MMBench

MMBench is a comprehensive benchmark suite for evaluating multimodal AI models, developed by OpenBMB. It differentiates itself through structured assessment across perception, reasoning, and knowledge tasks, providing fine-grained performance insight

Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.