{"benchmark_id":"medxpertqa","name":"MedXpertQA","parent_benchmark":null,"categories":["multimodal","reasoning","healthcare","vision"],"modality":"multimodal","multilingual":false,"max_score":1.0,"language":"en","description":"A comprehensive benchmark to evaluate expert-level medical knowledge and advanced reasoning, featuring 4,460 questions spanning 17 specialties and 11 body systems. Includes both text-only and multimodal subsets with expert-level exam questions incorporating diverse medical images and rich clinical information.","paper_link":"https://arxiv.org/abs/2501.18362","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:24.415506+00:00","updated_at":"2026-07-05T18:27:52.780746+00:00","statistics":{"total_models":12,"average_score":0.5005,"min_score":0.188,"max_score":0.784,"score_stddev":0.184979360027987,"verified_count":0,"self_reported_count":12},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"muse-spark","model_name":"Muse Spark","organization_id":"meta","organization_name":"Meta","organization_country":"US","score":0.784,"normalized_score":0.784,"verified":false,"self_reported":true,"self_reported_source":"https://ai.meta.com/static-resource/muse-spark-eval-methodology","analysis_method":"MM","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-04-08","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":2,"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":0.673,"normalized_score":0.673,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":"MM","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":3,"model_id":"qwen3.5-27b","model_name":"Qwen3.5-27B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.624,"normalized_score":0.624,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":"MM","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":4,"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":0.614,"normalized_score":0.614,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":"MM","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":5,"model_id":"gemma-4-31b-it","model_name":"Gemma 4 31B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.613,"normalized_score":0.613,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/blog/gemma4","analysis_method":"MM","verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.13,"output_cost_per_million":0.38,"context_window":262144,"announcement_date":"2026-04-02","param_count":30700000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"Together"},{"rank":6,"model_id":"gemma-4-26b-a4b-it","model_name":"Gemma 4 26B-A4B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.581,"normalized_score":0.581,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/blog/gemma4","analysis_method":"MM","verification_date":null,"provider_id":"novita","input_cost_per_million":0.13,"output_cost_per_million":0.4,"context_window":262144,"announcement_date":"2026-04-02","param_count":25200000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"Novita"},{"rank":7,"model_id":"diffusiongemma-26b-a4b-it","model_name":"DiffusionGemma 26B-A4B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.49,"normalized_score":0.49,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/diffusiongemma-26B-A4B-it","analysis_method":"MM","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-06-10","param_count":25200000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":8,"model_id":"gemma-4-12b-it","model_name":"Gemma 4 12B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.487,"normalized_score":0.487,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/gemma-4-12B-it","analysis_method":"MM","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-05-23","param_count":11959730224,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":9,"model_id":"mai-thinking-1","model_name":"MAI-Thinking-1","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.43,"normalized_score":0.43,"verified":false,"self_reported":true,"self_reported_source":"https://microsoft.ai/wp-content/uploads/2026/06/main_20260602_2.pdf","analysis_method":"Text","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-06-02","param_count":1000000000000,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":10,"model_id":"gemma-4-e4b-it","model_name":"Gemma 4 E4B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.287,"normalized_score":0.287,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/blog/gemma4","analysis_method":"MM","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-04-02","param_count":8000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":11,"model_id":"gemma-4-e2b-it","model_name":"Gemma 4 E2B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.235,"normalized_score":0.235,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/blog/gemma4","analysis_method":"MM","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-04-02","param_count":5100000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":12,"model_id":"medgemma-4b-it","model_name":"MedGemma 4B IT","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.188,"normalized_score":0.188,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/medgemma-4b-it","analysis_method":"Accuracy","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}]}