{"eval_library":{"additional_details":{"dataset":"mmlu-it","few_shot":"true","languages":"[\"it\"]","litellm_version":null,"raw_results":"[{\"mcc\": 0.19138824225087822, \"accuracy\": 0.39208984375}, {\"mcc\": 0.19080973640161306, \"accuracy\": 0.37646484375}, {\"mcc\": 0.15750834307384712, \"accuracy\": 0.36376953125}, {\"mcc\": 0.20643612544030732, \"accuracy\": 0.40576171875}, {\"mcc\": 0.19305329236955873, \"accuracy\": 0.400390625}, {\"mcc\": 0.1656532864396209, \"accuracy\": 0.36865234375}, {\"mcc\": 0.20278318678096935, \"accuracy\": 0.40234375}, {\"mcc\": 0.21912010503454868, \"accuracy\": 0.40771484375}, {\"mcc\": 0.21134043874838665, \"accuracy\": 0.4013671875}, {\"mcc\": 0.1743550573757673, \"accuracy\": 0.37841796875}]","task":"knowledge","torch_version":"2.7.0","transformers_version":"4.51.3","validation_split":"false","vllm_version":"0.9.1","xgrammar_version":"0.2.0"},"name":"euroeval","version":"15.10.0"},"evaluation_id":"mmlu-it/CohereForAI/aya-23-8B/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":19.12447813915497,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":17.880294719258078,"method":"bootstrap","upper":20.368661559051862},"num_samples":10}},"source_data":{"dataset_name":"mmlu-it","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":38.9697265625,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":37.95414548998242,"method":"bootstrap","upper":39.98530763501758},"num_samples":10}},"source_data":{"dataset_name":"mmlu-it","source_type":"hf_dataset"}}],"evaluation_timestamp":"2026-06-18T07:09:17.050512+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-23-8B","num_model_parameters":"8028033024","open":true,"release_date":"2024-05-23","trained_from_scratch":false,"vocabulary_size":"256000"},"id":"CohereForAI/aya-23-8B","inference_engine":{"name":"vllm","version":"0.9.1"},"name":"CohereForAI/aya-23-8B"},"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"}}
