{"benchmark_id":"mmlu-stem","benchmark_name":"MMLU-STEM","benchmark_description":"STEM-focused subset of the Massive Multitask Language Understanding benchmark, evaluating language models on science, technology, engineering, and mathematics topics including physics, chemistry, mathematics, and other technical subjects.","max_score":1.0,"categories":["math","physics","reasoning","chemistry"],"modality":"text","total_models":2,"entries":[{"rank":1,"model_id":"qwen-2.5-32b-instruct","model_name":"Qwen2.5 32B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.809,"normalized_score":0.809,"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":32500000000,"is_new":false},{"rank":2,"model_id":"qwen-2.5-14b-instruct","model_name":"Qwen2.5 14B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.764,"normalized_score":0.764,"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":14700000000,"is_new":false}]}