MoonshotAI: Kimi Dev 72B

Kimi Dev 72B is an open-source large language model fine-tuned for software engineering and issue resolution. Built on Qwen2.5-72B, it is trained with large-scale reinforcement learning that applies code patches to real repositories and validates them against full test suites—rewarding only correct and reliable solutions. The model achieves 60.4% on SWE-bench Verified, setting a new state-of-the-art benchmark among open-source models for code reasoning and automated bug fixing.