{"benchmark_id":"intergps","name":"InterGPS","parent_benchmark":null,"categories":["math","spatial_reasoning"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"Interpretable Geometry Problem Solver (Inter-GPS) with Geometry3K dataset of 3,002 geometry problems with dense annotation in formal language using theorem knowledge and symbolic reasoning","paper_link":"https://arxiv.org/abs/2105.04165","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:24.037179+00:00","updated_at":"2026-07-05T18:27:50.690838+00:00","statistics":{"total_models":2,"average_score":0.4245,"min_score":0.363,"max_score":0.486,"score_stddev":0.08697413408594534,"verified_count":0,"self_reported_count":2},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"phi-4-multimodal-instruct","model_name":"Phi-4-multimodal-instruct","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.486,"normalized_score":0.486,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/microsoft/Phi-4-multimodal-instruct","analysis_method":"testmini","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-02-01","param_count":5600000000,"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":"phi-3.5-vision-instruct","model_name":"Phi-3.5-vision-instruct","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.363,"normalized_score":0.363,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/microsoft/Phi-3.5-vision-instruct","analysis_method":"standard evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-08-23","param_count":4200000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}