{"benchmark_id":"olympiadbench","benchmark_name":"OlympiadBench","benchmark_description":"A challenging benchmark for promoting AGI with Olympiad-level bilingual multimodal scientific problems. Comprises 8,476 math and physics problems from international and Chinese Olympiads and the Chinese college entrance exam, featuring expert-level annotations for step-by-step reasoning. Includes both text-only and multimodal problems in English and Chinese.","max_score":1.0,"categories":["math","multimodal","physics","reasoning","vision"],"modality":"multimodal","total_models":1,"entries":[{"rank":1,"model_id":"qvq-72b-preview","model_name":"QvQ-72B-Preview","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.204,"normalized_score":0.204,"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":"2024-12-25","announcement_date":"2024-12-25","multimodal":true,"param_count":73400000000,"is_new":false}]}