{"benchmark_id":"stem","benchmark_name":"STEM","benchmark_description":"A comprehensive multimodal benchmark dataset with 448 skills and 1,073,146 questions spanning all STEM subjects (Science, Technology, Engineering, Mathematics), designed to test neural models' vision-language STEM skills based on K-12 curriculum. Unlike existing datasets that focus on expert-level ability, this dataset includes fundamental skills designed around educational standards.","max_score":1.0,"categories":["math","multimodal","reasoning","vision"],"modality":"multimodal","total_models":1,"entries":[{"rank":1,"model_id":"qwen-2.5-coder-7b-instruct","model_name":"Qwen2.5-Coder 7B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.34,"normalized_score":0.34,"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":"2024-09-19","announcement_date":"2024-09-19","multimodal":false,"param_count":7000000000,"is_new":false}]}