{"benchmark_id":"math-(cot)","benchmark_name":"MATH (CoT)","benchmark_description":"MATH dataset contains 12,500 challenging competition mathematics problems from AMC 10, AMC 12, AIME, and other mathematics competitions. Each problem includes full step-by-step solutions and spans multiple difficulty levels (1-5) across seven mathematical subjects. This variant uses Chain-of-Thought prompting to encourage step-by-step reasoning.","max_score":1.0,"categories":["math","reasoning"],"modality":"text","total_models":6,"entries":[{"rank":1,"model_id":"llama-3.1-70b-instruct","model_name":"Llama 3.1 70B Instruct","organization_name":"Meta","organization_id":"meta","benchmark_score":0.68,"normalized_score":0.68,"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":"2024-07-23","announcement_date":"2024-07-23","multimodal":false,"param_count":70000000000,"is_new":false},{"rank":2,"model_id":"ministral-3-14b-base-2512","model_name":"Ministral 3 (14B Base 2512)","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.676,"normalized_score":0.676,"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":3,"model_id":"mistral-large-3-2509","model_name":"Mistral Large 3","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.676,"normalized_score":0.676,"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":4,"model_id":"ministral-3-8b-base-2512","model_name":"Ministral 3 (8B Base 2512)","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.626,"normalized_score":0.626,"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":5,"model_id":"ministral-3-3b-base-2512","model_name":"Ministral 3 (3B Base 2512)","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.601,"normalized_score":0.601,"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":"llama-3.1-8b-instruct","model_name":"Llama 3.1 8B Instruct","organization_name":"Meta","organization_id":"meta","benchmark_score":0.519,"normalized_score":0.519,"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":"2024-07-23","announcement_date":"2024-07-23","multimodal":false,"param_count":8000000000,"is_new":false}]}