{"benchmark_id":"scienceqa","benchmark_name":"ScienceQA","benchmark_description":"ScienceQA is the first large-scale multimodal science question answering benchmark with 21,208 multiple-choice questions covering 3 subjects (natural science, language science, social science), 26 topics, 127 categories, and 379 skills. The benchmark includes both text and image modalities, featuring detailed explanations and Chain-of-Thought reasoning to diagnose multi-hop reasoning ability.","max_score":1.0,"categories":["math","multimodal","reasoning","vision"],"modality":"multimodal","total_models":1,"entries":[{"rank":1,"model_id":"phi-3.5-vision-instruct","model_name":"Phi-3.5-vision-instruct","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.913,"normalized_score":0.913,"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":"2024-08-23","announcement_date":"2024-08-23","multimodal":true,"param_count":4200000000,"is_new":false}]}