{"benchmark_id":"factscore","benchmark_name":"FActScore","benchmark_description":"A fine-grained atomic evaluation metric for factual precision in long-form text generation that breaks generated text into atomic facts and computes the percentage supported by reliable knowledge sources, with automated assessment using retrieval and language models","max_score":1.0,"categories":["reasoning"],"modality":"text","total_models":2,"entries":[{"rank":1,"model_id":"grok-4.1-2025-11-17","model_name":"Grok-4.1","organization_name":"xAI","organization_id":"xai","benchmark_score":0.9703,"normalized_score":0.9703,"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":"2025-11-17","announcement_date":"2025-11-17","multimodal":true,"param_count":null,"is_new":false},{"rank":2,"model_id":"gpt-5-2025-08-07","model_name":"GPT-5","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.01,"normalized_score":0.01,"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":"2025-08-07","announcement_date":"2025-08-07","multimodal":true,"param_count":null,"is_new":false}]}