| {"schema_version": "0.2.1", "evaluation_id": "allocine/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004029+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "allocine", "languages": "[\"fr\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.9438337727131021, \"macro_f1\": 0.9716484313837811}, {\"mcc\": 0.9424380393256419, \"macro_f1\": 0.9711798556655344}, {\"mcc\": 0.9527264149090116, \"macro_f1\": 0.9763546798029556}, {\"mcc\": 0.9599627603259993, \"macro_f1\": 0.9799699195748188}, {\"mcc\": 0.9387001442643925, \"macro_f1\": 0.969205322908052}, {\"mcc\": 0.9399016513601032, \"macro_f1\": 0.9697138250320807}, {\"mcc\": 0.9648049493040042, \"macro_f1\": 0.982402474652002}, {\"mcc\": 0.947203945955081, \"macro_f1\": 0.9736019729775405}, {\"mcc\": 0.949941617593551, \"macro_f1\": 0.9749686952916521}, {\"mcc\": 0.944242303503251, \"macro_f1\": 0.9720536261267569}]"}}, "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": 94.83755599254138, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 94.30464669067236, "upper": 95.37046529441041, "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": 97.41098803415173, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 97.14050978528321, "upper": 97.68146628302024, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "angry-tweets/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004065+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "angry-tweets", "languages": "[\"da\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.5163873067896068, \"macro_f1\": 0.6727034973934182}, {\"mcc\": 0.46100945391586834, \"macro_f1\": 0.6097595941263866}, {\"mcc\": 0.5495200434428005, \"macro_f1\": 0.702988654336354}, {\"mcc\": 0.5122720590283291, \"macro_f1\": 0.6772886350538104}, {\"mcc\": 0.5262465839325178, \"macro_f1\": 0.6869812739509235}, {\"mcc\": 0.5495706765830698, \"macro_f1\": 0.7047587019203316}, {\"mcc\": 0.4838030407058269, \"macro_f1\": 0.6456275558080873}, {\"mcc\": 0.515165816344112, \"macro_f1\": 0.6715256676909039}, {\"mcc\": 0.5590988210354959, \"macro_f1\": 0.7101652335839083}, {\"mcc\": 0.46001857147055947, \"macro_f1\": 0.6248382658092771}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "angry-tweets", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 51.33092373248187, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 49.12986413762949, "upper": 53.53198332733425, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "angry-tweets", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 67.06637079673402, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 64.94742548449871, "upper": 69.18531610896933, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "conll-en/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004098+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "conll-en", "languages": "[\"en\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.6815307106871047, \"micro_f1\": 0.6024988431281814}, {\"micro_f1_no_misc\": 0.6739268344258829, \"micro_f1\": 0.6355576294913672}, {\"micro_f1_no_misc\": 0.736010390734928, \"micro_f1\": 0.6972972972972973}, {\"micro_f1_no_misc\": 0.6498746047323083, \"micro_f1\": 0.5979441997063143}, {\"micro_f1_no_misc\": 0.7123258979997904, \"micro_f1\": 0.6718557190317987}, {\"micro_f1_no_misc\": 0.6620751947612058, \"micro_f1\": 0.6147084676237914}, {\"micro_f1_no_misc\": 0.617948717948718, \"micro_f1\": 0.6308294766820933}, {\"micro_f1_no_misc\": 0.6933737548722391, \"micro_f1\": 0.6351447979978547}, {\"micro_f1_no_misc\": 0.7048969072164949, \"micro_f1\": 0.6711277307616611}, {\"micro_f1_no_misc\": 0.7009326424870468, \"micro_f1\": 0.673249710879815}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "conll-en", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 68.32895655865718, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 66.2190610840619, "upper": 70.43885203325246, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "conll-en", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 64.30213872600174, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 62.213202776446096, "upper": 66.39107467555739, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "conll-es/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004130+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "conll-es", "languages": "[\"es\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.618066561014263, \"micro_f1\": 0.5669543773119605}, {\"micro_f1_no_misc\": 0.6419207948116462, \"micro_f1\": 0.5820030743762563}, {\"micro_f1_no_misc\": 0.6657840541335687, \"micro_f1\": 0.600273190115485}, {\"micro_f1_no_misc\": 0.6486636199972303, \"micro_f1\": 0.5863580177548039}, {\"micro_f1_no_misc\": 0.5577794010226443, \"micro_f1\": 0.5289818548387097}, {\"micro_f1_no_misc\": 0.5709480122324159, \"micro_f1\": 0.5618370148508673}, {\"micro_f1_no_misc\": 0.6130520764667106, \"micro_f1\": 0.5764345159877354}, {\"micro_f1_no_misc\": 0.6136487221315934, \"micro_f1\": 0.5576628578159971}, {\"micro_f1_no_misc\": 0.6663078579117331, \"micro_f1\": 0.6086260153300538}, {\"micro_f1_no_misc\": 0.6406949911768698, \"micro_f1\": 0.6014821898159216}]"}}, "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": 62.36866090898676, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 60.08620329918247, "upper": 