We present a challenging benchmark for the Open WorLd VISual question answering (OWLViz) task. OWLViz presents concise, unambiguous queries that require integrating multiple capabilities, including visual understanding, web exploration, and specialized tool usage. While humans achieve 69.2% accuracy on these intuitive tasks, even state-of-the-art VLMs struggle, with the best model, Gemini 2.0, achieving only 26.6% accuracy. Current agentic VLMs, which rely on limited vision and vision-language models as tools, perform even worse. This performance gap reveals significant limitations in multimodal systems' ability to select appropriate tools and execute complex reasoning sequences, establishing new directions for advancing practical AI research.
View on arXiv@article{nguyen2025_2503.07631,
title={ OWLViz: An Open-World Benchmark for Visual Question Answering },
author={ Thuy Nguyen and Dang Nguyen and Hoang Nguyen and Thuan Luong and Long Hoang Dang and Viet Dac Lai },
journal={arXiv preprint arXiv:2503.07631},
year={ 2025 }
}