HallusionBench, MME, AI2D, RealWorldQA, ScienceQA, POPE, MMBench, CCBench, Visual Spatial Reasoning, Visual7W
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
HallusionBench, MME, AI2D, RealWorldQA, ScienceQA, POPE, MMBench (EN/CN), CCBench, Visual Spatial Reasoning, Visual7W (test)
58.09HallusionBench Score
16