{"benchmark_id":"mega-udpos","name":"MEGA UDPOS","parent_benchmark":null,"categories":["language"],"modality":"text","multilingual":true,"max_score":1.0,"language":"en","description":"Universal Dependencies POS tagging as part of the MEGA benchmark suite. A multilingual part-of-speech tagging dataset based on Universal Dependencies treebanks, utilizing the universal POS tag set of 17 tags across 38 diverse languages from different language families. Used for evaluating multilingual POS tagging systems.","paper_link":"https://arxiv.org/abs/2004.10643","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:24.443871+00:00","updated_at":"2026-07-05T18:27:52.940751+00:00","statistics":{"total_models":2,"average_score":0.5345,"min_score":0.465,"max_score":0.604,"score_stddev":0.09828784258493012,"verified_count":0,"self_reported_count":2},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"phi-3.5-moe-instruct","model_name":"Phi-3.5-MoE-instruct","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.604,"normalized_score":0.604,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/microsoft/Phi-3.5-MoE-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":60000000000,"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-mini-instruct","model_name":"Phi-3.5-mini-instruct","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.465,"normalized_score":0.465,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/microsoft/Phi-3.5-mini-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":3800000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}