reinforcement learning fine-tuning on top of Kimi KR, specializing the model through training on large amounts of high-quality programming task data.71% similarVerifiedCursor released Composer 2, an agent model designed for long-duration coding tasks.70% similarVerifiedCursor 2.0's proprietary Composer model is claimed to be 4 times faster than comparable models.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/51429API
curl https://kongchang.com/api/v1/knowledge/claims/51429MCP
get_claim(id=51429)