WorldBench

WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark

arXiv:2606.06538v1 Announce Type: new Abstract: In real-world applications, models are expected to perform reliably across diverse settings. Yet, many existing multimodal benchmarks expand task types without capturing the visual diversity needed to handle open-ended visual inputs. We present WorldBench, a challenging and visually diverse reasoning benchmark to evaluate Multimodal Large Language Models (MLLMs).