{"benchmark_id":"mmmuval","benchmark_name":"MMMUval","benchmark_description":"Validation set for MMMU (Massive Multi-discipline Multimodal Understanding and Reasoning) benchmark, designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning across Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering.","max_score":1.0,"categories":["multimodal","reasoning","general","healthcare","vision"],"modality":"multimodal","total_models":4,"entries":[{"rank":1,"model_id":"qwen3-vl-235b-a22b-thinking","model_name":"Qwen3 VL 235B A22B Thinking","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.806,"normalized_score":0.806,"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":"2025-09-22","announcement_date":"2025-09-22","multimodal":true,"param_count":236000000000,"is_new":false},{"rank":2,"model_id":"qwen3-vl-235b-a22b-instruct","model_name":"Qwen3 VL 235B A22B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.787,"normalized_score":0.787,"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":"2025-09-22","announcement_date":"2025-09-22","multimodal":true,"param_count":236000000000,"is_new":false},{"rank":3,"model_id":"claude-sonnet-4-5-20250929","model_name":"Claude Sonnet 4.5","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.778,"normalized_score":0.778,"verified":false,"self_reported":true,"provider_id":"anthropic","input_cost_per_million":3.0,"output_cost_per_million":15.0,"speed_rps":42.0,"context_window":200000,"release_date":"2025-09-29","announcement_date":"2025-09-29","multimodal":true,"param_count":null,"is_new":false},{"rank":4,"model_id":"qwen2-vl-72b","model_name":"Qwen2-VL-72B-Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.645,"normalized_score":0.645,"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}]}