64.65111851879105, "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": 57.70613108197791, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 56.207075258777074, "upper": 59.20518690517874, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "conll-nl/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004162+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "conll-nl", "languages": "[\"nl\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.6608410704533042, \"micro_f1\": 0.5}, {\"micro_f1_no_misc\": 0.661498708010336, \"micro_f1\": 0.5877957658779577}, {\"micro_f1_no_misc\": 0.6871101871101871, \"micro_f1\": 0.5809786354238456}, {\"micro_f1_no_misc\": 0.5721362229102167, \"micro_f1\": 0.5418634607127523}, {\"micro_f1_no_misc\": 0.6565315315315315, \"micro_f1\": 0.5326352530541012}, {\"micro_f1_no_misc\": 0.6964187327823692, \"micro_f1\": 0.5609408410548825}, {\"micro_f1_no_misc\": 0.63884430176565, \"micro_f1\": 0.5921745673438675}, {\"micro_f1_no_misc\": 0.5918738629472409, \"micro_f1\": 0.502498215560314}, {\"micro_f1_no_misc\": 0.6712158808933003, \"micro_f1\": 0.510314875135722}, {\"micro_f1_no_misc\": 0.663271801400382, \"micro_f1\": 0.5656474820143885}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "conll-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 64.99742299804518, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 62.55144319819486, "upper": 67.4434027978955, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "conll-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 54.74849096177833, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 52.565218976735636, "upper": 56.931762946821024, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "danish-citizen-tests/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004194+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "danish-citizen-tests", "languages": "[\"da\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.5358860242909477, \"accuracy\": 0.6838095238095238}, {\"mcc\": 0.5354185819083631, \"accuracy\": 0.6876190476190476}, {\"mcc\": 0.5184399108411127, \"accuracy\": 0.6704761904761904}, {\"mcc\": 0.5804495579401014, \"accuracy\": 0.7161904761904762}, {\"mcc\": 0.64831779680805, \"accuracy\": 0.7638095238095238}, {\"mcc\": 0.6054866140992712, \"accuracy\": 0.7352380952380952}, {\"mcc\": 0.5323900451590958, \"accuracy\": 0.6857142857142857}, {\"mcc\": 0.5305016421711684, \"accuracy\": 0.6838095238095238}, {\"mcc\": 0.5071988465759365, \"accuracy\": 0.660952380952381}, {\"mcc\": 0.5834340489517981, \"accuracy\": 0.7238095238095238}]"}}, "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": 55.775230687458446, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 52.99420328627436, "upper": 58.55625808864253, "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": 70.11428571428571, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 68.11042100383798, "upper": 72.11815042473344, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "dansk/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004225+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "dansk", "languages": "[\"da\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.5642821410705352, \"micro_f1\": 0.40980961600516297}, {\"micro_f1_no_misc\": 0.5541176470588236, \"micro_f1\": 0.3804195804195804}, {\"micro_f1_no_misc\": 0.4996953077391834, \"micro_f1\": 0.40672934190994553}, {\"micro_f1_no_misc\": 0.5712927756653992, \"micro_f1\": 0.41074856046065256}, {\"micro_f1_no_misc\": 0.5267366316841579, \"micro_f1\": 0.3492236447834377}, {\"micro_f1_no_misc\": 0.5433231396534148, \"micro_f1\": 0.3804107424960505}, {\"micro_f1_no_misc\": 0.5482233502538072, \"micro_f1\": 0.4249554367201426}, {\"micro_f1_no_misc\": 0.5777777777777778, \"micro_f1\": 0.44622905027932963}, {\"micro_f1_no_misc\": 0.5712669683257918, \"micro_f1\": 0.41791044776119407}, {\"micro_f1_no_misc\": 0.5443526170798899, \"micro_f1\": 0.39238845144356954}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "dansk", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 55.0106835630878, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 53.542576856125905, "upper": 56.4787902700497, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "dansk", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 40.188248722790654, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 38.496431315619375, "upper": 41.88006612996193, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "danske-talemaader/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004257+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "danske-talemaader", "languages": "[\"da\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.2979038680307466, \"accuracy\": 0.4665841584158416}, {\"mcc\": 0.2800782731103287, \"accuracy\": 0.46163366336633666}, {\"mcc\": 0.28576187677566195, \"accuracy\": 0.45173267326732675}, {\"mcc\": 0.2363846937271293, \"accuracy\": 0.4158415841584158}, {\"mcc\": 0.29371969552484084, \"accuracy\": 0.46905940594059403}, {\"mcc\": 0.2788489359476192, \"accuracy\": 0.45544554455445546}, {\"mcc\": 0.2941359346512629, \"accuracy\": 0.46163366336633666}, {\"mcc\": 0.24206345230136958, \"accuracy\": 0.4245049504950495}, {\"mcc\": 0.23300912316080788, \"accuracy\": 0.4207920792079208}, {\"mcc\": 0.3088128491102455, \"accuracy\": 