Google DeepMind 与 Artificial Analysis 推出 MKA 多模态知识智能体基准，Gemini 4 Carbon 排名第 2
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://t.co/E6tc98a705
Google DeepMind 与 Artificial Analysis 联合构建 MKA（Multimodal Knowledge Agent）基准，用于评估智能体处理视觉复杂任务的能力，覆盖交叉比对蓝图、阅读科学图表等现有评测未涉及的场景。Gemini 4 Carbon 在该基准中排名第 2，平均每任务成本比排名第 1 的模型低 6 倍。
粉丝 161万
认证：X 认证的官方组织
The engine room of @Google. Building AI safely and responsibly to solve the world’s most complex problems. Join us: https://t.co/jUHQA27iBL
- 浏览
- 2.7万
- 点赞
- 113
- 评论
- 14
- 分享
- 14
- 收藏
- 15
数字来自平台，为最近一次抓取时的数据。
来源：X · Google DeepMind · x.com