This is a personal open-source project for learning and exchange, licensed under MIT and free to redistribute. The original name “Yunshu (云枢)” conflicted with other enterprise projects; it has been ...
A compact software-engineering evaluation benchmark. It contains five realistic Python engineering tasks, each with a verified reference solution, and a small CLI that applies a candidate patch (human ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results