0.4814356435643564}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "danske-talemaader", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 27.507187023400125, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 25.793501258841907, "upper": 29.220872787958342, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "danske-talemaader", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 45.08663366336634, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 43.68657409803327, "upper": 46.486693228699416, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "dbrd/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004288+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "dbrd", "languages": "[\"nl\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.8749146461674351, \"macro_f1\": 0.9339516290283163}, {\"mcc\": 0.8922589560705567, \"macro_f1\": 0.944300028628686}, {\"mcc\": 0.9006080982862634, \"macro_f1\": 0.9482137404580153}, {\"mcc\": 0.8889812702006682, \"macro_f1\": 0.9421276073995739}, {\"mcc\": 0.8691321648534012, \"macro_f1\": 0.9305527297388945}, {\"mcc\": 0.8829424999433295, \"macro_f1\": 0.9384481514981509}, {\"mcc\": 0.8605545519529532, \"macro_f1\": 0.9255169377569137}, {\"mcc\": 0.8532675208987531, \"macro_f1\": 0.9213169146154605}, {\"mcc\": 0.8811089271930115, \"macro_f1\": 0.9378812771385494}, {\"mcc\": 0.8588934450482054, \"macro_f1\": 0.9245626724530526}]"}}, "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": 87.62662080614577, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 86.6557395216002, "upper": 88.59750209069134, "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": 93.46871688715612, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 92.90742806196616, "upper": 94.03000571234608, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "dutch-social/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004319+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.8.2"}}, "eval_library": {"name": "euroeval", "version": "15.5.0", "additional_details": {"dataset": "dutch-social", "languages": "[\"nl\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.0.dev0", "torch_version": "2.6.0", "vllm_version": "0.8.2", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.1122841131988631, \"macro_f1\": 0.29100016376845467}, {\"mcc\": 0.11245172092229472, \"macro_f1\": 0.27497426970871236}, {\"mcc\": 0.08421073643385744, \"macro_f1\": 0.27283308798288347}, {\"mcc\": 0.12078945339781517, \"macro_f1\": 0.25420431818091577}, {\"mcc\": 0.09514780802653273, \"macro_f1\": 0.3030269866107096}, {\"mcc\": 0.1012660959558297, \"macro_f1\": 0.27983133872163674}, {\"mcc\": 0.10227256853007835, \"macro_f1\": 0.2624318449749484}, {\"mcc\": 0.14342802893641488, \"macro_f1\": 0.28536614071400734}, {\"mcc\": 0.09045176578317841, \"macro_f1\": 0.2944764803271535}, {\"mcc\": 0.162260829350579, \"macro_f1\": 0.30234369708053915}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "dutch-social", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 11.245631205354437, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 9.738747283380453, "upper": 12.75251512732842, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "dutch-social", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 28.20488328069961, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 27.193253707824177, "upper": 29.216512853575047, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "eltec/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004350+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "eltec", "languages": "[\"fr\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.6344322344322345, \"micro_f1\": 0.6065649560795192}, {\"micro_f1_no_misc\": 0.6178630656242596, \"micro_f1\": 0.6046298418519367}, {\"micro_f1_no_misc\": 0.6529025989798397, \"micro_f1\": 0.6217777777777778}, {\"micro_f1_no_misc\": 0.6447980416156671, \"micro_f1\": 0.600086467790748}, {\"micro_f1_no_misc\": 0.6693982074263763, \"micro_f1\": 0.6511516314779271}, {\"micro_f1_no_misc\": 0.663147792706334, \"micro_f1\": 0.6436371740583908}, {\"micro_f1_no_misc\": 0.6503644486245004, \"micro_f1\": 0.6043979969518833}, {\"micro_f1_no_misc\": 0.6706408345752608, \"micro_f1\": 0.639887902849136}, {\"micro_f1_no_misc\": 0.6260304771421434, \"micro_f1\": 0.5791335101679929}, {\"micro_f1_no_misc\": 0.6652730598379932, \"micro_f1\": 0.5726033326119887}]"}}, "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": 64.94850760964609, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 63.79984652516809, "upper": 66.09716869412408, "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": 61.238705916173, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 59.59605802611974, "upper": 62.88135380622625, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "fone/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004381+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "fone", "languages": "[\"fo\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.6526939769238912, \"micro_f1\": 0.5027606878056476}, {\"micro_f1_no_misc\": 0.6392188443728609, \"micro_f1\": 0.627735831023607}, {\"micro_f1_no_misc\": 0.6398941698951147, \"micro_f1\": 0.5145560407569142}, {\"micro_f1_no_misc\": 0.6052631578947368, \"micro_f1\": 0.5515896566341669}, {\"micro_f1_no_misc\": 