{"benchmark_id":"mmvetgpt4turbo","benchmark_name":"MMVetGPT4Turbo","benchmark_description":"MM-Vet evaluation using GPT-4 Turbo for scoring. This variant of MM-Vet examines large multimodal models on complicated multimodal tasks requiring integrated capabilities across six core vision-language abilities: recognition, knowledge, spatial awareness, language generation, OCR, and math.","max_score":1.0,"categories":["math","multimodal","reasoning","spatial_reasoning","general","vision"],"modality":"multimodal","total_models":1,"entries":[{"rank":1,"model_id":"qwen2-vl-72b","model_name":"Qwen2-VL-72B-Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.74,"normalized_score":0.74,"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}]}