🔶 Gemini 4 Argon
英文标题:🔶 Gemini 4 Argon
Gemini 4 Argon 凭借编程、推理、多模态能力以及持续执行长链路、多步骤任务的能力,可覆盖多种企业工作流。该模型在衡量真实世界长周期软件工程任务的 DeepSWE v1.1 上取得 77.9%,并被用于调试、大规模代码库迁移和算法设计等日常工程任务。在金融、法律、税务和企业自动化等领域,Argon 在 Vals Index、Vals Finance Agent v2、Harvey Legal Agent Benchmark 和 AutomationBench 等评测中表现领先,其中 AutomationBench 得分为 51.3%。其视觉理解能力也较为突出,在长视频理解评测 LVBench 上以 91.7% 的成绩达到当前最佳水平。
333.4 KB
40.1 KB
37.3 KB
38.9 KB
30.8 KB
35.8 KB
中文
支持跨领域的编程与企业工作流
Gemini 4 Argon 在编程、推理和多模态方面的能力,以及持续完成长链路、多步骤任务的能力,使其能够在多种企业工作流中表现出色。
Google 工程师已将 Argon 用于日常工作,涵盖日常调试、大规模代码库迁移以及算法设计等任务。它在 DeepSWE v1.1 上创下新的当前最佳成绩(77.9%);该评测用于衡量模型在真实世界、长周期软件工程任务中的表现。
除编程外,Argon 也是 Vals Index 上的领先模型。该指数衡量模型在金融、编程、法律和税务工作中的经济影响,并按照各行业对美国 GDP 的贡献进行加权。我们还观察到它在其他特定领域评测中同样表现领先,例如 Vals Finance Agent v2(多步骤金融研究)和 Harvey 的 Legal Agent Benchmark(法律研究与文书起草)。在 Zapier 用于衡量核心业务职能端到端执行能力的基准测试 AutomationBench 上,Argon 以 51.3% 的得分位居第一。
当知识型工作需要视觉理解能力时,Argon 同样展现出独特优势。它能够进行专业图表分析、从长视频中识别细节,并基于一系列文档采取行动。例如,在衡量长视频理解能力的 LVBench 上,Argon 以 91.7% 的得分达到当前最佳水平。
English / 原文
Enabling coding and enterprise workflows across domains
Gemini 4 Argon’s capabilities across coding, reasoning, and multimodality and its ability to sustain long, multi-step tasks enable it to excel across a range of enterprise workflows.
Google engineers have been using Argon for their daily tasks, from everyday debugging to large-scale codebase migrations and algorithm designs. It sets a new state of the art on DeepSWE v1.1 (77.9%), which measures a model’s performance in real-world long-horizon software engineering tasks.
Beyond coding, Argon is the leading model on the Vals Index, which measures economic impact across finance, coding, legal, and tax work, with every sector weighted by its contribution to U.S. GDP. We see similarly leading performance across other domain specific evaluations, like Vals Finance Agent v2 (multi-step financial research) and Harvey’s Legal Agent Benchmark (legal research and drafting). On AutomationBench, Zapier’s benchmark measuring end-to-end execution across core business functions, Argon ranks #1 with a score of 51.3%.
Argon is also uniquely strong when knowledge work requires visual understanding. It’s able to drive professional chart analysis, identify details from long videos, and take action based on a series of documents. For example, on LVBench, which measures long video understanding, Argon is state of the art with a score of 91.7%.