ModelsSelected

World Labs Atlas 登顶 Rapidata 相机运动基准第一

Why we picked it

World Labs 的 Atlas 在 Rapidata 榜单上拿了第一,19 个模型、600 条提示、51 万多条人类投票评出来的。做视频生成或创意工具的朋友可以看看这份评测,挑模型跟相机指令走得好不好有实际参考价值。

李飞飞在 X 上宣布,World Labs 的 Atlas 在 RapidataAI 的相机运动基准中排名第一。该基准评估模型对相机指令的遵循能力,共对比 19 个世界模型与视频模型,使用 600 条提示词,累计收集超过 51.3 万条人类判断。

Body

相机控制能力对创意与设计类工作尤为关键——能否准确执行推拉摇移等镜头指令,直接决定生成内容是否可用于实际制作流程。此次评测以人类判断为核心依据,而非自动化指标,排名结果更贴近真实使用体验。

对视频生成和世界模型赛道的开发者而言,这份榜单提供了一个横向对比 19 个模型遵循能力的参考,Atlas 的高排名也强化了 World Labs 在空间智能方向的定位。

Original · Fei-Fei Li

Great job @theworldlabs teams! 🚀 Camera control is so critical for many creative and design work. I’m very excited by Atlas’ strong results! World Labs @theworldlabs Atlas ranks #1 in @RapidataAI 's camera-movement benchmark, which evaluates how well models follow camera instructions. The evaluation compares 19 world and video models across 600 prompts, with 513K+ human judgments. More on the results and methodology below. 🔗 View Quoted Tweet

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 World Labs, Atlas, Rapidata, 视频生成.

Source attribution: curated from Fei-Fei Li (@drfeifei).