热点
"CORE-Bench" 相关文章
Can AI automate computational reproducibility?
AI Snake Oil 2024-12-13T05:08:42.000000Z
AI科学家太多，谁靠谱一试便知！普林斯顿新基准CORE-Bench：最强模型仅有21%准确率
智源社区 2024-09-26T09:53:20.000000Z
AI科学家太多，谁靠谱一试便知，普林斯顿新基准CORE-Bench：最强模型仅有21%准确率
36kr 2024-09-25T10:45:56.000000Z
CORE-Bench: A Benchmark Consisting of 270 Tasks based on 90 Scientific Papers Across Computer Science, Social Science, and Medicine with Python or R Codebases
MarkTechPost@AI 2024-09-22T10:20:34.000000Z