| {"schema_version": "0.2.1", "evaluation_id": "allocine/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.151557+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.3.1", "additional_details": {"dataset": "allocine", "languages": "[\"fr\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.9157818925916902, \"macro_f1\": 0.9565364921826396}, {\"mcc\": 0.9180897025850727, \"macro_f1\": 0.9584958463659665}, {\"mcc\": 0.9218703649893203, \"macro_f1\": 0.9598039215686274}, {\"mcc\": 0.9359665479958722, \"macro_f1\": 0.9672851484501716}, {\"mcc\": 0.9074271633249587, \"macro_f1\": 0.9526307443770827}, {\"mcc\": 0.9222782408615512, \"macro_f1\": 0.9604458143565614}, {\"mcc\": 0.921917812664714, \"macro_f1\": 0.959960899315738}, {\"mcc\": 0.9189258295856969, \"macro_f1\": 0.9589787415874372}, {\"mcc\": 0.934143643329881, \"macro_f1\": 0.9667008113425362}, {\"mcc\": 0.9358369513270431, \"macro_f1\": 0.9672175561530991}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "allocine", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 92.32238149255801, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 91.73989135698166, "upper": 92.90487162813436, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "allocine", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 96.08055975699858, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 95.778734258832, "upper": 96.38238525516516, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "conll-es/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.151596+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.8.4"}}, "eval_library": {"name": "euroeval", "version": "15.7.1.dev0", "additional_details": {"dataset": "conll-es", "languages": "[\"es\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.6.0", "vllm_version": "0.8.4", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.6296060181053169, \"micro_f1\": 0.5551497443389336}, {\"micro_f1_no_misc\": 0.6512605042016807, \"micro_f1\": 0.5607121424284858}, {\"micro_f1_no_misc\": 0.6560762509928515, \"micro_f1\": 0.506082235850005}, {\"micro_f1_no_misc\": 0.6524156678611146, \"micro_f1\": 0.5499021526418787}, {\"micro_f1_no_misc\": 0.6566134185303514, \"micro_f1\": 0.5748138827723602}, {\"micro_f1_no_misc\": 0.6468682505399568, \"micro_f1\": 0.5859323158593231}, {\"micro_f1_no_misc\": 0.6620934358367829, \"micro_f1\": 0.5737976782752903}, {\"micro_f1_no_misc\": 0.6501869046183528, \"micro_f1\": 0.5435757457594073}, {\"micro_f1_no_misc\": 0.6681519699812383, \"micro_f1\": 0.5748995599770422}, {\"micro_f1_no_misc\": 0.6644712769849982, \"micro_f1\": 0.5939018087855298}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "conll-es", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 65.37743697652644, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 64.70588653770659, "upper": 66.04898741534629, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "conll-es", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 56.18767266688256, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 54.62494896017524, "upper": 57.750396373589886, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "danish-citizen-tests/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.151630+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.2.0.dev0", "additional_details": {"dataset": "danish-citizen-tests", "languages": "[\"da\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.6246126116794449, \"accuracy\": 0.7504761904761905}, {\"mcc\": 0.7190560571189761, \"accuracy\": 0.8114285714285714}, {\"mcc\": 0.5981940413707174, \"accuracy\": 0.7333333333333333}, {\"mcc\": 0.6652112062168373, \"accuracy\": 0.7771428571428571}, {\"mcc\": 0.664567858844853, \"accuracy\": 0.7771428571428571}, {\"mcc\": 0.7194428726486483, \"accuracy\": 0.8133333333333334}, {\"mcc\": 0.6328046281926136, \"accuracy\": 0.7561904761904762}, {\"mcc\": 0.6274394555828495, \"accuracy\": 0.7523809523809524}, {\"mcc\": 0.6533660610118863, \"accuracy\": 0.7695238095238095}, {\"mcc\": 0.6225351803906611, \"accuracy\": 0.7485714285714286}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "danish-citizen-tests", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 65.27229973057487, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 62.75385520978698, "upper": 67.79074425136277, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "danish-citizen-tests", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 76.8952380952381, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 75.2461261606383, "upper": 78.5443500298379, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "dbrd/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.151663+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.8.4"}}, "eval_library": {"name": "euroeval", "version": "15.7.0.dev0", "additional_details": {"dataset": "dbrd", "languages": "[\"nl\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.6.0", "vllm_version": "0.8.4", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.9075570332606445, \"macro_f1\": 0.953612739330346}, {\"mcc\": 0.9023153811041312, \"macro_f1\": 0.9511567829109795}, {\"mcc\": 0.8897084651840076, \"macro_f1\": 0.943842822851908}, {\"mcc\": 0.9083414075175633, \"macro_f1\": 0.9535294208971907}, {\"mcc\": 0.9071890555029, \"macro_f1\": 0.9535888380392142}, {\"mcc\": 0.9005323653172315, \"macro_f1\": 0.9492185562841655}, {\"mcc\": 0.9053246267012132, \"macro_f1\": 0.9511326814509394}, {\"mcc\": 0.9139612468814992, \"macro_f1\": 0.9565180778276596}, {\"mcc\": 0.9101975982180566, \"macro_f1\": 0.9550760257008164}, {\"mcc\": 0.8741987827659826, \"macro_f1\": 0.9349931111084063}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "dbrd", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 90.1932596245323, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 89.46411414639698, "upper": 90.92240510266762, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "dbrd", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 95.02669056401626, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 94.62806258464438, "upper": 95.42531854338814, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "eltec/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.151694+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.3.1", "additional_details": {"dataset": "eltec", "languages": "[\"fr\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.5485005170630817, \"micro_f1\": 0.4832432432432432}, {\"micro_f1_no_misc\": 0.5355715427657873, \"micro_f1\": 0.45948232109626125}, {\"micro_f1_no_misc\": 0.5362076182503138, \"micro_f1\": 0.4619324001365654}, {\"micro_f1_no_misc\": 0.5953248981342484, \"micro_f1\": 0.5007985803016859}, {\"micro_f1_no_misc\": 0.6034878384580082, \"micro_f1\": 0.54715108199325}, {\"micro_f1_no_misc\": 0.5508653440270156, \"micro_f1\": 0.4590107821324662}, {\"micro_f1_no_misc\": 0.569919729615547, \"micro_f1\": 0.4973204715969988}, {\"micro_f1_no_misc\": 0.5787592008412198, \"micro_f1\": 0.49809402795425667}, {\"micro_f1_no_misc\": 0.5273611674098095, \"micro_f1\": 0.44682661221711756}, {\"micro_f1_no_misc\": 0.5488689714041827, \"micro_f1\": 0.432658524343316}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "eltec", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 