Artificial Analysis 与 Google DeepMind 合作引入 MKA 基准
Artificial Analysis 与 Google DeepMind 合作，将面向视觉复杂任务的 MKA（Multimodal Knowledge Agent）基准引入 Artificial Analysis。该基准考察智能体处理蓝图交叉比对、科学图表阅读等超出文本范围的专业工作，现有评测未覆盖此类能力。Gemini 4 Carbon 在该基准排名第 2，单任务平均成本比榜首模型低 6 倍。
Artificial Analysis· @ArtificialAnlys · X·2026-11-11 02:28· 36 分钟前AI 评分40
AI 导读
很高兴与 @GoogleDeepMind 合作，将 MKA Benchmark 引入 Artificial Analysis
正文 · 原文
Great to partner with @GoogleDeepMind in bringing MKA Benchmark to Artificial Analysis
在 X 查看被引用的帖子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. → goo.gle/4AikIja
来源：Artificial Analysis · x.com
来源：RadarAI · aihot.news