{"benchmark_id":"nih-multi-needle","benchmark_name":"NIH/Multi-needle","benchmark_description":"Multi-needle in a haystack benchmark for evaluating long-context comprehension capabilities of language models by testing retrieval of multiple target pieces of information from extended documents","max_score":1.0,"categories":["long_context"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"llama-3.2-3b-instruct","model_name":"Llama 3.2 3B Instruct","organization_name":"Meta","organization_id":"meta","benchmark_score":0.847,"normalized_score":0.847,"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":"2024-09-25","announcement_date":"2024-09-25","multimodal":false,"param_count":3210000000,"is_new":false}]}