55.94866827969215, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 54.327872918355965, "upper": 57.569463641028335, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "eltec", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 47.86518045015161, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 45.78975595558078, "upper": 49.940604944722445, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "fquad/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.151727+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.3.1", "additional_details": {"dataset": "fquad", "languages": "[\"fr\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 64.91194932656259, \"em\": 32.196969696969695}, {\"f1\": 62.71061729138031, \"em\": 31.2357846853677}, {\"f1\": 63.93261019123643, \"em\": 29.836829836829835}, {\"f1\": 61.09054504095943, \"em\": 25.951293759512936}, {\"f1\": 61.79480841624698, \"em\": 32.92212798766384}, {\"f1\": 63.72752548420903, \"em\": 30.076335877862597}, {\"f1\": 66.26200518711563, \"em\": 36.661466458658346}, {\"f1\": 64.83386840435898, \"em\": 35.14150943396226}, {\"f1\": 62.91195996295727, \"em\": 34.28792569659443}, {\"f1\": 61.29287870919797, \"em\": 27.237654320987655}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "fquad", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 63.34687680142247, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 62.294231640705775, "upper": 64.39952196213916, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "fquad", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 31.55478977544093, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 29.448151437971774, "upper": 33.66142811291009, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "goldenswag-pt/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.151758+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.10.0"}}, "eval_library": {"name": "euroeval", "version": "15.16.0", "additional_details": {"dataset": "goldenswag-pt", "languages": "[\"pt\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.55.2", "torch_version": "2.7.1", "vllm_version": "0.10.0", "xgrammar_version": "0.1.21", "litellm_version": null, "raw_results": "[{\"mcc\": 0.476149503656778, \"accuracy\": 0.6044921875}, {\"mcc\": 0.49536014582571974, \"accuracy\": 0.6142578125}, {\"mcc\": 0.426795964346621, \"accuracy\": 0.55224609375}, {\"mcc\": 0.45593263231490316, \"accuracy\": 0.59033203125}, {\"mcc\": 0.4894824317935786, \"accuracy\": 0.6044921875}, {\"mcc\": 0.45664491512161975, \"accuracy\": 0.5830078125}, {\"mcc\": 0.4720901899226658, \"accuracy\": 0.60009765625}, {\"mcc\": 0.4313754241488048, \"accuracy\": 0.56396484375}, {\"mcc\": 0.46383663291357147, \"accuracy\": 0.59228515625}, {\"mcc\": 0.4605515949007629, \"accuracy\": 0.58984375}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "goldenswag-pt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 46.28219434945024, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 44.90994585376161, "upper": 47.654442845138874, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "goldenswag-pt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 58.9501953125, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 57.76959383207401, "upper": 60.13079679292599, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "harem/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.151789+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.10.0"}}, "eval_library": {"name": "euroeval", "version": "15.16.0", "additional_details": {"dataset": "harem", "languages": "[\"pt\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.55.2", "torch_version": "2.7.1", "vllm_version": "0.10.0", "xgrammar_version": "0.1.21", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.49176251165682316, \"micro_f1\": 0.4218415417558886}, {\"micro_f1_no_misc\": 0.5315591948140566, \"micro_f1\": 0.411619517752041}, {\"micro_f1_no_misc\": 0.46414852752880925, \"micro_f1\": 0.3795476892822025}, {\"micro_f1_no_misc\": 0.44725738396624476, \"micro_f1\": 0.40343013057883453}, {\"micro_f1_no_misc\": 0.4822553897180763, \"micro_f1\": 0.40736196319018403}, {\"micro_f1_no_misc\": 0.4457077885162024, \"micro_f1\": 0.38607594936708867}, {\"micro_f1_no_misc\": 0.4965197215777262, \"micro_f1\": 0.45757408429965024}, {\"micro_f1_no_misc\": 0.5175577348940209, \"micro_f1\": 0.4283796740172579}, {\"micro_f1_no_misc\": 0.4926205313217448, \"micro_f1\": 0.367927802846234}, {\"micro_f1_no_misc\": 0.49504950495049505, \"micro_f1\": 0.4223050967856509}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "harem", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 48.644382889442, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 46.921375706767954, "upper": 50.367390072116045, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "harem", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 40.86063449875033, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 39.234393581926035, "upper": 42.48687541557462, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "hellaswag-es/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.151820+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.8.4"}}, "eval_library": {"name": "euroeval", "version": "15.7.1.dev0", "additional_details": {"dataset": "hellaswag-es", "languages": "[\"es\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.6.0", "vllm_version": "0.8.4", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.4196954898335244, \"accuracy\": 0.56005859375}, {\"mcc\": 0.39621249479694265, \"accuracy\": 0.54248046875}, {\"mcc\": 0.38321959204609074, \"accuracy\": 0.52880859375}, {\"mcc\": 0.43836076216522196, \"accuracy\": 0.5703125}, {\"mcc\": 0.4081554142734589, \"accuracy\": 0.544921875}, {\"mcc\": 0.4206614908697408, \"accuracy\": 0.56103515625}, {\"mcc\": 0.4181557231124506, \"accuracy\": 0.55419921875}, {\"mcc\": 0.4168204193028935, \"accuracy\": 0.5546875}, {\"mcc\": 0.43608314706546175, \"accuracy\": 0.568359375}, {\"mcc\": 0.3875285412331905, \"accuracy\": 0.5380859375}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "hellaswag-es", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 41.24893074698976, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 40.087713637864915, "upper": 42.4101478561146, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "hellaswag-es", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 55.22949218749999, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 54.3946290668083, "upper": 56.064355308191686, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "hellaswag-fi/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.151850+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.10.0"}}, "eval_library": {"name": "euroeval", "version": "15.16.0", "additional_details": {"dataset": "hellaswag-fi", "languages": "[\"fi\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.55.2", "torch_version": "2.7.1", "vllm_version": "0.10.0", "xgrammar_version": "0.1.21", "litellm_version": null, "raw_results": "[{\"mcc\": 0.1368973388636787, \"accuracy\": 0.343956704750451}, {\"mcc\": 0.1379244001712774, \"accuracy\": 0.343956704750451}, {\"mcc\": 0.17552472695882385, \"accuracy\": 