{"benchmark_id":"mmau-speech","benchmark_name":"MMAU Speech","benchmark_description":"A subset of the MMAU benchmark focused specifically on speech understanding and reasoning tasks. Part of a comprehensive multimodal audio understanding benchmark that evaluates models on expert-level knowledge and complex reasoning across speech audio clips.","max_score":1.0,"categories":["multimodal","reasoning","speech_to_text","audio"],"modality":"multimodal","total_models":1,"entries":[{"rank":1,"model_id":"qwen2.5-omni-7b","model_name":"Qwen2.5-Omni-7B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.5976,"normalized_score":0.5976,"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":"2025-03-27","announcement_date":"2025-03-27","multimodal":true,"param_count":7000000000,"is_new":false}]}