{"benchmark_id":"pathmcqa","benchmark_name":"PathMCQA","benchmark_description":"PathMMU is a massive multimodal expert-level benchmark for understanding and reasoning in pathology, containing 33,428 multimodal multi-choice questions and 24,067 images validated by seven pathologists. It evaluates Large Multimodal Models (LMMs) performance on pathology tasks, with the top-performing model GPT-4V achieving only 49.8% zero-shot performance compared to 71.8% for human pathologists.","max_score":1.0,"categories":["multimodal","reasoning","healthcare","vision"],"modality":"multimodal","total_models":1,"entries":[{"rank":1,"model_id":"medgemma-4b-it","model_name":"MedGemma 4B IT","organization_name":"Google","organization_id":"google","benchmark_score":0.698,"normalized_score":0.698,"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":"2025-05-20","announcement_date":"2025-05-20","multimodal":true,"param_count":4300000000,"is_new":false}]}