Meta 预览 WildArtifactBench 智能体评测框架
Today we’re also previewing WildArtifactBench, an internal evaluation framework designed to assess agents on complex, real-world tasks across diverse deliverabl
Meta 预览内部评测框架 WildArtifactBench，用于评估智能体在多种交付格式下的复杂真实任务，并开放其中 10 个任务。该框架采用人类与智能体偏好评判给出的胜率和 Elo 分数，而非严格的标准答案评分标准，从而扩大对实际多模态工作流的任务覆盖。帖子还展示了 Muse Spark 1.1 和 1.2 在 Cat Mesh、Plywood Whale 任务上生成的产物。
正文
当前显示原文，中文全文译文尚未就绪。
Today we’re also previewing WildArtifactBench, an internal evaluation framework designed to assess agents on complex, real-world tasks across diverse deliverable formats.
By using win rates and Elo scores from human and agentic preference judges rather than strict ground-truth rubrics, it expands task coverage across practical multimodal workflows.
We’re releasing 10 tasks from WildArtifactBench as a step forward in our ability to measure the real practical utility delivered by multimodal agents: https://t.co/UIpdcw8JF2