Meta Previews WildArtifactBench for Evaluating Multimodal Agents on Real-World Tasks

Meta previewed WildArtifactBench, an internal evaluation framework for assessing agents on complex real-world tasks across diverse deliverable formats. It uses win rates and Elo scores from human and agentic preference judges rather than strict ground-truth rubrics, expanding task coverage across practical multimodal workflows. Ten tasks from WildArtifactBench are being released to advance measurement of real practical utility delivered by multimodal agents.