{"benchmark_id":"polymath-en","benchmark_name":"PolyMath-en","benchmark_description":"PolyMath is a multilingual mathematical reasoning benchmark covering 18 languages and 4 difficulty levels from easy to hard, ensuring difficulty comprehensiveness, language diversity, and high-quality translation. The benchmark evaluates mathematical reasoning capabilities of large language models across diverse linguistic contexts, making it a highly discriminative multilingual mathematical benchmark.","max_score":1.0,"categories":["math","reasoning"],"modality":"text","total_models":2,"entries":[{"rank":1,"model_id":"kimi-k2-instruct-0905","model_name":"Kimi K2-Instruct-0905","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.651,"normalized_score":0.651,"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":2,"model_id":"kimi-k2-instruct","model_name":"Kimi K2 Instruct","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.651,"normalized_score":0.651,"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}]}