0.37161755862898377}, {\"mcc\": 0.10569871135141885, \"accuracy\": 0.31689717378232113}, {\"mcc\": 0.15329644382251045, \"accuracy\": 0.36019242333132895}, {\"mcc\": 0.1694437738686983, \"accuracy\": 0.3656043295249549}, {\"mcc\": 0.14819874087185547, \"accuracy\": 0.35117257967528565}, {\"mcc\": 0.14686975909270225, \"accuracy\": 0.35598316295850874}, {\"mcc\": 0.12912137262662485, \"accuracy\": 0.34155141310883946}, {\"mcc\": 0.13691224882428643, \"accuracy\": 0.34034876728803365}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "hellaswag-fi", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 14.398875164518769, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 13.162807040105367, "upper": 15.63494328893217, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "hellaswag-fi", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 34.912808177991586, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 33.94869644948972, "upper": 35.876919906493455, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "hellaswag-fr/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.151880+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.3.1", "additional_details": {"dataset": "hellaswag-fr", "languages": "[\"fr\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.44330066693709724, \"accuracy\": 0.5791015625}, {\"mcc\": 0.41185625047637764, \"accuracy\": 0.5546875}, {\"mcc\": 0.4549361468429659, \"accuracy\": 0.591796875}, {\"mcc\": 0.4632422884157874, \"accuracy\": 0.59228515625}, {\"mcc\": 0.46744870718120235, \"accuracy\": 0.5966796875}, {\"mcc\": 0.4399914303327398, \"accuracy\": 0.57763671875}, {\"mcc\": 0.4547541336235615, \"accuracy\": 0.5888671875}, {\"mcc\": 0.45724806396524176, \"accuracy\": 0.58837890625}, {\"mcc\": 0.47155452381576785, \"accuracy\": 0.59619140625}, {\"mcc\": 0.4141308643621677, \"accuracy\": 0.55419921875}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "hellaswag-fr", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 44.784630759529094, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 43.49702960061604, "upper": 46.07223191844215, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "hellaswag-fr", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 58.19824218750001, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 57.217634054890524, "upper": 59.17885032010949, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "hellaswag-it/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.151909+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.3.1", "additional_details": {"dataset": "hellaswag-it", "languages": "[\"it\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.4326414099262081, \"accuracy\": 0.5732421875}, {\"mcc\": 0.46808006659282264, \"accuracy\": 0.59814453125}, {\"mcc\": 0.4461641269647352, \"accuracy\": 0.58251953125}, {\"mcc\": 0.45316297741407785, \"accuracy\": 0.587890625}, {\"mcc\": 0.47639805327588824, \"accuracy\": 0.60791015625}, {\"mcc\": 0.4675338298297135, \"accuracy\": 0.60107421875}, {\"mcc\": 0.5093020785648417, \"accuracy\": 0.63037109375}, {\"mcc\": 0.501604389963137, \"accuracy\": 0.6259765625}, {\"mcc\": 0.4996700169806048, \"accuracy\": 0.6240234375}, {\"mcc\": 0.42938261101972985, \"accuracy\": 0.56640625}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "hellaswag-it", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 46.839395605317584, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 45.0686596636222, "upper": 48.61013154701297, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "hellaswag-it", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 59.9755859375, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 58.58387762958139, "upper": 61.36729424541861, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "icelandic-knowledge/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.151941+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.2.0.dev0", "additional_details": {"dataset": "icelandic-knowledge", "languages": "[\"is\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.11312960918675412, \"accuracy\": 0.337890625}, {\"mcc\": 0.11051579506459125, \"accuracy\": 0.333984375}, {\"mcc\": 0.055407687797233526, \"accuracy\": 0.296875}, {\"mcc\": 0.1539894227361898, \"accuracy\": 0.357421875}, {\"mcc\": 0.10806902366254731, \"accuracy\": 0.3232421875}, {\"mcc\": 0.14831469056952115, \"accuracy\": 0.359375}, {\"mcc\": 0.08882752696588136, \"accuracy\": 0.31640625}, {\"mcc\": 0.04601262202998603, \"accuracy\": 0.2744140625}, {\"mcc\": 0.08651564672273394, \"accuracy\": 0.31640625}, {\"mcc\": 0.13490460555810094, \"accuracy\": 0.3525390625}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "icelandic-knowledge", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 10.456866302935394, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 8.211013349408407, "upper": 12.70271925646238, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "icelandic-knowledge", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 32.685546875, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 30.99387701626783, "upper": 34.37721673373217, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "idioms-no/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.151971+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.1.dev0", "additional_details": {"dataset": "idioms-no", "languages": "[\"nb\", \"nn\", \"no\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.53.0", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": -0.027172222327777114, \"accuracy\": 0.24169921875}, {\"mcc\": -0.013127248205685315, \"accuracy\": 0.24169921875}, {\"mcc\": -0.0015868129959337788, \"accuracy\": 0.2548828125}, {\"mcc\": -0.015023922642812257, \"accuracy\": 0.2412109375}, {\"mcc\": -0.023191697430843462, \"accuracy\": 0.23583984375}, {\"mcc\": -0.006030716210216353, \"accuracy\": 0.251953125}, {\"mcc\": 0.006880378843192363, \"accuracy\": 0.255859375}, {\"mcc\": -0.025612828633491614, \"accuracy\": 0.232421875}, {\"mcc\": 0.001128498978295545, \"accuracy\": 0.25341796875}, {\"mcc\": -0.020579930725785935, \"accuracy\": 0.236328125}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "idioms-no", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": -1.2431650135105794, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": -1.9868808711179191, "upper": -0.4994491559032397, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "idioms-no", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 24.453125, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 23.911971992097207, "upper": 24.994278007902793, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "life-in-the-uk/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152001+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.1.dev0", "additional_details": {"dataset": "life-in-the-uk", "languages": "[\"en\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.53.0", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.7720395431833751, \"accuracy\": 0.833984375}, {\"mcc\": 0.8143130105797286, \"accuracy\": 0.86328125}, {\"mcc\": 0.7653599310493382, \"accuracy\": 0.828125}, {\"mcc\": 0.7893225217713508, \"accuracy\": 0.84375}, {\"mcc\": 