{"benchmark_id":"mmvet","name":"MMVet","parent_benchmark":null,"categories":["math","multimodal","reasoning","spatial_reasoning","general","vision"],"modality":"multimodal","multilingual":false,"max_score":1.0,"language":"en","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.","paper_link":"https://arxiv.org/abs/2308.02490","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:25.021855+00:00","updated_at":"2026-07-05T18:27:55.480683+00:00","statistics":{"total_models":2,"average_score":0.71645,"min_score":0.671,"max_score":0.7619,"score_stddev":0.06427600640985716,"verified_count":0,"self_reported_count":2},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"qwen2.5-vl-72b","model_name":"Qwen2.5 VL 72B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.7619,"normalized_score":0.7619,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/Qwen/Qwen2.5-VL-72B-Instruct","analysis_method":"Score","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-01-26","param_count":72000000000,"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":"qwen2.5-vl-7b","model_name":"Qwen2.5 VL 7B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.671,"normalized_score":0.671,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct","analysis_method":"Score","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-01-26","param_count":8290000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}