{"benchmark_id":"wild-bench","benchmark_name":"Wild Bench","benchmark_description":"WildBench is an automated evaluation framework that benchmarks large language models using 1,024 challenging, real-world tasks selected from over one million human-chatbot conversation logs. It introduces two evaluation metrics (WB-Reward and WB-Score) that achieve high correlation with human preferences and uses task-specific checklists for systematic evaluation.","max_score":1.0,"categories":["reasoning","general","communication"],"modality":"text","total_models":8,"entries":[{"rank":1,"model_id":"ministral-3-14b-instruct-2512","model_name":"MiniStral 3 (14B Instruct 2512)","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.685,"normalized_score":0.685,"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":"2025-12-04","announcement_date":"2025-12-04","multimodal":true,"param_count":14000000000,"is_new":false},{"rank":2,"model_id":"mistral-large-3-2509","model_name":"Mistral Large 3","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.685,"normalized_score":0.685,"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":"2025-09-01","announcement_date":"2025-09-01","multimodal":true,"param_count":675000000000,"is_new":false},{"rank":3,"model_id":"ministral-3-8b-instruct-2512","model_name":"Ministral 3 (8B Instruct 2512)","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.668,"normalized_score":0.668,"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":"2025-12-04","announcement_date":"2025-12-04","multimodal":true,"param_count":8000000000,"is_new":false},{"rank":4,"model_id":"mistral-small-3.2-24b-instruct-2506","model_name":"Mistral Small 3.2 24B Instruct","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.6533,"normalized_score":0.6533,"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":"2025-06-20","announcement_date":"2025-06-20","multimodal":true,"param_count":23600000000,"is_new":false},{"rank":5,"model_id":"ministral-3-3b-instruct-2512","model_name":"Ministral 3 (3B Instruct 2512)","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.568,"normalized_score":0.568,"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":"2025-12-04","announcement_date":"2025-12-04","multimodal":true,"param_count":3000000000,"is_new":false},{"rank":6,"model_id":"mistral-small-24b-instruct-2501","model_name":"Mistral Small 3 24B Instruct","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.522,"normalized_score":0.522,"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":"2025-01-30","announcement_date":"2025-01-30","multimodal":false,"param_count":24000000000,"is_new":false},{"rank":7,"model_id":"jamba-1.5-large","model_name":"Jamba 1.5 Large","organization_name":"AI21 Labs","organization_id":"ai21","benchmark_score":0.485,"normalized_score":0.485,"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":"2024-08-22","announcement_date":"2024-08-22","multimodal":false,"param_count":398000000000,"is_new":false},{"rank":8,"model_id":"jamba-1.5-mini","model_name":"Jamba 1.5 Mini","organization_name":"AI21 Labs","organization_id":"ai21","benchmark_score":0.424,"normalized_score":0.424,"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":"2024-08-22","announcement_date":"2024-08-22","multimodal":false,"param_count":52000000000,"is_new":false}]}