Models

Google 联合 Artificial Analysis 发布 Multimodal Knowledge Agent 基准

Why we picked it

Google 和 Artificial Analysis 一起搞了个新基准,200 个任务专测模型看 CAD 图、电路图、GIS 地图这类专业图片再做多步推理。想给企业场景选多模态模型的人可以直接拿结果对比各家模型,比单纯跑通用基准更有参考价值。

Google 与 Artificial Analysis 合作发布 Multimodal Knowledge Agent 基准,包含 200 个多步骤任务,覆盖 10 个行业垂直领域。任务素材围绕 CAD 蓝图、RF 电路原理图、GIS 地图、凝胶电泳图和图表等专业文档构建,要求智能体在多轮推理中读取并整合这些非文本信息。

Body

与常见仅依赖文本推理的智能体评测不同,该基准专门考察模型对工程、生物实验和地理空间等专业图像的理解能力,更贴近企业实际工作场景中处理技术文档的需求。发布方为 Google,合作方 Artificial Analysis 是一家第三方模型评测机构,双方通过博客公布了基准详情。

对开发者而言,这一基准提供了一个衡量多模态智能体在垂直行业任务上表现的参考,有助于企业在选型时比较不同模型处理专业文档与多步任务的能力。

Original · Philipp Schmid

We partnered with Artificial Analysis to release the Multimodal Knowledge Agent benchmark: 200 multi-step tasks across 10 verticals built around CAD blueprints, RF schematics, GIS maps, gel plates, and charts. blog.google/innovation-and…📊 1 ⚡

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Multimodal Knowledge Agent, Google, Artificial Analysis, multimodal.

Source attribution: curated from Philipp Schmid (@_philschmid).