Browser Use：Muse Ember 以 3 美分成本跑完数百步浏览器任务
Browser Use 拿 Muse Ember 跑最难的长时程浏览器基准，63.9 分追平 GPT-6 Luna medium，单任务 3 美分还便宜 2.4 倍。做浏览器智能体的人可以算算换成 Ember 能省多少预算，跑几百步的长任务终于不用心疼钱了。
Browser Use 团队用 Muse Ember 模型跑了最难的长时程浏览器基准，得分 63.9/100，与 GPT-6 Luna medium 持平。
成本是最大亮点：数百步浏览器操作的单任务价格只要 3 美分，比 GPT-6 Luna medium 便宜 2.4 倍；5 美分以内的任务拿下最高分，整条 Pareto 前沿（性价比曲线）由 Ember 占据。
Browser Use 创始人在推文中向 Scale AI 的 Alexandr Wang 表示祝贺，认为能真正驱动浏览器的廉价模型对智能体行业意义重大。对做浏览器自动化和长任务智能体的开发者来说，单价从美元级降到美分级会直接改变任务编排的预算逻辑。
The entire Pareto Frontier is now dominated by Ember Browser Use @browser_use Ran Muse Ember on hardest long horizon browser benchmark 👀 It's EXTREMELY cheap, pareto frontier. Tasks with 100s of browser steps cost CENTS, not USD > 63.9/100, same as GPT-6 Luna medium > 3 cents a task, 2.4x cheaper > best score under 5 cents congrats @alexandr_wang , cheap models that can actually drive a browser are huge 🔗 View Quoted Tweet📊 2 ⚡
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 Muse Ember, Browser Use, GPT-6, 智能体.
Source attribution: curated from Browser Use (@browser_use). Cross-source corroboration: 11 independent sources have covered this development (including Alexandr Wang (Meta MSL), 宝玉, AI SDK), confirming industry-wide signal strength.