0.6435298935298935, \"micro_f1\": 0.4843525043570508}, {\"micro_f1_no_misc\": 0.6948919449901768, \"micro_f1\": 0.6088360237892948}, {\"micro_f1_no_misc\": 0.6771621345328154, \"micro_f1\": 0.6408375089477452}, {\"micro_f1_no_misc\": 0.6793862305673328, \"micro_f1\": 0.5986240529478359}, {\"micro_f1_no_misc\": 0.642666118082699, \"micro_f1\": 0.5670217298679164}, {\"micro_f1_no_misc\": 0.6654830287206266, \"micro_f1\": 0.5681975138121548}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "fone", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 65.40189499510147, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 63.799232880325576, "upper": 67.00455710987737, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "fone", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 56.64511549942335, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 53.3243615615836, "upper": 59.965869437263095, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "foqa/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004412+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "foqa", "languages": "[\"fo\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 60.39210693640134, \"em\": 41.911764705882355}, {\"f1\": 61.63054260569709, \"em\": 44.47174447174447}, {\"f1\": 68.16279332956222, \"em\": 51.111111111111114}, {\"f1\": 64.89699633718296, \"em\": 47.57281553398058}, {\"f1\": 66.07892829896377, \"em\": 48.51485148514851}, {\"f1\": 62.49061806032827, \"em\": 45.4320987654321}, {\"f1\": 64.16742400733655, \"em\": 46.93396226415094}, {\"f1\": 67.91223227219236, \"em\": 48.600508905852415}, {\"f1\": 67.58933038993133, \"em\": 50.62344139650873}, {\"f1\": 65.75035486084305, \"em\": 46.19164619164619}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "foqa", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 64.90713270984389, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 63.22340033363734, "upper": 66.59086508605044, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "foqa", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 47.136394483145736, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 45.402568264470595, "upper": 48.87022070182088, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "fosent/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004443+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "fosent", "languages": "[\"fo\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.2360327268993237, \"macro_f1\": 0.3772441714365489}, {\"mcc\": 0.17500800764709398, \"macro_f1\": 0.36836088944522677}, {\"mcc\": 0.17808627918469153, \"macro_f1\": 0.3744581525329089}, {\"mcc\": 0.23254041913020493, \"macro_f1\": 0.3992389604020765}, {\"mcc\": 0.2415804511678057, \"macro_f1\": 0.463895783057585}, {\"mcc\": 0.40347933977635014, \"macro_f1\": 0.5869849221118858}, {\"mcc\": 0.2573066128786684, \"macro_f1\": 0.3941646501310749}, {\"mcc\": 0.22643820230964196, \"macro_f1\": 0.4148481514818149}, {\"mcc\": 0.2750436896834069, \"macro_f1\": 0.42775002775002774}, {\"mcc\": 0.1710966372014744, \"macro_f1\": 0.35648665639792526}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "fosent", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 23.966123658786618, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 19.766726292745897, "upper": 28.16552102482734, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "fosent", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 41.634323647470744, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 37.42730142155908, "upper": 45.84134587338241, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "fquad/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004473+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "fquad", "languages": "[\"fr\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 75.04300933622719, \"em\": 47.34848484848485}, {\"f1\": 74.49130844355544, \"em\": 46.39878695981805}, {\"f1\": 76.1598536444198, \"em\": 48.873348873348874}, {\"f1\": 75.26560602783863, \"em\": 47.1841704718417}, {\"f1\": 71.89097995042816, \"em\": 45.720894371626834}, {\"f1\": 76.05126549095377, \"em\": 48.54961832061068}, {\"f1\": 74.3564038673692, \"em\": 47.50390015600624}, {\"f1\": 73.24357239384071, \"em\": 46.38364779874214}, {\"f1\": 74.35521606122208, \"em\": 49.14860681114551}, {\"f1\": 74.54822522693647, \"em\": 46.06481481481482}]"}}, "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": 74.54054404427914, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 73.75502945596902, "upper": 75.32605863258927, "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": 47.31762734264397, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 46.56758194136147, "upper": 48.06767274392648, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "germanquad/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004504+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "germanquad", "languages": "[\"de\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 67.82746869299466, \"em\": 39.54545454545455}, {\"f1\": 61.45456726051359, \"em\": 34.34420015163002}, {\"f1\": 67.16592453832642, \"em\": 37.60683760683761}, {\"f1\": 67.04004346131963, \"em\": 40.334855403348556}, {\"f1\": 64.87786516996172, \"em\": 38.781804163454126}, {\"f1\": 66.90453005744597, \"em\": 