Controlling a lunar lander using a 1980s home computer is not for the faint of heart, and this project shows how one intrepid developer linked the world of BASIC to the simulated world of Kerbal Space ...
On SWE-Bench Verified, the model achieved a score of 70.6%. This performance is notably competitive when placed alongside significantly larger models; it outpaces DeepSeek-V3.2, which scores 70.2%, ...