Tag
Parsimony 是一个开源基准，用于衡量 AI 编程模型在解决任务时净增加了多少代码，通过统计语法单元（而非行数）并对删除的代码进行扣减，以奖励更精简的代码修改。
CursorBench 3.1 introduces new benchmark tasks focused on codebase understanding, bugfinding, planning, and code review, and presents updated scores and cost comparisons for various AI models.
CodeAlchemy is a synthetic data generation framework that transforms publicly available code into semantically rich training data using five strategies, producing over 500 billion tokens and enabling small models to outperform much larger ones on code benchmarks.