{"benchmark_id":"natural2code","name":"Natural2Code","parent_benchmark":null,"categories":["reasoning","general"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"NaturalCodeBench (NCB) is a challenging code benchmark designed to mirror the complexity and variety of real-world coding tasks. It comprises 402 high-quality problems in Python and Java, selected from natural user queries from online coding services, covering 6 different domains.","paper_link":"https://arxiv.org/abs/2405.04520","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:25.348434+00:00","updated_at":"2026-07-05T18:27:56.870736+00:00","statistics":{"total_models":8,"average_score":0.7813750000000002,"min_score":0.56,"max_score":0.929,"score_stddev":0.11205475383553734,"verified_count":0,"self_reported_count":8},"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":0.929,"normalized_score":0.929,"verified":false,"self_reported":true,"self_reported_source":"https://blog.google/technology/google-deepmind/google-gemini-ai-update-december-2024/","analysis_method":"Code generation evaluation across multiple languages","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":"gemini-1.5-pro","model_name":"Gemini 1.5 Pro","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.854,"normalized_score":0.854,"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":3,"model_id":"gemma-3-27b-it","model_name":"Gemma 3 27B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.845,"normalized_score":0.845,"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":4,"model_id":"gemma-3-12b-it","model_name":"Gemma 3 12B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.807,"normalized_score":0.807,"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-flash","model_name":"Gemini 1.5 Flash","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.798,"normalized_score":0.798,"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":6,"model_id":"gemini-1.5-flash-8b","model_name":"Gemini 1.5 Flash 8B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.755,"normalized_score":0.755,"verified":false,"self_reported":true,"self_reported_source":"https://deepmind.google/technologies/gemini/flash/","analysis_method":"Pass rate on code generation tasks across multiple programming languages","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":7,"model_id":"gemma-3-4b-it","model_name":"Gemma 3 4B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.703,"normalized_score":0.703,"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-3-1b-it","model_name":"Gemma 3 1B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.56,"normalized_score":0.56,"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}]}