0.7902834908902187, \"accuracy\": 0.845703125}, {\"mcc\": 0.7733981240157669, \"accuracy\": 0.833984375}, {\"mcc\": 0.8145386597862013, \"accuracy\": 0.86328125}, {\"mcc\": 0.7411689487766318, \"accuracy\": 0.810546875}, {\"mcc\": 0.8222126802906771, \"accuracy\": 0.869140625}, {\"mcc\": 0.771603206370842, \"accuracy\": 0.833984375}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "life-in-the-uk", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 78.54240116714129, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 76.94870774265362, "upper": 80.13609459162896, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "life-in-the-uk", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 84.2578125, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 83.12048779395552, "upper": 85.39513720604448, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mlqa-es/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152031+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.8.4"}}, "eval_library": {"name": "euroeval", "version": "15.7.1.dev0", "additional_details": {"dataset": "mlqa-es", "languages": "[\"es\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.6.0", "vllm_version": "0.8.4", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 56.330966287911245, \"em\": 24.422187981510014}, {\"f1\": 59.08672890027865, \"em\": 27.636643571978446}, {\"f1\": 60.59543661984999, \"em\": 32.210031347962385}, {\"f1\": 57.252873426799184, \"em\": 25.641025641025642}, {\"f1\": 57.05460009866829, \"em\": 24.088748019017434}, {\"f1\": 58.19441221044903, \"em\": 29.738058551617872}, {\"f1\": 50.68426371021068, \"em\": 17.069368667186282}, {\"f1\": 61.29365372087367, \"em\": 33.93987341772152}, {\"f1\": 58.10877325279971, \"em\": 27.6326207442597}, {\"f1\": 56.38627705901886, \"em\": 24.74864655839134}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "mlqa-es", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 57.498798528685924, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 55.689822746767085, "upper": 59.30777431060476, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "mlqa-es", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 26.712720450067064, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 23.765927763697146, "upper": 29.65951313643698, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mmlu-es/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152061+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.8.4"}}, "eval_library": {"name": "euroeval", "version": "15.7.1.dev0", "additional_details": {"dataset": "mmlu-es", "languages": "[\"es\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.6.0", "vllm_version": "0.8.4", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.4526138182192999, \"accuracy\": 0.58837890625}, {\"mcc\": 0.44381710746057884, \"accuracy\": 0.58154296875}, {\"mcc\": 0.4368638072612208, \"accuracy\": 0.576171875}, {\"mcc\": 0.4437419160075709, \"accuracy\": 0.5810546875}, {\"mcc\": 0.43964199933708303, \"accuracy\": 0.578125}, {\"mcc\": 0.47172405221984715, \"accuracy\": 0.599609375}, {\"mcc\": 0.4378383382150436, \"accuracy\": 0.572265625}, {\"mcc\": 0.42793481347054224, \"accuracy\": 0.56689453125}, {\"mcc\": 0.4524452888232663, \"accuracy\": 0.5849609375}, {\"mcc\": 0.4178861259594593, \"accuracy\": 0.56201171875}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "mmlu-es", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 44.24507266973913, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 43.335518731543, "upper": 45.15462660793526, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "mmlu-es", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 57.91015625, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 57.24129858834071, "upper": 58.57901391165929, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mmlu-fr/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152091+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.3.1", "additional_details": {"dataset": "mmlu-fr", "languages": "[\"fr\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.4422626712169452, \"accuracy\": 0.578125}, {\"mcc\": 0.4512123600606908, \"accuracy\": 0.587890625}, {\"mcc\": 0.40673734486091273, \"accuracy\": 0.55029296875}, {\"mcc\": 0.4471593272323532, \"accuracy\": 0.58203125}, {\"mcc\": 0.4311336653083763, \"accuracy\": 0.568359375}, {\"mcc\": 0.4441545054031431, \"accuracy\": 0.5791015625}, {\"mcc\": 0.4233265296568955, \"accuracy\": 0.5634765625}, {\"mcc\": 0.4171155707809235, \"accuracy\": 0.5595703125}, {\"mcc\": 0.44977895685628216, \"accuracy\": 0.5849609375}, {\"mcc\": 0.4612525197577882, \"accuracy\": 0.58984375}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "mmlu-fr", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 43.74133451134311, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 42.674486954195224, "upper": 44.808182068491, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "mmlu-fr", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 57.4365234375, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 56.614484906883334, "upper": 58.258561968116666, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mmlu-it/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152120+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.3.1", "additional_details": {"dataset": "mmlu-it", "languages": "[\"it\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.4709641639127738, \"accuracy\": 0.60205078125}, {\"mcc\": 0.4222137667504461, \"accuracy\": 0.564453125}, {\"mcc\": 0.41358199596217704, \"accuracy\": 0.55859375}, {\"mcc\": 0.44187574429282717, \"accuracy\": 0.5810546875}, {\"mcc\": 0.4322820096533369, \"accuracy\": 0.57080078125}, {\"mcc\": 0.4517432887502547, \"accuracy\": 0.58740234375}, {\"mcc\": 0.41579597858455236, \"accuracy\": 0.55908203125}, {\"mcc\": 0.41503465739380463, \"accuracy\": 0.55810546875}, {\"mcc\": 0.42730057131819493, \"accuracy\": 0.56884765625}, {\"mcc\": 0.4235309589129774, \"accuracy\": 0.5673828125}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "mmlu-it", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 43.143231355313446, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 41.99634076555911, "upper": 44.29012194506778, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "mmlu-it", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 57.177734375, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 56.2888451788161, "upper": 58.0666235711839, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mmlu-pt/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152149+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.10.0"}}, "eval_library": {"name": "euroeval", "version": "15.16.0", "additional_details": {"dataset": "mmlu-pt", "languages": "[\"pt\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.55.2", "torch_version": "2.7.1", "vllm_version": "0.10.0", "xgrammar_version": "0.1.21", "litellm_version": null, "raw_results": "[{\"mcc\": 0.43545236252721947, \"accuracy\": 0.57421875}, {\"mcc\": 0.44704381070004695, \"accuracy\": 0.583984375}, {\"mcc\": 0.4452126921103507, \"accuracy\": 0.58251953125}, {\"mcc\": 0.3975828368341457, \"accuracy\": 0.5439453125}, {\"mcc\": 