{"benchmark_id":"openai-mrcr:-2-needle-256k","benchmark_name":"OpenAI-MRCR: 2 needle 256k","benchmark_description":"Multi-Round Co-reference Resolution (MRCR) benchmark that tests long-context reasoning by evaluating a model's ability to distinguish between similar outputs, reason about ordering, and reproduce specific content from multi-turn conversations containing multiple writing requests on overlapping topics at 256k tokens.","max_score":1.0,"categories":["long_context","reasoning"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"gpt-5-2025-08-07","model_name":"GPT-5","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.868,"normalized_score":0.868,"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}]}