Primary sourceelvis
View sourceEvent ·Multi-source
新基准DataSpace:数据智能体异构任务最佳准确率66.34%
新研究发布DataSpace基准,用于评估数据智能体在异构数据工作区生成可验证表格结果的能力。该基准包含410个跨语言任务,覆盖7439个工件,总数据量15.01GB,涉及CSV、JSON、SQLite、Markdown、PDF和视频等格式。在六个前沿多模态模型和五个常用智能体框架的测试中,最佳准确率为66.34%。固定模型主干时,更换框架可使准确率变动15.36个百分点。多模态证据整合和连接操作在六个骨干模型上均降低了准确率。
Current read
想知道数据智能体怎么选?DataSpace测了6个模型和5个框架,换框架能让准确率差15个点,值得看。
3 sources53° AI heatLast updated 2026/8/5 19:15:02
Evidence
3 sourcesConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.