{"benchmark_id":"slakevqa","name":"SlakeVQA","parent_benchmark":null,"categories":["multimodal","reasoning","image_to_text","healthcare","vision"],"modality":"multimodal","multilingual":true,"max_score":1.0,"language":"en","description":"A semantically-labeled knowledge-enhanced dataset for medical visual question answering. Contains 642 radiology images (CT scans, MRI scans, X-rays) covering five body parts and 14,028 bilingual English-Chinese question-answer pairs annotated by experienced physicians. Features comprehensive semantic labels and a structural medical knowledge base with both vision-only and knowledge-based questions requiring external medical knowledge reasoning.","paper_link":"https://arxiv.org/abs/2102.09542","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:26.173917+00:00","updated_at":"2026-07-05T18:28:00.582688+00:00","statistics":{"total_models":4,"average_score":0.7565,"min_score":0.623,"max_score":0.816,"score_stddev":0.08978678447670717,"verified_count":0,"self_reported_count":4},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"qwen3.5-122b-a10b","model_name":"Qwen3.5-122B-A10B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.816,"normalized_score":0.816,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-02-24","param_count":122000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":2,"model_id":"qwen3.5-27b","model_name":"Qwen3.5-27B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.8,"normalized_score":0.8,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":null,"verification_date":null,"provider_id":"novita","input_cost_per_million":0.3,"output_cost_per_million":2.4,"context_window":262144,"announcement_date":"2026-02-24","param_count":27000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"Novita"},{"rank":3,"model_id":"qwen3.5-35b-a3b","model_name":"Qwen3.5-35B-A3B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.787,"normalized_score":0.787,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-02-24","param_count":35000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":4,"model_id":"medgemma-4b-it","model_name":"MedGemma 4B IT","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.623,"normalized_score":0.623,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/medgemma-4b-it","analysis_method":"Tokenized F1","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-05-20","param_count":4300000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}