{"benchmark_id":"hiddenmath","name":"HiddenMath","parent_benchmark":null,"categories":["math","reasoning"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"Google DeepMind's internal mathematical reasoning benchmark that introduces novel problems not encountered during model training to evaluate true mathematical reasoning capabilities rather than memorization","paper_link":"https://storage.googleapis.com/deepmind-media/gemini/gemini_v1_5_report.pdf","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:23.823229+00:00","updated_at":"2026-07-05T18:27:49.740765+00:00","statistics":{"total_models":13,"average_score":0.42669230769230765,"min_score":0.158,"max_score":0.63,"score_stddev":0.14283696102864074,"verified_count":0,"self_reported_count":13},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"gemini-2.0-flash","model_name":"Gemini 2.0 Flash","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.63,"normalized_score":0.63,"verified":false,"self_reported":true,"self_reported_source":"https://blog.google/technology/google-deepmind/google-gemini-ai-update-december-2024/","analysis_method":"Competition-level math problems, Held out dataset AIME/AMC-like","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-12-01","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":2,"model_id":"gemma-3-27b-it","model_name":"Gemma 3 27B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.603,"normalized_score":0.603,"verified":false,"self_reported":true,"self_reported_source":"https://ai.google.dev/gemma/docs/core/model_card_3","analysis_method":"0-shot evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-03-12","param_count":27000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":3,"model_id":"gemini-2.0-flash-lite","model_name":"Gemini 2.0 Flash-Lite","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.553,"normalized_score":0.553,"verified":false,"self_reported":true,"self_reported_source":"https://ai.google.dev/gemini-api/docs/models","analysis_method":"0-shot evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-02-05","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":4,"model_id":"gemma-3-12b-it","model_name":"Gemma 3 12B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.545,"normalized_score":0.545,"verified":false,"self_reported":true,"self_reported_source":"https://ai.google.dev/gemma/docs/core/model_card_3","analysis_method":"0-shot evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-03-12","param_count":12000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":5,"model_id":"gemini-1.5-pro","model_name":"Gemini 1.5 Pro","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.52,"normalized_score":0.52,"verified":false,"self_reported":true,"self_reported_source":"https://deepmind.google/technologies/gemini/pro/","analysis_method":"Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-05-01","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":6,"model_id":"gemini-1.5-flash","model_name":"Gemini 1.5 Flash","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.472,"normalized_score":0.472,"verified":false,"self_reported":true,"self_reported_source":"https://deepmind.google/technologies/gemini/flash/","analysis_method":"Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-05-01","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":7,"model_id":"gemma-3-4b-it","model_name":"Gemma 3 4B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.43,"normalized_score":0.43,"verified":false,"self_reported":true,"self_reported_source":"https://ai.google.dev/gemma/docs/core/model_card_3","analysis_method":"0-shot evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-03-12","param_count":4000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":8,"model_id":"gemma-3n-e4b-it-litert-preview","model_name":"Gemma 3n E4B Instructed LiteRT Preview","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.377,"normalized_score":0.377,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/gemma-3n-E4B-it-litert-preview","analysis_method":"0-shot Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-05-20","param_count":1910000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":8,"model_id":"gemma-3n-e4b-it","model_name":"Gemma 3n E4B Instructed","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.377,"normalized_score":0.377,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/gemma-3n-E4B-it","analysis_method":"Accuracy. 0-shot.","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-06-26","param_count":8000000000,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":10,"model_id":"gemini-1.5-flash-8b","model_name":"Gemini 1.5 Flash 8B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.328,"normalized_score":0.328,"verified":false,"self_reported":true,"self_reported_source":"https://deepmind.google/technologies/gemini/flash/","analysis_method":"Accuracy on competition-level math problems","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-03-15","param_count":8000000000,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":11,"model_id":"gemma-3n-e2b-it","model_name":"Gemma 3n E2B Instructed","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.277,"normalized_score":0.277,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/gemma-3n-E2B-it","analysis_method":"Accuracy. 0-shot.","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-06-26","param_count":8000000000,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":11,"model_id":"gemma-3n-e2b-it-litert-preview","model_name":"Gemma 3n E2B Instructed LiteRT (Preview)","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.277,"normalized_score":0.277,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/google/gemma-3n-E2B-it-litert-preview","analysis_method":"0-shot Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-05-20","param_count":1910000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":13,"model_id":"gemma-3-1b-it","model_name":"Gemma 3 1B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.158,"normalized_score":0.158,"verified":false,"self_reported":true,"self_reported_source":"https://ai.google.dev/gemma/docs/core/model_card_3","analysis_method":"0-shot evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-03-12","param_count":1000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}