{"benchmark_id":"big-bench-audio","benchmark_name":"Big Bench Audio","benchmark_description":"Big Bench Audio is an audio reasoning benchmark adapted from a subset of Big Bench Hard, with text questions converted to spoken audio. It evaluates the reasoning ability of speech-to-speech and audio language models on tasks delivered as audio input, with accuracy scored by an independent evaluation (Artificial Analysis).","max_score":1.0,"categories":["reasoning","audio"],"modality":"audio","total_models":1,"entries":[{"rank":1,"model_id":"nova-2-sonic","model_name":"Nova 2 Sonic","organization_name":"Amazon","organization_id":"amazon","benchmark_score":0.87,"normalized_score":0.87,"verified":false,"self_reported":true,"provider_id":"bedrock","input_cost_per_million":0.33,"output_cost_per_million":2.75,"speed_rps":null,"context_window":1000000,"release_date":"2025-12-02","announcement_date":"2025-12-02","multimodal":true,"param_count":null,"is_new":false}]}