38.70229007633588}, {\"f1\": 61.381039069277044, \"em\": 34.86739469578783}, {\"f1\": 65.12266076709842, \"em\": 36.63522012578616}, {\"f1\": 66.01788144381997, \"em\": 36.9969040247678}, {\"f1\": 56.3864306899603, \"em\": 32.33024691358025}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "germanquad", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 64.41784111507178, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 62.17345022330143, "upper": 66.66223200684213, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "germanquad", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 37.014520770698276, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 35.44678884557778, "upper": 38.582252695818774, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "germeval/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004534+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "germeval", "languages": "[\"de\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.6305278174037089, \"micro_f1\": 0.4720880819007147}, {\"micro_f1_no_misc\": 0.6230211966729273, \"micro_f1\": 0.5503476115721014}, {\"micro_f1_no_misc\": 0.6538995281709686, \"micro_f1\": 0.49261268000748076}, {\"micro_f1_no_misc\": 0.604179471419791, \"micro_f1\": 0.44545973729297544}, {\"micro_f1_no_misc\": 0.584070796460177, \"micro_f1\": 0.48771610555050043}, {\"micro_f1_no_misc\": 0.6968128575320076, \"micro_f1\": 0.5466772151898734}, {\"micro_f1_no_misc\": 0.6331955109273479, \"micro_f1\": 0.4843282092233979}, {\"micro_f1_no_misc\": 0.6204782342121398, \"micro_f1\": 0.5290780141843971}, {\"micro_f1_no_misc\": 0.6329545454545454, \"micro_f1\": 0.4656909332826459}, {\"micro_f1_no_misc\": 0.6331342345174473, \"micro_f1\": 0.48014200133126245}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "germeval", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 63.122741927710614, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 61.27891978564577, "upper": 64.96656406977546, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "germeval", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 49.5414058953535, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 47.36225705505923, "upper": 51.72055473564777, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "goldenswag-pt/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004565+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "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\": 0.5388059976551505, \"accuracy\": 0.64404296875}, {\"mcc\": 0.7051827020911826, \"accuracy\": 0.77783203125}, {\"mcc\": 0.49382579189630493, \"accuracy\": 0.59375}, {\"mcc\": 0.5774011968046141, \"accuracy\": 0.67529296875}, {\"mcc\": 0.6760305963066702, \"accuracy\": 0.7529296875}, {\"mcc\": 0.5786440009490454, \"accuracy\": 0.654296875}, {\"mcc\": 0.6345256855911521, \"accuracy\": 0.72216796875}, {\"mcc\": 0.6190994578410491, \"accuracy\": 0.7080078125}, {\"mcc\": 0.5990274559546463, \"accuracy\": 0.685546875}, {\"mcc\": 0.5080336990700799, \"accuracy\": 0.5927734375}]"}}, "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": 59.30576584159895, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 55.05346901667572, "upper": 63.558062666522176, "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": 68.06640625, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 64.22882894399878, "upper": 71.90398355600122, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "harem/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004596+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "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\": 0.5777444735856125, \"micro_f1\": 0.47889643813053323}, {\"micro_f1_no_misc\": 0.5322772277227723, \"micro_f1\": 0.467280888258918}, {\"micro_f1_no_misc\": 0.5207547169811321, \"micro_f1\": 0.3890074706510139}, {\"micro_f1_no_misc\": 0.5308370044052864, \"micro_f1\": 0.46531153336279274}, {\"micro_f1_no_misc\": 0.5239533880017263, \"micro_f1\": 0.43387096774193545}, {\"micro_f1_no_misc\": 0.49529326574945687, \"micro_f1\": 0.410958904109589}, {\"micro_f1_no_misc\": 0.5286404416839199, \"micro_f1\": 0.43850490707872203}, {\"micro_f1_no_misc\": 0.5856137607505864, \"micro_f1\": 0.4920328343795268}, {\"micro_f1_no_misc\": 0.5663716814159292, \"micro_f1\": 0.45479685173367373}, {\"micro_f1_no_misc\": 0.5254612546125461, \"micro_f1\": 0.4632117722328855}]"}}, "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": 53.86947214908968, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 52.104955406429525, "upper": 55.63398889174984, "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": 44.93872567679591, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 42.982516468520295, "upper": 46.89493488507153, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "hellaswag-da/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004626+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "hellaswag-da", "languages": "[\"da\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.23839282360917427, \"accuracy\": 0.40966796875}, {\"mcc\": 0.19925479913061478, \"accuracy\": 0.3740234375}, {\"mcc\": 0.25203758311362157, \"accuracy\": 0.42431640625}, {\"mcc\": 0.2608544961714322, \"accuracy\": 0.44140625}, {\"mcc\": 0.25415990230172053, \"accuracy\": 0.41357421875}, {\"mcc\": 