0.4476573602451816, \"accuracy\": 0.58251953125}, {\"mcc\": 0.4299387681261658, \"accuracy\": 0.5703125}, {\"mcc\": 0.4460792093889382, \"accuracy\": 0.58349609375}, {\"mcc\": 0.45390247097888764, \"accuracy\": 0.58837890625}, {\"mcc\": 0.4376696191619618, \"accuracy\": 0.576171875}, {\"mcc\": 0.4586284814162777, \"accuracy\": 0.591796875}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "mmlu-pt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 43.99167611489176, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 42.93030300386392, "upper": 45.0530492259196, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "mmlu-pt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 57.7734375, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 56.93658373002978, "upper": 58.61029126997022, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "multi-wiki-qa-pt/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152180+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.10.0"}}, "eval_library": {"name": "euroeval", "version": "15.16.0", "additional_details": {"dataset": "multi-wiki-qa-pt", "languages": "[\"pt\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.55.2", "torch_version": "2.7.1", "vllm_version": "0.10.0", "xgrammar_version": "0.1.21", "litellm_version": null, "raw_results": "[{\"f1\": 71.92728286247096, \"em\": 45.72025052192067}, {\"f1\": 72.58644337008569, \"em\": 46.398305084745765}, {\"f1\": 70.93199206739419, \"em\": 46.47302904564315}, {\"f1\": 69.86150190042177, \"em\": 42.973523421588595}, {\"f1\": 68.11338452310633, \"em\": 42.68041237113402}, {\"f1\": 69.92552609503387, \"em\": 45.790554414784395}, {\"f1\": 70.21220627596111, \"em\": 43.81551362683438}, {\"f1\": 73.37222461987497, \"em\": 51.88284518828452}, {\"f1\": 70.13839307701387, \"em\": 45.22821576763486}, {\"f1\": 70.61856714177289, \"em\": 45.66115702479339}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "multi-wiki-qa-pt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 70.76875219331357, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 69.82727930117127, "upper": 71.71022508545587, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "multi-wiki-qa-pt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 45.66238064673638, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 44.06693317492055, "upper": 47.25782811855221, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "multinerd-it/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152211+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.3.1", "additional_details": {"dataset": "multinerd-it", "languages": "[\"it\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.6988099619678567, \"micro_f1\": 0.4665720369056068}, {\"micro_f1_no_misc\": 0.7172719841177156, \"micro_f1\": 0.5501549625822058}, {\"micro_f1_no_misc\": 0.6381601756616202, \"micro_f1\": 0.4672470386756101}, {\"micro_f1_no_misc\": 0.6644043146285298, \"micro_f1\": 0.5135626729932781}, {\"micro_f1_no_misc\": 0.7210493441599001, \"micro_f1\": 0.571147379644058}, {\"micro_f1_no_misc\": 0.6841069568237064, \"micro_f1\": 0.5300022990267452}, {\"micro_f1_no_misc\": 0.6954403063000348, \"micro_f1\": 0.4853850477796514}, {\"micro_f1_no_misc\": 0.7095516569200782, \"micro_f1\": 0.5694733194733195}, {\"micro_f1_no_misc\": 0.7009105766985757, \"micro_f1\": 0.48808747918024475}, {\"micro_f1_no_misc\": 0.70376271601912, \"micro_f1\": 0.4919462095463277}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "multinerd-it", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 69.33467993297137, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 67.76518622952592, "upper": 70.90417363641681, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "multinerd-it", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 51.33578445807048, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 48.86394463886245, "upper": 53.80762427727851, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "nor-common-sense-qa/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152243+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.2.0.dev0", "additional_details": {"dataset": "nor-common-sense-qa", "languages": "[\"nb\", \"nn\", \"no\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.5376327164077473, \"accuracy\": 0.6263219741480611}, {\"mcc\": 0.49895403133694805, \"accuracy\": 0.5945945945945946}, {\"mcc\": 0.5259464484166969, \"accuracy\": 0.6133960047003525}, {\"mcc\": 0.5128169764515605, \"accuracy\": 0.6063454759106933}, {\"mcc\": 0.5180720756367996, \"accuracy\": 0.6110458284371327}, {\"mcc\": 0.4751544382243017, \"accuracy\": 0.5746180963572268}, {\"mcc\": 0.5646219570341957, \"accuracy\": 0.6474735605170387}, {\"mcc\": 0.47574150387227515, \"accuracy\": 0.5734430082256169}, {\"mcc\": 0.4547377383204681, \"accuracy\": 0.554641598119859}, {\"mcc\": 0.4763932131302142, \"accuracy\": 0.5769682726204466}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "nor-common-sense-qa", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 50.40071098831207, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 48.29290681135438, "upper": 52.50851516526976, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "nor-common-sense-qa", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 59.78848413631022, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 58.0341712382992, "upper": 61.54279703432123, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "nrk-quiz-qa/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152273+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.2.0.dev0", "additional_details": {"dataset": "nrk-quiz-qa", "languages": "[\"nb\", \"nn\", \"no\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.3092981967499771, \"accuracy\": 0.48828125}, {\"mcc\": 0.3217234850554586, \"accuracy\": 0.501953125}, {\"mcc\": 0.319923849647568, \"accuracy\": 0.5009765625}, {\"mcc\": 0.346548468959356, \"accuracy\": 0.51611328125}, {\"mcc\": 0.33273898292227555, \"accuracy\": 0.50439453125}, {\"mcc\": 0.3321238819335516, \"accuracy\": 0.50390625}, {\"mcc\": 0.32159563536732627, \"accuracy\": 0.50048828125}, {\"mcc\": 0.3150371512235765, \"accuracy\": 0.4912109375}, {\"mcc\": 0.29041892616380083, \"accuracy\": 0.47216796875}, {\"mcc\": 0.32400104841214283, \"accuracy\": 0.50048828125}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "nrk-quiz-qa", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 32.13409626435033, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 31.202818094721806, "upper": 33.06537443397886, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "nrk-quiz-qa", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 49.7998046875, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 49.06977250667999, "upper": 50.52983686832001, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-es/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152303+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.8.4"}}, "eval_library": {"name": "euroeval", "version": "15.7.1.dev0", "additional_details": {"dataset": "scala-es", "languages": "[\"es\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.6.0", "vllm_version": "0.8.4", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.23836590542303746, \"macro_f1\": 