{"benchmark_id":"mega-tydi-qa","benchmark_name":"MEGA TyDi QA","benchmark_description":"TyDi QA as part of the MEGA benchmark suite. A question answering dataset covering 11 typologically diverse languages (Arabic, Bengali, English, Finnish, Indonesian, Japanese, Korean, Russian, Swahili, Telugu, and Thai) with 204K question-answer pairs. Features realistic information-seeking questions written by people who want to know the answer but don't know it yet.","max_score":1.0,"categories":["language","reasoning"],"modality":"text","total_models":2,"entries":[{"rank":1,"model_id":"phi-3.5-moe-instruct","model_name":"Phi-3.5-MoE-instruct","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.671,"normalized_score":0.671,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2024-08-23","announcement_date":"2024-08-23","multimodal":false,"param_count":60000000000,"is_new":false},{"rank":2,"model_id":"phi-3.5-mini-instruct","model_name":"Phi-3.5-mini-instruct","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.622,"normalized_score":0.622,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2024-08-23","announcement_date":"2024-08-23","multimodal":false,"param_count":3800000000,"is_new":false}]}