0.2676046415934403, \"accuracy\": 0.4404296875}, {\"mcc\": 0.21864791662979186, \"accuracy\": 0.38916015625}, {\"mcc\": 0.22360606520999507, \"accuracy\": 0.392578125}, {\"mcc\": 0.22137130309242783, \"accuracy\": 0.404296875}, {\"mcc\": 0.2223727891333397, \"accuracy\": 0.40234375}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "hellaswag-da", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 23.58302319985558, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 22.210457604433994, "upper": 24.95558879527717, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "hellaswag-da", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 40.91796875, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 39.571608727748874, "upper": 42.264328772251126, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "hellaswag-de/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004655+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "hellaswag-de", "languages": "[\"de\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.6413424505705206, \"accuracy\": 0.728515625}, {\"mcc\": 0.4773637723947521, \"accuracy\": 0.5849609375}, {\"mcc\": 0.5051516217389359, \"accuracy\": 0.6103515625}, {\"mcc\": 0.5615215599423178, \"accuracy\": 0.6689453125}, {\"mcc\": 0.459361259757744, \"accuracy\": 0.5712890625}, {\"mcc\": 0.47285732976368877, \"accuracy\": 0.583984375}, {\"mcc\": 0.5817206813323945, \"accuracy\": 0.67529296875}, {\"mcc\": 0.5920449428875398, \"accuracy\": 0.6875}, {\"mcc\": 0.5780994221795035, \"accuracy\": 0.68212890625}, {\"mcc\": 0.5008372465302744, \"accuracy\": 0.60498046875}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "hellaswag-de", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 53.70300287097671, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 49.88067944744598, "upper": 57.525326294507444, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "hellaswag-de", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 63.9794921875, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 60.58827341336168, "upper": 67.37071096163832, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "hellaswag-es/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004696+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "hellaswag-es", "languages": "[\"es\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.665485067230798, \"accuracy\": 0.74658203125}, {\"mcc\": 0.6171524895192818, \"accuracy\": 0.70849609375}, {\"mcc\": 0.5452077990535261, \"accuracy\": 0.642578125}, {\"mcc\": 0.6536761139746308, \"accuracy\": 0.73779296875}, {\"mcc\": 0.5661405644412681, \"accuracy\": 0.65576171875}, {\"mcc\": 0.5817832437387935, \"accuracy\": 0.67333984375}, {\"mcc\": 0.6412027006577018, \"accuracy\": 0.72509765625}, {\"mcc\": 0.589044571200855, \"accuracy\": 0.6826171875}, {\"mcc\": 0.6610333868213059, \"accuracy\": 0.74169921875}, {\"mcc\": 0.6199325587657056, \"accuracy\": 0.71044921875}]"}}, "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": 61.40658495403868, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 58.80096351756447, "upper": 64.01220639051289, "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": 70.244140625, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 67.94761124562156, "upper": 72.54067000437844, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "hellaswag-fi/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004726+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "hellaswag-fi", "languages": "[\"fi\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.12258733697183082, \"accuracy\": 0.34515935057125674}, {\"mcc\": 0.1364598507163282, \"accuracy\": 0.33974744437763077}, {\"mcc\": 0.1420888040680102, \"accuracy\": 0.34155141310883946}, {\"mcc\": 0.1278920998825502, \"accuracy\": 0.35057125676488277}, {\"mcc\": 0.18527579387337265, \"accuracy\": 0.3920625375826819}, {\"mcc\": 0.11927756345102102, \"accuracy\": 0.3319302465423933}, {\"mcc\": 0.11683434156923012, \"accuracy\": 0.3391461214672279}, {\"mcc\": 0.1356623381935118, \"accuracy\": 0.34876728803367407}, {\"mcc\": 0.14956004927533864, \"accuracy\": 0.3644016837041491}, {\"mcc\": 0.12422537248743937, \"accuracy\": 0.34876728803367407}]"}}, "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": 13.59863550488633, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 12.345219681048622, "upper": 14.852051328724038, "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": 35.021046301864104, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 33.962760000105334, "upper": 36.07933260362287, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "hellaswag-fr/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004756+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "hellaswag-fr", "languages": "[\"fr\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.6459644882078386, \"accuracy\": 0.72705078125}, {\"mcc\": 0.523896689836356, \"accuracy\": 0.62939453125}, {\"mcc\": 0.5894718460481831, \"accuracy\": 0.68310546875}, {\"mcc\": 0.5952935901300225, \"accuracy\": 0.6875}, {\"mcc\": 0.6294956339699348, \"accuracy\": 0.712890625}, {\"mcc\": 0.6390394851458637, \"accuracy\": 0.724609375}, {\"mcc\": 0.5778858323199937, \"accuracy\": 0.66552734375}, {\"mcc\": 0.6004662119495545, \"accuracy\": 0.693359375}, {\"mcc\": 0.5201934649320011, \"accuracy\": 