ViGoR-Bench

ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners? 🔍 Overview ViGoR-Bench (Vision-Generative Reasoning-centric Benchmark) is a unified evaluation framework designed to stress-test the reasoning capabilities of visual generative models. Beneath the stunning visual fidelity of modern AIGC models lies a logical desert — systems frequently fail tasks requiring physical, causal, or complex spatial reasoning. Existing evaluations, relying on… See the full description on the dataset page:

Source: Hugging Face Hub (VincentHancoder/ViGoR-Bench). Metadata imported from the dataset’s Hub tags.