{"benchmark_id":"math-500","benchmark_name":"MATH-500","benchmark_description":"MATH-500 is a subset of the MATH dataset containing 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 across seven mathematical subjects including Prealgebra, Algebra, Number Theory, Counting and Probability, Geometry, Intermediate Algebra, and Precalculus.","max_score":1.0,"categories":["math","reasoning"],"modality":"text","total_models":32,"entries":[{"rank":1,"model_id":"longcat-flash-thinking","model_name":"LongCat-Flash-Thinking","organization_name":"Meituan","organization_id":"meituan","benchmark_score":0.992,"normalized_score":0.992,"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":"2025-09-22","announcement_date":"2025-09-22","multimodal":false,"param_count":560000000000,"is_new":false},{"rank":2,"model_id":"sarvam-105b","model_name":"Sarvam-105B","organization_name":"Sarvam AI","organization_id":"sarvamai","benchmark_score":0.986,"normalized_score":0.986,"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":"2026-03-06","announcement_date":"2026-03-06","multimodal":false,"param_count":105000000000,"is_new":false},{"rank":3,"model_id":"glm-4.5","model_name":"GLM-4.5","organization_name":"Zhipu AI","organization_id":"zai-org","benchmark_score":0.982,"normalized_score":0.982,"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":"2025-07-28","announcement_date":"2025-07-28","multimodal":false,"param_count":355000000000,"is_new":false},{"rank":4,"model_id":"glm-4.5-air","model_name":"GLM-4.5-Air","organization_name":"Zhipu AI","organization_id":"zai-org","benchmark_score":0.981,"normalized_score":0.981,"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":"2025-07-28","announcement_date":"2025-07-28","multimodal":false,"param_count":106000000000,"is_new":false},{"rank":5,"model_id":"nvidia-nemotron-nano-9b-v2","model_name":"Nemotron Nano 9B v2","organization_name":"NVIDIA","organization_id":"nvidia","benchmark_score":0.978,"normalized_score":0.978,"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":"2025-08-18","announcement_date":"2025-08-18","multimodal":false,"param_count":8900000000,"is_new":false},{"rank":6,"model_id":"kimi-k2-instruct-0905","model_name":"Kimi K2-Instruct-0905","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.974,"normalized_score":0.974,"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":"2025-09-05","announcement_date":"2025-09-05","multimodal":false,"param_count":1000000000000,"is_new":false},{"rank":7,"model_id":"kimi-k2-instruct","model_name":"Kimi K2 Instruct","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.974,"normalized_score":0.974,"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":"2025-07-11","announcement_date":"2025-07-11","multimodal":false,"param_count":1000000000000,"is_new":false},{"rank":8,"model_id":"sarvam-30b","model_name":"Sarvam-30B","organization_name":"Sarvam AI","organization_id":"sarvamai","benchmark_score":0.97,"normalized_score":0.97,"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":"2026-03-06","announcement_date":"2026-03-06","multimodal":false,"param_count":30000000000,"is_new":false},{"rank":9,"model_id":"llama-3.1-nemotron-ultra-253b-v1","model_name":"Llama 3.1 Nemotron Ultra 253B v1","organization_name":"NVIDIA","organization_id":"nvidia","benchmark_score":0.97,"normalized_score":0.97,"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":"2025-04-07","announcement_date":"2025-04-07","multimodal":false,"param_count":253000000000,"is_new":false},{"rank":10,"model_id":"longcat-flash-lite","model_name":"LongCat-Flash-Lite","organization_name":"Meituan","organization_id":"meituan","benchmark_score":0.968,"normalized_score":0.968,"verified":false,"self_reported":true,"provider_id":"meituan","input_cost_per_million":0.1,"output_cost_per_million":0.4,"speed_rps":500.0,"context_window":256000,"release_date":"2026-02-05","announcement_date":"2026-02-05","multimodal":false,"param_count":68500000000,"is_new":false},{"rank":11,"model_id":"minimax-m1-80k","model_name":"MiniMax M1 80K","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.968,"normalized_score":0.968,"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":"2025-06-16","announcement_date":"2025-06-16","multimodal":false,"param_count":456000000000,"is_new":false},{"rank":12,"model_id":"llama-3.3-nemotron-super-49b-v1","model_name":"Llama-3.3 Nemotron Super 49B v1","organization_name":"NVIDIA","organization_id":"nvidia","benchmark_score":0.966,"normalized_score":0.966,"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":"2025-03-18","announcement_date":"2025-03-18","multimodal":false,"param_count":49900000000,"is_new":false},{"rank":13,"model_id":"longcat-flash-chat","model_name":"LongCat-Flash-Chat","organization_name":"Meituan","organization_id":"meituan","benchmark_score":0.964,"normalized_score":0.964,"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":"2025-08-29","announcement_date":"2025-08-29","multimodal":false,"param_count":560000000000,"is_new":false},{"rank":14,"model_id":"claude-3-7-sonnet-20250219","model_name":"Claude 3.7 Sonnet","organization_name":"Anthropic","organization_id":"anthropic","benchmark_score":0.962,"normalized_score":0.962,"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":"2025-02-24","announcement_date":"2025-02-24","multimodal":true,"param_count":null,"is_new":false},{"rank":15,"model_id":"kimi-k1.5","model_name":"Kimi-k1.5","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.962,"normalized_score":0.962,"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":"2025-01-20","announcement_date":"2025-01-20","multimodal":true,"param_count":null,"is_new":false},{"rank":16,"model_id":"minimax-m1-40k","model_name":"MiniMax