{"benchmark_id":"mtvqa","benchmark_name":"MTVQA","benchmark_description":"MTVQA (Multilingual Text-Centric Visual Question Answering) is the first benchmark featuring high-quality human expert annotations across 9 diverse languages, consisting of 6,778 question-answer pairs across 2,116 images. It addresses visual-textual misalignment problems in multilingual text-centric VQA.","max_score":1.0,"categories":["multimodal","text-to-image","vision"],"modality":"multimodal","total_models":1,"entries":[{"rank":1,"model_id":"qwen2-vl-72b","model_name":"Qwen2-VL-72B-Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.309,"normalized_score":0.309,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2024-08-29","announcement_date":"2024-08-29","multimodal":true,"param_count":73400000000,"is_new":false}]}