{"benchmark_id":"musiccaps","benchmark_name":"MusicCaps","benchmark_description":"MusicCaps is a dataset composed of 5,521 music examples, each labeled with an English aspect list and a free text caption written by musicians. The dataset contains 10-second music clips from AudioSet paired with rich textual descriptions that capture sonic qualities and musical elements like genre, mood, tempo, instrumentation, and rhythm. Created to support research in music-text understanding and generation tasks.","max_score":1.0,"categories":["multimodal","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":0.328,"normalized_score":0.328,"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}]}