0.61962890625}, {\"mcc\": 0.5485650469479917, \"accuracy\": 0.64404296875}]"}}, "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": 58.702722894877404, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 55.91149223490952, "upper": 61.49395355484529, "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": 67.87109375, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 65.49550476238896, "upper": 70.24668273761104, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "hellaswag-it/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004785+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "hellaswag-it", "languages": "[\"it\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.6455242212507218, \"accuracy\": 0.72802734375}, {\"mcc\": 0.5441599698449119, \"accuracy\": 0.6416015625}, {\"mcc\": 0.6049340732665062, \"accuracy\": 0.69677734375}, {\"mcc\": 0.6544667882708264, \"accuracy\": 0.73681640625}, {\"mcc\": 0.6075791561824726, \"accuracy\": 0.69775390625}, {\"mcc\": 0.5933977639566429, \"accuracy\": 0.69091796875}, {\"mcc\": 0.6361122062821154, \"accuracy\": 0.71875}, {\"mcc\": 0.6557232112815289, \"accuracy\": 0.73828125}, {\"mcc\": 0.6432712610661772, \"accuracy\": 0.7265625}, {\"mcc\": 0.5726511648413645, \"accuracy\": 0.6689453125}]"}}, "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": 61.57819816243266, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 59.238809363430455, "upper": 63.91758696143487, "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": 70.4443359375, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 68.49100986169594, "upper": 72.39766201330406, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "hellaswag-nl/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004813+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "hellaswag-nl", "languages": "[\"nl\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.5784352147970655, \"accuracy\": 0.673828125}, {\"mcc\": 0.5525966049228194, \"accuracy\": 0.64404296875}, {\"mcc\": 0.5675673294003099, \"accuracy\": 0.66455078125}, {\"mcc\": 0.5789412235682594, \"accuracy\": 0.6806640625}, {\"mcc\": 0.5452893608070787, \"accuracy\": 0.630859375}, {\"mcc\": 0.5655284498472637, \"accuracy\": 0.6630859375}, {\"mcc\": 0.5861907611886226, \"accuracy\": 0.68359375}, {\"mcc\": 0.5455375270099947, \"accuracy\": 0.650390625}, {\"mcc\": 0.5925181323097358, \"accuracy\": 0.69091796875}, {\"mcc\": 0.46509996845396445, \"accuracy\": 0.5615234375}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "hellaswag-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 55.777045723051145, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 53.51699168749962, "upper": 58.03709975860267, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "hellaswag-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 65.4345703125, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 63.10306679948124, "upper": 67.76607382551876, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "hellaswag-sv/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004842+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "hellaswag-sv", "languages": "[\"sv\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.33159396690224824, \"accuracy\": 0.47900390625}, {\"mcc\": 0.22049618540160953, \"accuracy\": 0.3935546875}, {\"mcc\": 0.34866522092982305, \"accuracy\": 0.501953125}, {\"mcc\": 0.38452841053035197, \"accuracy\": 0.53662109375}, {\"mcc\": 0.34261415316969734, \"accuracy\": 0.49755859375}, {\"mcc\": 0.34884513765990044, \"accuracy\": 0.5009765625}, {\"mcc\": 0.2577030504431781, \"accuracy\": 0.40283203125}, {\"mcc\": 0.3357884063362142, \"accuracy\": 0.4921875}, {\"mcc\": 0.27778537842974094, \"accuracy\": 0.443359375}, {\"mcc\": 0.2949641200073462, \"accuracy\": 0.46728515625}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "hellaswag-sv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 31.4298402981011, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 28.325410046271777, "upper": 34.534270549930426, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "hellaswag-sv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 47.1533203125, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 44.32047727675758, "upper": 49.98616334824242, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "hellaswag/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004871+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "hellaswag", "languages": "[\"en\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.7883322607242887, \"accuracy\": 0.83740234375}, {\"mcc\": 0.8030672711902905, \"accuracy\": 0.84912109375}, {\"mcc\": 0.7725053162802955, \"accuracy\": 0.82373046875}, {\"mcc\": 0.8055707336109355, \"accuracy\": 0.85205078125}, {\"mcc\": 0.7977339345546554, \"accuracy\": 0.84521484375}, {\"mcc\": 0.7927913408129736, \"accuracy\": 0.8408203125}, {\"mcc\": 0.7894968460365526, \"accuracy\": 0.837890625}, {\"mcc\": 0.7438619589354639, \"accuracy\": 0.80224609375}, {\"mcc\": 0.7896765754896, \"accuracy\": 0.83984375}, {\"mcc\": 0.769958509685004, \"accuracy\": 0.82373046875}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "hellaswag", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 78.52994747320061, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 