{"benchmark_id":"mega-xstorycloze","benchmark_name":"MEGA XStoryCloze","benchmark_description":"XStoryCloze as part of the MEGA benchmark suite. A cross-lingual story completion task that consists of professionally translated versions of the English StoryCloze dataset to 10 non-English languages. Requires models to predict the correct ending for a given four-sentence story, evaluating commonsense reasoning and narrative understanding.","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":0.828,"normalized_score":0.828,"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":0.735,"normalized_score":0.735,"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}]}