M1 40K","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.96,"normalized_score":0.96,"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":"2025-06-16","announcement_date":"2025-06-16","multimodal":false,"param_count":456000000000,"is_new":false},{"rank":17,"model_id":"deepseek-r1-zero","model_name":"DeepSeek R1 Zero","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.959,"normalized_score":0.959,"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":"2025-01-20","announcement_date":"2025-01-20","multimodal":false,"param_count":671000000000,"is_new":false},{"rank":18,"model_id":"llama-3.1-nemotron-nano-8b-v1","model_name":"Llama 3.1 Nemotron Nano 8B V1","organization_name":"NVIDIA","organization_id":"nvidia","benchmark_score":0.954,"normalized_score":0.954,"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":"2025-03-18","announcement_date":"2025-03-18","multimodal":false,"param_count":8000000000,"is_new":false},{"rank":19,"model_id":"phi-4-mini-reasoning","model_name":"Phi 4 Mini Reasoning","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.946,"normalized_score":0.946,"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":"2025-04-30","announcement_date":"2025-04-30","multimodal":false,"param_count":3800000000,"is_new":false},{"rank":20,"model_id":"deepseek-r1-distill-llama-70b","model_name":"DeepSeek R1 Distill Llama 70B","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.945,"normalized_score":0.945,"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":"2025-01-20","announcement_date":"2025-01-20","multimodal":false,"param_count":70600000000,"is_new":false},{"rank":21,"model_id":"deepseek-r1-distill-qwen-32b","model_name":"DeepSeek R1 Distill Qwen 32B","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.943,"normalized_score":0.943,"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":"2025-01-20","announcement_date":"2025-01-20","multimodal":false,"param_count":32800000000,"is_new":false},{"rank":22,"model_id":"deepseek-v3-0324","model_name":"DeepSeek-V3 0324","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.94,"normalized_score":0.94,"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":"2025-03-25","announcement_date":"2025-03-25","multimodal":false,"param_count":671000000000,"is_new":false},{"rank":23,"model_id":"deepseek-r1-distill-qwen-14b","model_name":"DeepSeek R1 Distill Qwen 14B","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.939,"normalized_score":0.939,"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":"2025-01-20","announcement_date":"2025-01-20","multimodal":false,"param_count":14800000000,"is_new":false},{"rank":24,"model_id":"deepseek-r1-distill-qwen-7b","model_name":"DeepSeek R1 Distill Qwen 7B","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.928,"normalized_score":0.928,"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":"2025-01-20","announcement_date":"2025-01-20","multimodal":false,"param_count":7620000000,"is_new":false},{"rank":25,"model_id":"qwq-32b","model_name":"QwQ-32B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.906,"normalized_score":0.906,"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":"2025-03-05","announcement_date":"2025-03-05","multimodal":false,"param_count":32500000000,"is_new":false},{"rank":26,"model_id":"qwq-32b-preview","model_name":"QwQ-32B-Preview","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.906,"normalized_score":0.906,"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":"2024-11-28","announcement_date":"2024-11-28","multimodal":false,"param_count":32500000000,"is_new":false},{"rank":27,"model_id":"deepseek-v3","model_name":"DeepSeek-V3","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.902,"normalized_score":0.902,"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":"2024-12-25","announcement_date":"2024-12-25","multimodal":false,"param_count":671000000000,"is_new":false},{"rank":28,"model_id":"o1-mini","model_name":"o1-mini","organization_name":"OpenAI","organization_id":"openai","benchmark_score":0.9,"normalized_score":0.9,"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":"2024-09-12","announcement_date":"2024-09-12","multimodal":false,"param_count":null,"is_new":false},{"rank":29,"model_id":"deepseek-r1-distill-llama-8b","model_name":"DeepSeek R1 Distill Llama 8B","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.891,"normalized_score":0.891,"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":"2025-01-20","announcement_date":"2025-01-20","multimodal":false,"param_count":8030000000,"is_new":false},{"rank":30,"model_id":"deepseek-r1-distill-qwen-1.5b","model_name":"DeepSeek R1 Distill Qwen 1.5B","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.839,"normalized_score":0.839,"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":"2025-01-20","announcement_date":"2025-01-20","multimodal":false,"param_count":1780000000,"is_new":false},{"rank":31,"model_id":"granite-3.3-8b-instruct","model_name":"Granite 3.3 8B Instruct","organization_name":"IBM","organization_id":"ibm","benchmark_score":0.6902,"normalized_score":0.6902,"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":"2025-04-16","announcement_date":"2025-04-16","multimodal":true,"param_count":8000000000,"is_new":false},{"rank":32,"model_id":"granite-3.3-8b-base","model_name":"Granite 3.3 8B Base","organization_name":"IBM","organization_id":"ibm","benchmark_score":0.6902,"normalized_score":0.6902,"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":"2025-04-16","announcement_date":"2025-04-16","multimodal":true,"param_count":8170000000,"is_new":false}]}