{"benchmark_id":"cvtg-2k","benchmark_name":"CVTG-2K","benchmark_description":"CVTG-2K (Chinese Visual Text Generation 2K) is a benchmark for evaluating text-to-image models on their ability to accurately render text within generated images. It measures Word Accuracy, Normalized Edit Distance (NED), and CLIPScore across 2,000 prompts.","max_score":1.0,"categories":["image-generation","language","vision"],"modality":"image","total_models":0,"entries":[]}