{"benchmark_id":"math-(cot)","name":"MATH (CoT)","parent_benchmark":null,"categories":["math","reasoning"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","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.","paper_link":"https://arxiv.org/abs/2103.03874","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:24.259999+00:00","updated_at":"2026-07-05T18:27:51.980719+00:00","statistics":{"total_models":6,"average_score":0.6296666666666667,"min_score":0.519,"max_score":0.68,"score_stddev":0.06310203377599387,"verified_count":0,"self_reported_count":6},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"llama-3.1-70b-instruct","model_name":"Llama 3.1 70B Instruct","organization_id":"meta","organization_name":"Meta","organization_country":"US","score":0.68,"normalized_score":0.68,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct","analysis_method":"0-shot Chain-of-Thought","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-07-23","param_count":70000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":2,"model_id":"ministral-3-14b-base-2512","model_name":"Ministral 3 (14B Base 2512)","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.676,"normalized_score":0.676,"verified":false,"self_reported":true,"self_reported_source":"https://mistral.ai/news/mistral-3","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-12-04","param_count":14000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":2,"model_id":"mistral-large-3-2509","model_name":"Mistral Large 3","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.676,"normalized_score":0.676,"verified":false,"self_reported":true,"self_reported_source":"https://mistral.ai/news/ministral-14b-8b-3b/","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-01","param_count":675000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":4,"model_id":"ministral-3-8b-base-2512","model_name":"Ministral 3 (8B Base 2512)","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.626,"normalized_score":0.626,"verified":false,"self_reported":true,"self_reported_source":"https://mistral.ai/news/mistral-3","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-12-04","param_count":8000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":5,"model_id":"ministral-3-3b-base-2512","model_name":"Ministral 3 (3B Base 2512)","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.601,"normalized_score":0.601,"verified":false,"self_reported":true,"self_reported_source":"https://mistral.ai/news/mistral-3","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-12-04","param_count":3000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":6,"model_id":"llama-3.1-8b-instruct","model_name":"Llama 3.1 8B Instruct","organization_id":"meta","organization_name":"Meta","organization_country":"US","score":0.519,"normalized_score":0.519,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct","analysis_method":"0-shot","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-07-23","param_count":8000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}