0.6098683128823913}, {\"mcc\": 0.24543605302575622, \"macro_f1\": 0.6225563440104962}, {\"mcc\": 0.18425349139463645, \"macro_f1\": 0.591330200982052}, {\"mcc\": 0.22144728986556636, \"macro_f1\": 0.6059368572517834}, {\"mcc\": 0.17493678441956517, \"macro_f1\": 0.5864309099814675}, {\"mcc\": 0.21265157408919408, \"macro_f1\": 0.5771307989606479}, {\"mcc\": 0.24788924422352113, \"macro_f1\": 0.5986758339699516}, {\"mcc\": 0.253826689591681, \"macro_f1\": 0.5777392498428243}, {\"mcc\": 0.18730607760337228, \"macro_f1\": 0.5913231979556972}, {\"mcc\": 0.21130125800804841, \"macro_f1\": 0.5761817430664876}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-es", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 21.774143676443785, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 20.001152522700522, "upper": 23.547134830187048, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-es", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 59.37173448903798, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 58.409563317470045, "upper": 60.33390566060592, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-fi/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152334+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.10.0"}}, "eval_library": {"name": "euroeval", "version": "15.16.0", "additional_details": {"dataset": "scala-fi", "languages": "[\"fi\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.55.2", "torch_version": "2.7.1", "vllm_version": "0.10.0", "xgrammar_version": "0.1.21", "litellm_version": null, "raw_results": "[{\"mcc\": 0.07476392588705677, \"macro_f1\": 0.518826794279069}, {\"mcc\": 0.08797300739890032, \"macro_f1\": 0.5317887778050837}, {\"mcc\": 0.019550285338702816, \"macro_f1\": 0.4654872067308286}, {\"mcc\": 0.05575382346778318, \"macro_f1\": 0.4946858877423659}, {\"mcc\": 0.023123187207654005, \"macro_f1\": 0.4205598775513504}, {\"mcc\": 0.02987723807823196, \"macro_f1\": 0.49211947536647194}, {\"mcc\": 0.0483984031282732, \"macro_f1\": 0.5062967683553239}, {\"mcc\": 0.004928000033831756, \"macro_f1\": 0.45378254635597626}, {\"mcc\": 0.06868998011872962, \"macro_f1\": 0.5136747255536518}, {\"mcc\": 0.04177354901769915, \"macro_f1\": 0.47904550013827946}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-fi", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 4.548313996768628, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 2.8968143011255183, "upper": 6.1998136924117375, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-fi", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 48.762675598784014, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 46.67323400406069, "upper": 50.85211719350734, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-fr/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152365+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.3.1", "additional_details": {"dataset": "scala-fr", "languages": "[\"fr\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.28238099744816103, \"macro_f1\": 0.6349088147693032}, {\"mcc\": 0.27627935093451284, \"macro_f1\": 0.630403899238863}, {\"mcc\": 0.3115755855660189, \"macro_f1\": 0.6440314050987033}, {\"mcc\": 0.2352362502515704, \"macro_f1\": 0.6166991273639506}, {\"mcc\": 0.33652018131946526, \"macro_f1\": 0.65439386948663}, {\"mcc\": 0.29545116307900093, \"macro_f1\": 0.6417758870471493}, {\"mcc\": 0.27232606215635885, \"macro_f1\": 0.6042303503039247}, {\"mcc\": 0.29348255977392884, \"macro_f1\": 0.6420511759780853}, {\"mcc\": 0.32332882253723333, \"macro_f1\": 0.6616074589873717}, {\"mcc\": 0.3087440606263901, \"macro_f1\": 0.6352603661026648}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-fr", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 29.353250336926408, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 27.556098753296023, "upper": 31.150401920556792, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-fr", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 63.65362354376647, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 62.61226464481908, "upper": 64.69498244271387, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-it/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152395+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.3.1", "additional_details": {"dataset": "scala-it", "languages": "[\"it\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.16574795258459035, \"macro_f1\": 0.5826730995910225}, {\"mcc\": 0.21752131356905638, \"macro_f1\": 0.6052811942766234}, {\"mcc\": 0.19419898609445935, \"macro_f1\": 0.5784115199115372}, {\"mcc\": 0.1883162742575789, \"macro_f1\": 0.581817029039225}, {\"mcc\": 0.13788840062244528, \"macro_f1\": 0.5586550435865505}, {\"mcc\": 0.16656003917109302, \"macro_f1\": 0.5757899258967178}, {\"mcc\": 0.2220151838717295, \"macro_f1\": 0.6087954280031223}, {\"mcc\": 0.21096867346087242, \"macro_f1\": 0.6044359080220432}, {\"mcc\": 0.1927907976606629, \"macro_f1\": 0.568232677802288}, {\"mcc\": 0.19743270351649203, \"macro_f1\": 0.5835340615452593}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-it", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 18.9344032480898, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 17.313598008310883, "upper": 20.55520848786872, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-it", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 58.476258876743906, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 57.44824594218894, "upper": 59.50427181129887, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-pt/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152425+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.10.0"}}, "eval_library": {"name": "euroeval", "version": "15.16.0", "additional_details": {"dataset": "scala-pt", "languages": "[\"pt\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.55.2", "torch_version": "2.7.1", "vllm_version": "0.10.0", "xgrammar_version": "0.1.21", "litellm_version": null, "raw_results": "[{\"mcc\": 0.12426771305689648, \"macro_f1\": 0.5580479299321822}, {\"mcc\": 0.1795943798380739, \"macro_f1\": 0.5560961788942651}, {\"mcc\": 0.1535690987083791, \"macro_f1\": 0.565365025466893}, {\"mcc\": 0.17985562607428218, \"macro_f1\": 0.5672691609171396}, {\"mcc\": 0.17548076261901346, \"macro_f1\": 0.5829366363174193}, {\"mcc\": 0.144722385588081, \"macro_f1\": 0.571013032258529}, {\"mcc\": 0.08803953037625172, \"macro_f1\": 0.5140307845116757}, {\"mcc\": 0.18164841037270377, \"macro_f1\": 0.583552540495639}, {\"mcc\": 0.13769497396097946, \"macro_f1\": 0.5542622224013543}, {\"mcc\": 0.15168913713249912, \"macro_f1\": 0.5740542587402356}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-pt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 15.165620177271602, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 13.307721697162542, "upper": 17.023518657380663, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-pt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 56.26627769935333, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 55.030893266051486, "upper": 