{"eval_library":{"additional_details":{"dataset":"hellaswag-de","few_shot":"true","languages":"[\"de\"]","litellm_version":null,"raw_results":"[{\"mcc\": 0.6413424505705206, \"accuracy\": 0.728515625}, {\"mcc\": 0.4773637723947521, \"accuracy\": 0.5849609375}, {\"mcc\": 0.5051516217389359, \"accuracy\": 0.6103515625}, {\"mcc\": 0.5615215599423178, \"accuracy\": 0.6689453125}, {\"mcc\": 0.459361259757744, \"accuracy\": 0.5712890625}, {\"mcc\": 0.47285732976368877, \"accuracy\": 0.583984375}, {\"mcc\": 0.5817206813323945, \"accuracy\": 0.67529296875}, {\"mcc\": 0.5920449428875398, \"accuracy\": 0.6875}, {\"mcc\": 0.5780994221795035, \"accuracy\": 0.68212890625}, {\"mcc\": 0.5008372465302744, \"accuracy\": 0.60498046875}]","task":"common-sense-reasoning","torch_version":"2.7.0","transformers_version":"4.52.4","validation_split":"false","vllm_version":"0.9.1","xgrammar_version":"0.2.0"},"name":"euroeval","version":"15.10.0.dev0"},"evaluation_id":"hellaswag-de/CohereForAI/aya-23-35B/1781766557","evaluation_results":[{"evaluation_name":"test_mcc","metric_config":{"lower_is_better":false,"max_score":100,"min_score":0,"score_type":"continuous"},"score_details":{"details":{"num_failed_instances":"0.0"},"score":53.70300287097671,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":49.88067944744598,"method":"bootstrap","upper":57.525326294507444},"num_samples":10}},"source_data":{"dataset_name":"hellaswag-de","source_type":"hf_dataset"}},{"evaluation_name":"test_accuracy","metric_config":{"lower_is_better":false,"max_score":100,"min_score":0,"score_type":"continuous"},"score_details":{"details":{"num_failed_instances":"0.0"},"score":63.9794921875,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":60.58827341336168,"method":"bootstrap","upper":67.37071096163832},"num_samples":10}},"source_data":{"dataset_name":"hellaswag-de","source_type":"hf_dataset"}}],"evaluation_timestamp":"2026-06-18T07:09:17.004655+00:00","model_info":{"additional_details":{"commercially_licensed":false,"generative":"true","generative_type":"instruction_tuned","max_sequence_length":"8192","merge":"false","model_url":"https://hf.co/CohereForAI/aya-23-35B","num_model_parameters":"34980831232","open":true,"release_date":"2024-05-23","trained_from_scratch":false,"vocabulary_size":"256000"},"id":"CohereForAI/aya-23-35B","inference_engine":{"name":"vllm","version":"0.9.1"},"name":"CohereForAI/aya-23-35B"},"retrieved_timestamp":"1781766557","schema_version":"0.2.1","source_metadata":{"evaluator_relationship":"third_party","source_name":"EuroEval","source_organization_name":"EuroEval","source_organization_url":"https://euroeval.com","source_type":"evaluation_run"}}
