{"benchmark_id":"amc-2022-23","name":"AMC_2022_23","parent_benchmark":null,"categories":["math","reasoning"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"American Mathematics Competition problems from the 2022-23 academic year, consisting of multiple-choice mathematics competition problems designed for high school students. These problems require advanced mathematical reasoning, problem-solving strategies, and mathematical knowledge covering topics like algebra, geometry, number theory, and combinatorics. The benchmark is derived from the official AMC competitions sponsored by the Mathematical Association of America.","paper_link":"https://arxiv.org/abs/2103.03874","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:21.585808+00:00","updated_at":"2026-07-05T18:27:42.740857+00:00","statistics":{"total_models":6,"average_score":0.482,"min_score":0.348,"max_score":0.52,"score_stddev":0.06936281424509821,"verified_count":0,"self_reported_count":6},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"mistral-large-3-675b-base-2512","model_name":"Mistral Large 3 (675B Base)","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.52,"normalized_score":0.52,"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":675000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":1,"model_id":"mistral-large-3-675B-instruct-2512-eagle","model_name":"Mistral Large 3 (675B Instruct 2512 Eagle)","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.52,"normalized_score":0.52,"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":675000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":1,"model_id":"mistral-large-3-675b-instruct-2512-nvfp4","model_name":"Mistral Large 3 (675B Instruct 2512 NVFP4)","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.52,"normalized_score":0.52,"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":675000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":1,"model_id":"mistral-large-latest","model_name":"Mistral Large 3 (675B Instruct 2512)","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.52,"normalized_score":0.52,"verified":false,"self_reported":true,"self_reported_source":"https://mistral.ai/news/mistral-3","analysis_method":null,"verification_date":null,"provider_id":"mistral","input_cost_per_million":0.5,"output_cost_per_million":1.5,"context_window":262100,"announcement_date":"2025-12-04","param_count":675000000000,"is_open_source":true,"is_new":false,"best_latency":1.7,"latency_provider":"Mistral AI","best_throughput":45.89,"throughput_provider":"Mistral AI","context_provider":"Mistral AI"},{"rank":5,"model_id":"gemini-1.5-pro","model_name":"Gemini 1.5 Pro","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.464,"normalized_score":0.464,"verified":false,"self_reported":true,"self_reported_source":"https://arxiv.org/pdf/2403.05530","analysis_method":"4-shot","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-05-01","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":6,"model_id":"gemini-1.5-flash","model_name":"Gemini 1.5 Flash","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.348,"normalized_score":0.348,"verified":false,"self_reported":true,"self_reported_source":"https://www.maa.org/math-competitions/amc-1012","analysis_method":"Accuracy (4-shot)","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-05-01","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}