Google DeepMind· @GoogleDeepMind · X·· 6 小时前AI 评分38
AI 导读
我们与 @ArtificialAnlys 共同构建了 MKA(多模态知识智能体):一个衡量智能体处理视觉复杂任务能力的基准。 日常专业工作往往不只用到文本——从交叉比对蓝图到阅读科学图表。现有评测并未覆盖这些内容。 Gemini 4 Carbon 排名第 2,平均每任务成本比排名第一的模型低 6 倍。→ https://goo.gle/4AikIja
正文 · 原文
With @ArtificialAnlys, we built MKA (Multimodal Knowledge Agent): a benchmark for how well agents handle visually complex tasks.
Everyday professional work often uses more than just text – from cross-referencing blueprints to reading scientific charts. This is not covered by existing evaluations.
Gemini 4 Carbon ranks #2, at 6x lower average cost per task than the top model. → https://goo.gle/4AikIja
来源:Google DeepMind · x.com