{"benchmark_id":"mmvet","benchmark_name":"MMVet","benchmark_description":"MM-Vet is an evaluation benchmark that examines large multimodal models on complicated multimodal tasks requiring integrated capabilities. It assesses six core vision-language capabilities: recognition, knowledge, spatial awareness, language generation, OCR, and math through questions that require one or more of these capabilities.","max_score":1.0,"categories":["math","multimodal","reasoning","spatial_reasoning","general","vision"],"modality":"multimodal","total_models":2,"entries":[{"rank":1,"model_id":"qwen2.5-vl-72b","model_name":"Qwen2.5 VL 72B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.7619,"normalized_score":0.7619,"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":"2025-01-26","announcement_date":"2025-01-26","multimodal":true,"param_count":72000000000,"is_new":false},{"rank":2,"model_id":"qwen2.5-vl-7b","model_name":"Qwen2.5 VL 7B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.671,"normalized_score":0.671,"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":"2025-01-26","announcement_date":"2025-01-26","multimodal":true,"param_count":8290000000,"is_new":false}]}