{"benchmark_id":"gdpval-mm","name":"GDPval-MM","parent_benchmark":{"id":"gdpval-aa","name":"GDPval-AA"},"categories":["multimodal","reasoning","finance","general"],"modality":"multimodal","multilingual":false,"max_score":1.0,"language":"en","description":"GDPval-MM is the multimodal variant of the GDPval benchmark, evaluating AI model performance on real-world economically valuable tasks that require processing and generating multimodal content including documents, slides, diagrams, spreadsheets, images, and other professional deliverables across diverse industries.","paper_link":"https://arxiv.org/abs/2510.04374","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:23.415260+00:00","updated_at":"2026-07-05T18:27:48.740747+00:00","statistics":{"total_models":3,"average_score":0.754,"min_score":0.59,"max_score":0.849,"score_stddev":0.14262187770464954,"verified_count":0,"self_reported_count":3},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"gpt-5.5","model_name":"GPT-5.5","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.849,"normalized_score":0.849,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/introducing-gpt-5-5/","analysis_method":"GDPval (wins or ties). Reasoning effort xhigh.","verification_date":null,"provider_id":"openai","input_cost_per_million":5.0,"output_cost_per_million":30.0,"context_window":1050000,"announcement_date":"2026-04-23","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"OpenAI","best_throughput":null,"throughput_provider":"OpenAI","context_provider":"OpenAI"},{"rank":2,"model_id":"gpt-5.5-pro","model_name":"GPT-5.5 Pro","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.823,"normalized_score":0.823,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/introducing-gpt-5-5/","analysis_method":"GPT-5.5 Pro - GDPval (wins or ties).","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-04-23","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":3,"model_id":"minimax-m2.5","model_name":"MiniMax M2.5","organization_id":"minimax","organization_name":"MiniMax","organization_country":"CN","score":0.59,"normalized_score":0.59,"verified":false,"self_reported":true,"self_reported_source":"https://www.minimax.io/news/minimax-m25","analysis_method":null,"verification_date":null,"provider_id":"minimax","input_cost_per_million":0.3,"output_cost_per_million":1.2,"context_window":1000000,"announcement_date":"2026-02-12","param_count":230000000000,"is_open_source":true,"is_new":false,"best_latency":3.0,"latency_provider":"MiniMax","best_throughput":100.0,"throughput_provider":"MiniMax","context_provider":"MiniMax"}]}