Runway 发布 Praxis-1，速度比 GPT-6 Astra 快 15.6 倍、成本低 51 倍
Runway 把自家机器人模型 Praxis-1 和 GPT-6 Astra 放在同一个工作站上比，结果快了 15.6 倍，每个任务还便宜 51 倍。做机器人或自动化的开发者可以关注这种专用模型和通用 LLM 的选型对比。
Runway 发布机器人操作模型 Praxis-1，在相同工作站与任务测试中，完成速度达到 GPT-6 Astra 驱动机械臂的 15.6 倍，每完成一个任务的成本仅为后者的 1/51。
Praxis-1 的核心能力是直接驱动机械臂执行任务，Runway 通过统一的站点和任务集对比两类模型，衡量标准为完成速度与单位任务成本，而非单纯的感知或推理分数。
这一结果把机器人领域的专用操作模型与通用大语言模型放到了同一坐标系里比较。如果 51 倍的单位成本差距在实际部署中可复现，做具身智能和自动化产线的团队在选型时会倾向专用模型，通用 LLM 阵营需要重新评估其在物理任务上的定位。
Praxis-1 dramatically outperforms frontier LLMs on speed and cost. On the same station and tasks, Praxis-1 finished 15.6x faster than GPT-6 Astra driving the arm, at 51x lower cost per completed task.
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 US-China foundation model benchmarks and commercialization comparison and AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Praxis-1, Runway, GPT-6 Astra, 具身智能.
Source attribution: curated from Runway ML (@runwayml). Cross-source corroboration: 11 independent sources have covered this development (including Epoch AI, Artificial Analysis, AI Will), confirming industry-wide signal strength.