57.50166213265518, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scandisent-fi/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152455+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.10.0"}}, "eval_library": {"name": "euroeval", "version": "15.16.0", "additional_details": {"dataset": "scandisent-fi", "languages": "[\"fi\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.55.2", "torch_version": "2.7.1", "vllm_version": "0.10.0", "xgrammar_version": "0.1.21", "litellm_version": null, "raw_results": "[{\"mcc\": 0.8884638554573439, \"macro_f1\": 0.9424213566938994}, {\"mcc\": 0.8770621523517677, \"macro_f1\": 0.936465209070126}, {\"mcc\": 0.859780588150522, \"macro_f1\": 0.9273753296939213}, {\"mcc\": 0.8666801877419537, \"macro_f1\": 0.9304417366923163}, {\"mcc\": 0.8786347207156113, \"macro_f1\": 0.9369359240515576}, {\"mcc\": 0.8825390724974693, \"macro_f1\": 0.9394516814155915}, {\"mcc\": 0.852251169719772, \"macro_f1\": 0.9231947960805307}, {\"mcc\": 0.8799986264055817, \"macro_f1\": 0.938729229867107}, {\"mcc\": 0.8905203752261514, \"macro_f1\": 0.9436996671749601}, {\"mcc\": 0.8950446198518326, \"macro_f1\": 0.9466205386296405}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scandisent-fi", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 87.70975368118006, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 86.85851419353959, "upper": 88.56099316882053, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scandisent-fi", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 93.65335469369649, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 93.1912972103302, "upper": 94.11541217706277, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "sentiment-headlines-es/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152485+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.8.4"}}, "eval_library": {"name": "euroeval", "version": "15.7.1.dev0", "additional_details": {"dataset": "sentiment-headlines-es", "languages": "[\"es\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.6.0", "vllm_version": "0.8.4", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.4580861172600679, \"macro_f1\": 0.618896024413082}, {\"mcc\": 0.4393179771804917, \"macro_f1\": 0.5792481320502056}, {\"mcc\": 0.4806802020062777, \"macro_f1\": 0.6210738044082452}, {\"mcc\": 0.43637716416522976, \"macro_f1\": 0.621619658860394}, {\"mcc\": 0.4911432743826835, \"macro_f1\": 0.6561595817989966}, {\"mcc\": 0.4334733660783987, \"macro_f1\": 0.5748430765670648}, {\"mcc\": 0.4696784145031777, \"macro_f1\": 0.6342170711807092}, {\"mcc\": 0.4448084525505321, \"macro_f1\": 0.6053599829041089}, {\"mcc\": 0.43002902621592437, \"macro_f1\": 0.5889894653892415}, {\"mcc\": 0.4221641639807315, \"macro_f1\": 0.5883344261465787}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "sentiment-headlines-es", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 45.05758158323515, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 43.61775644418361, "upper": 46.497406722286684, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "sentiment-headlines-es", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 60.887412237186275, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 59.26649520603658, "upper": 62.50832926833597, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "sentipolc16/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152528+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.3.1", "additional_details": {"dataset": "sentipolc16", "languages": "[\"it\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.5727895878236514, \"macro_f1\": 0.6968596699747435}, {\"mcc\": 0.5156634425104549, \"macro_f1\": 0.6473581638595336}, {\"mcc\": 0.5526954018300891, \"macro_f1\": 0.6533218827955669}, {\"mcc\": 0.5399135418642895, \"macro_f1\": 0.6696183833249112}, {\"mcc\": 0.5216465933801391, \"macro_f1\": 0.6642270151078231}, {\"mcc\": 0.5681369568318695, \"macro_f1\": 0.6651361126870711}, {\"mcc\": 0.5012693851807382, \"macro_f1\": 0.6247073822651663}, {\"mcc\": 0.5974670507760569, \"macro_f1\": 0.7141037547551813}, {\"mcc\": 0.5214553867851467, \"macro_f1\": 0.6225008809523622}, {\"mcc\": 0.5356949536813522, \"macro_f1\": 0.6708570797506302}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "sentipolc16", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 54.26732300663788, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 52.413578046437124, "upper": 56.12106796683864, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "sentipolc16", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 66.28690325472989, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 64.51996075726163, "upper": 68.05384575219816, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "speed/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152565+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.3.1", "additional_details": {"dataset": "speed", "languages": "[\"ab\", \"aa\", \"af\", \"sq\", \"am\", \"ar\", \"an\", \"hy\", \"as\", \"av\", \"ae\", \"ay\", \"az\", \"bm\", \"ba\", \"eu\", \"be\", \"bn\", \"bi\", \"bs\", \"br\", \"bg\", \"my\", \"ca\", \"ch\", \"ce\", \"ny\", \"zh\", \"cu\", \"cv\", \"kw\", \"co\", \"cr\", \"hr\", \"cs\", \"da\", \"dv\", \"nl\", \"dz\", \"en\", \"eo\", \"et\", \"ee\", \"fo\", \"fj\", \"fi\", \"fr\", \"fy\", \"ff\", \"gd\", \"gl\", \"lg\", \"ka\", \"de\", \"el\", \"kl\", \"gn\", \"gu\", \"ht\", \"ha\", \"he\", \"hz\", \"hi\", \"ho\", \"hu\", \"is\", \"io\", \"ig\", \"id\", \"ia\", \"ie\", \"iu\", \"ik\", \"ga\", \"it\", \"ja\", \"kn\", \"kr\", \"ks\", \"kk\", \"km\", \"ki\", \"rw\", \"ky\", \"kv\", \"kg\", \"ko\", \"kj\", \"ku\", \"lo\", \"la\", \"lv\", \"li\", \"ln\", \"lt\", \"lu\", \"lb\", \"mk\", \"mg\", \"ms\", \"ml\", \"mt\", \"gv\", \"mi\", \"mr\", \"mh\", \"mn\", \"na\", \"nv\", \"nd\", \"nr\", \"ng\", \"ne\", \"no\", \"nb\", \"nn\", \"ii\", \"oc\", \"oj\", \"or\", \"om\", \"os\", \"pi\", \"ps\", \"fa\", \"pl\", \"pt\", \"pa\", \"qu\", \"ro\", \"rm\", \"rn\", \"ru\", \"se\", \"sm\", \"sg\", \"sa\", \"sc\", \"sr\", \"sn\", \"sd\", \"si\", \"sk\", \"sl\", \"so\", \"st\", \"es\", \"su\", \"sw\", \"ss\", \"sv\", \"tl\", \"ty\", \"tg\", \"ta\", \"tt\", \"te\", \"th\", \"bo\", \"ti\", \"to\", \"ts\", \"tn\", \"tr\", \"tk\", \"tw\", \"ug\", \"uk\", \"ur\", \"uz\", \"ve\", \"vi\", \"vo\", \"wa\", \"cy\", \"wo\", \"xh\", \"yi\", \"yo\", \"za\", \"zu\"]", "task": "speed", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_speed\": 386.95, \"test_speed_short\": 43.92}, {\"test_speed\": 759.99, \"test_speed_short\": 82.8}, {\"test_speed\": 1143.62, \"test_speed_short\": 161.53}, {\"test_speed\": 1511.78, \"test_speed_short\": 199.79999999999998}, {\"test_speed\": 1895.4, \"test_speed_short\": 239.07999999999998}, {\"test_speed\": 2264.98, \"test_speed_short\": 312.93}, {\"test_speed\": 2661.22, \"test_speed_short\": 354.56}, {\"test_speed\": 3001.35, \"test_speed_short\": 390.5}, {\"test_speed\": 3319.06, \"test_speed_short\": 429.78}, {\"test_speed\": 3694.2699999999995, \"test_speed_short\": 471.75}]"}}, "evaluation_results": [{"evaluation_name": "test_speed", "source_data": {"dataset_name": "speed", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false}, "score_details": {"score": 2063.862, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 1372.3755181263582, "upper": 