Kimi-K2.7-Code
Moonshot
Open-source coding model from Moonshot AI. Improves on K2.6 with +21.8% on Kimi Code Bench v2, +11.0% on Program Bench, and +31.5% on MLS Bench Lite. Uses 30% fewer reasoning tokens, with stronger long-horizon instruction following and end-to-end task success.
Modality
text->text
License
open_weights
Open source
Yes
Open Kimi-K2.7-Code in AIniverse
Compare versions, read real ratings, save to your stack.
Open in App