{"benchmark_id":"wmt23","name":"WMT23","parent_benchmark":null,"categories":["language","healthcare"],"modality":"text","multilingual":true,"max_score":1.0,"language":"en","description":"The Eighth Conference on Machine Translation (WMT23) benchmark evaluating machine translation systems across 8 language pairs (14 translation directions) including general, biomedical, literary, and low-resource language translation tasks. Features specialized shared tasks for quality estimation, metrics evaluation, sign language translation, and discourse-level literary translation with professional human assessment.","paper_link":"https://aclanthology.org/2023.wmt-1.1/","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:26.995203+00:00","updated_at":"2026-07-05T18:28:05.960773+00:00","statistics":{"total_models":4,"average_score":0.73375,"min_score":0.717,"max_score":0.751,"score_stddev":0.015173990905493522,"verified_count":0,"self_reported_count":3},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"gemini-1.5-pro","model_name":"Gemini 1.5 Pro","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.751,"normalized_score":0.751,"verified":false,"self_reported":true,"self_reported_source":"https://deepmind.google/technologies/gemini/pro/","analysis_method":"Score","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":2,"model_id":"gemini-1.5-flash","model_name":"Gemini 1.5 Flash","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.741,"normalized_score":0.741,"verified":false,"self_reported":true,"self_reported_source":"https://deepmind.google/technologies/gemini/flash/","analysis_method":"Score","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":"gemini-1.5-flash-8b","model_name":"Gemini 1.5 Flash 8B","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.726,"normalized_score":0.726,"verified":false,"self_reported":true,"self_reported_source":"https://deepmind.google/technologies/gemini/flash/","analysis_method":"Translation quality score","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":4,"model_id":"gemini-1.0-pro","model_name":"Gemini 1.0 Pro","organization_id":"google","organization_name":"Google","organization_country":"US","score":0.717,"normalized_score":0.717,"verified":false,"self_reported":false,"self_reported_source":"https://example.com/benchmark-image","analysis_method":"Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-02-15","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}]}