{"eval_library":{"additional_details":{"dataset":"scandiqa-da","few_shot":"true","languages":"[\"da\"]","litellm_version":null,"raw_results":"[{\"f1\": 65.85235471599108, \"em\": 58.63636363636363}, {\"f1\": 65.62848237601838, \"em\": 58.83244882486732}, {\"f1\": 67.94869312061356, \"em\": 61.22766122766123}, {\"f1\": 66.62927224009118, \"em\": 60.273972602739725}, {\"f1\": 67.43399428586847, \"em\": 61.680801850424054}, {\"f1\": 65.66550761359686, \"em\": 57.86259541984733}, {\"f1\": 65.94973523921858, \"em\": 58.03432137285491}, {\"f1\": 64.39958057440825, \"em\": 57.704402515723274}, {\"f1\": 66.37778152993242, \"em\": 60.139318885448915}, {\"f1\": 67.29333222252613, \"em\": 58.7962962962963}]","task":"reading-comprehension","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":"scandiqa-da/CohereForAI/aya-23-35B/1781766557","evaluation_results":[{"evaluation_name":"test_f1","metric_config":{"lower_is_better":false,"max_score":100,"min_score":0,"score_type":"continuous"},"score_details":{"details":{"num_failed_instances":"0.0"},"score":66.31787339182651,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":65.66813351508225,"method":"bootstrap","upper":66.96761326857077},"num_samples":10}},"source_data":{"dataset_name":"scandiqa-da","source_type":"hf_dataset"}},{"evaluation_name":"test_em","metric_config":{"lower_is_better":false,"max_score":100,"min_score":0,"score_type":"continuous"},"score_details":{"details":{"num_failed_instances":"0.0"},"score":59.31881826322267,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":58.43838346092886,"method":"bootstrap","upper":60.19925306551647},"num_samples":10}},"source_data":{"dataset_name":"scandiqa-da","source_type":"hf_dataset"}}],"evaluation_timestamp":"2026-06-18T07:09:17.006063+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"}}