2755.348481873642, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_speed_short", "source_data": {"dataset_name": "speed", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false}, "score_details": {"score": 268.66499999999996, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 177.7754722921917, "upper": 359.55452770780823, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "squad-it/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152603+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.3.1", "additional_details": {"dataset": "squad-it", "languages": "[\"it\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 64.43562694133357, \"em\": 42.121212121212125}, {\"f1\": 63.268064092634276, \"em\": 36.770280515542076}, {\"f1\": 66.23481318579444, \"em\": 46.85314685314685}, {\"f1\": 65.62445529434146, \"em\": 42.23744292237443}, {\"f1\": 63.96926231418031, \"em\": 39.01310717039321}, {\"f1\": 64.040413965041, \"em\": 41.603053435114504}, {\"f1\": 64.47850903237193, \"em\": 40.24960998439938}, {\"f1\": 65.21996608496828, \"em\": 40.801886792452834}, {\"f1\": 67.48300797088747, \"em\": 47.29102167182663}, {\"f1\": 61.983886565793405, \"em\": 36.111111111111114}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "squad-it", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 64.67380054473462, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 63.71061351345264, "upper": 65.6369875760166, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "squad-it", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 41.30518725775731, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 39.01946548009178, "upper": 43.59090903542284, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "sst2-pt/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152634+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.10.0"}}, "eval_library": {"name": "euroeval", "version": "15.16.0", "additional_details": {"dataset": "sst2-pt", "languages": "[\"pt\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.55.2", "torch_version": "2.7.1", "vllm_version": "0.10.0", "xgrammar_version": "0.1.21", "litellm_version": null, "raw_results": "[{\"mcc\": 0.751497873364583, \"macro_f1\": 0.8734438819272112}, {\"mcc\": 0.7955322964225093, \"macro_f1\": 0.897271268057785}, {\"mcc\": 0.7726853151253263, \"macro_f1\": 0.8858319438672448}, {\"mcc\": 0.8162451446124735, \"macro_f1\": 0.9057341872166014}, {\"mcc\": 0.7578691578186681, \"macro_f1\": 0.8789044022278172}, {\"mcc\": 0.7714800103931965, \"macro_f1\": 0.885698584970463}, {\"mcc\": 0.7734294108448082, \"macro_f1\": 0.8854682213460839}, {\"mcc\": 0.7584756465748567, \"macro_f1\": 0.8792325695046099}, {\"mcc\": 0.7840120532940416, \"macro_f1\": 0.8919290373616634}, {\"mcc\": 0.7824299321119988, \"macro_f1\": 0.8890691208896558}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "sst2-pt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 77.63656840562462, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 76.43550217891267, "upper": 78.83763463233656, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "sst2-pt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 88.72583217369137, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 88.14168403565736, "upper": 89.30998031172538, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "turku-ner-fi/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152665+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.10.0"}}, "eval_library": {"name": "euroeval", "version": "15.16.0", "additional_details": {"dataset": "turku-ner-fi", "languages": "[\"fi\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.55.2", "torch_version": "2.7.1", "vllm_version": "0.10.0", "xgrammar_version": "0.1.21", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.5035799522673031, \"micro_f1\": 0.31568659390780257}, {\"micro_f1_no_misc\": 0.4463687150837989, \"micro_f1\": 0.2959285004965243}, {\"micro_f1_no_misc\": 0.45053360253821745, \"micro_f1\": 0.2893890675241158}, {\"micro_f1_no_misc\": 0.4798301486199576, \"micro_f1\": 0.2756137479541735}, {\"micro_f1_no_misc\": 0.4324002382370459, \"micro_f1\": 0.2781410143134829}, {\"micro_f1_no_misc\": 0.46766169154228854, \"micro_f1\": 0.29717242653853265}, {\"micro_f1_no_misc\": 0.4539772727272728, \"micro_f1\": 0.25856320096999097}, {\"micro_f1_no_misc\": 0.4504657070279424, \"micro_f1\": 0.2912416461484348}, {\"micro_f1_no_misc\": 0.4593381940549635, \"micro_f1\": 0.28794280142996426}, {\"micro_f1_no_misc\": 0.4615865084322298, \"micro_f1\": 0.25541795665634676}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "turku-ner-fi", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 46.0574203053102, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 44.832502383996705, "upper": 47.2823382266237, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "turku-ner-fi", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 28.450969559393684, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 27.32259379045252, "upper": 29.57934532833485, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "tydiqa-fi/CohereForAI/c4ai-command-r-v01/1781766554", "evaluation_timestamp": "2026-06-18T07:09:14.152696+00:00", "retrieved_timestamp": "1781766554", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "CohereForAI/c4ai-command-r-v01", "id": "CohereForAI/c4ai-command-r-v01", "additional_details": {"num_model_parameters": "34980831232", "max_sequence_length": "8192", "vocabulary_size": "256000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/CohereForAI/c4ai-command-r-v01"}, "inference_engine": {"name": "vllm", "version": "0.10.0"}}, "eval_library": {"name": "euroeval", "version": "15.16.0", "additional_details": {"dataset": "tydiqa-fi", "languages": "[\"fi\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.55.2", "torch_version": "2.7.1", "vllm_version": "0.10.0", "xgrammar_version": "0.1.21", "litellm_version": null, "raw_results": "[{\"f1\": 63.290300957193374, \"em\": 41.36363636363637}, {\"f1\": 57.43483514534089, \"em\": 38.36239575435936}, {\"f1\": 63.03666155067305, \"em\": 45.53224553224553}, {\"f1\": 59.86755461683524, \"em\": 39.42161339421613}, {\"f1\": 56.306780906196536, \"em\": 34.6183500385505}, {\"f1\": 59.68241474435629, \"em\": 38.70229007633588}, {\"f1\": 54.569876123897785, \"em\": 35.569422776911075}, {\"f1\": 60.743223581935524, \"em\": 42.45283018867924}, {\"f1\": 57.75649948450771, \"em\": 38.1578947368421}, {\"f1\": 59.58723681199048, \"em\": 39.04320987654321}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "tydiqa-fi", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 59.227538392292686, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 57.50317079472812, "upper": 60.95190598985725, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "tydiqa-fi", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 39.32238887383194, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 37.34621642829647, "upper": 41.29856131936741, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
Xet Storage Details
- Size:
- 109 kB
- Xet hash:
- 130fa389f017a5cea47c3cfa90c9a88f7b355be2222aea2c709733585d0c7003
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.