{"benchmark_id":"omnimath","benchmark_name":"OmniMath","benchmark_description":"A Universal Olympiad Level Mathematic Benchmark for Large Language Models containing 4,428 competition-level problems with rigorous human annotation, categorized into over 33 sub-domains and spanning more than 10 distinct difficulty levels","max_score":1.0,"categories":["math","reasoning"],"modality":"text","total_models":2,"entries":[{"rank":1,"model_id":"phi-4-reasoning-plus","model_name":"Phi 4 Reasoning Plus","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.819,"normalized_score":0.819,"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":14000000000,"is_new":false},{"rank":2,"model_id":"phi-4-reasoning","model_name":"Phi 4 Reasoning","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.766,"normalized_score":0.766,"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":14000000000,"is_new":false}]}