{"benchmark_id":"lmarena-text","benchmark_name":"LMArena Text Leaderboard","benchmark_description":"LMArena Text Leaderboard is a blind human preference evaluation benchmark that ranks models based on pairwise comparisons in real-world conversations. The leaderboard uses Elo ratings computed from user preferences in head-to-head model battles, providing a comprehensive measure of overall model capability and style.","max_score":2000.0,"categories":["chat","reasoning","general"],"modality":"text","total_models":2,"entries":[{"rank":1,"model_id":"grok-4.1-thinking-2025-11-17","model_name":"Grok-4.1 Thinking","organization_name":"xAI","organization_id":"xai","benchmark_score":1483.0,"normalized_score":0.7415,"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":"grok-4.1-2025-11-17","model_name":"Grok-4.1","organization_name":"xAI","organization_id":"xai","benchmark_score":1465.0,"normalized_score":0.7325,"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}]}