DeepMind 与 Artificial Analysis 联合发布 MKA 多模态智能体基准
原标题：Great to partner with @GoogleDeepMind in bringing MKA Benchmark to Artificial Analysis
58AI 研判分
Google DeepMind 与 Artificial Analysis 合作推出 MKA（Multimodal Knowledge Agent）基准，专门评估智能体在视觉复杂任务上的表现，填补现有评测对蓝图交叉比对、科学图表阅读等专业场景的空白。Gemini 4 Carbon 在该基准上排名第二，单任务平均成本比榜首模型低 6 倍。
报道正文
Artificial Analysis (@ArtificialAnlys) · 2026-11-10 18
Great to partner with @GoogleDeepMind in bringing MKA Benchmark to Artificial Analysis
↳ 引用 @GoogleDeepMind (Google DeepMind): 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. →