77.37973924592859, "upper": 79.68015570047262, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "hellaswag", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 83.5205078125, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 82.59832489500857, "upper": 84.44269072999143, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "hotter-and-colder-sentiment/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004901+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "hotter-and-colder-sentiment", "languages": "[\"is\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.16099475813572056, \"macro_f1\": 0.26608869367066895}, {\"mcc\": 0.25708961990638235, \"macro_f1\": 0.4079672976710102}, {\"mcc\": 0.15824805397072642, \"macro_f1\": 0.3770638272813902}, {\"mcc\": 0.2959586542285822, \"macro_f1\": 0.4318666561747125}, {\"mcc\": 0.05092643596749269, \"macro_f1\": 0.19886805671864424}, {\"mcc\": 0.24147069865516255, \"macro_f1\": 0.32950152409552513}, {\"mcc\": 0.20860682585582402, \"macro_f1\": 0.3383384142561257}, {\"mcc\": 0.02854420762224293, \"macro_f1\": 0.19270929483131075}, {\"mcc\": 0.34199436055115245, \"macro_f1\": 0.5455735243825589}, {\"mcc\": 0.3146387868562488, \"macro_f1\": 0.45013417838620157}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "hotter-and-colder-sentiment", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 20.58472401749535, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 13.98287612081408, "upper": 27.18657191417662, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "hotter-and-colder-sentiment", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 35.38111467468148, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 28.402244396376105, "upper": 42.35998495298685, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "icelandic-knowledge/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004931+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "icelandic-knowledge", "languages": "[\"is\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.017578386405086816, \"accuracy\": 0.2685546875}, {\"mcc\": 0.0622481519247776, \"accuracy\": 0.3017578125}, {\"mcc\": 0.014056137375661361, \"accuracy\": 0.267578125}, {\"mcc\": 0.05653809192205327, \"accuracy\": 0.2939453125}, {\"mcc\": 0.0272163822248578, \"accuracy\": 0.2685546875}, {\"mcc\": 0.02505395996986633, \"accuracy\": 0.2705078125}, {\"mcc\": 0.058749280640033145, \"accuracy\": 0.2998046875}, {\"mcc\": 0.0654634973920401, \"accuracy\": 0.2890625}, {\"mcc\": -0.009250898246792741, \"accuracy\": 0.2548828125}, {\"mcc\": 0.055446637361472914, \"accuracy\": 0.296875}]"}}, "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": 3.730996269690566, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 2.1409759002286624, "upper": 5.32101663915247, "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": 28.115234374999996, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 27.071743548725365, "upper": 29.158725201274628, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "idioms-no/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004960+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "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\": 0.009449933446339475, \"accuracy\": 0.25244140625}, {\"mcc\": 0.015748402548604927, \"accuracy\": 0.26123046875}, {\"mcc\": -0.005060452683718559, \"accuracy\": 0.24609375}, {\"mcc\": -0.021948571626302347, \"accuracy\": 0.23486328125}, {\"mcc\": 0.021910337383569175, \"accuracy\": 0.26220703125}, {\"mcc\": 0.014136827266103704, \"accuracy\": 0.26025390625}, {\"mcc\": 0.0065272705378316255, \"accuracy\": 0.251953125}, {\"mcc\": -0.020621183321402448, \"accuracy\": 0.23779296875}, {\"mcc\": 0.014225889014851804, \"accuracy\": 0.2587890625}, {\"mcc\": -0.017153264288297908, \"accuracy\": 0.23388671875}]"}}, "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": 0.17215188277579443, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": -0.8524336794218323, "upper": 1.1967374449734212, "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": 24.9951171875, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 24.30360002103476, "upper": 25.68663435396524, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "life-in-the-uk/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.004989+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "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\": 0.7497216480899715, \"accuracy\": 0.810546875}, {\"mcc\": 0.7841952989182768, \"accuracy\": 0.837890625}, {\"mcc\": 0.7402528319993062, \"accuracy\": 0.8046875}, {\"mcc\": 0.7675832588454228, \"accuracy\": 0.826171875}, {\"mcc\": 0.7440361964390214, \"accuracy\": 0.8046875}, {\"mcc\": 0.7743820923306717, \"accuracy\": 0.830078125}, {\"mcc\": 0.7425803484509256, \"accuracy\": 0.806640625}, {\"mcc\": 0.7403671363768692, \"accuracy\": 0.8046875}, {\"mcc\": 0.7842256987266291, \"accuracy\": 0.8359375}, {\"mcc\": 0.7498962303043866, \"accuracy\": 0.814453125}]"}}, "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": 75.77240740481481, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 74.65479352870406, "upper": 76.89002128092557, "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": 81.7578125, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 80.9167858379053, "upper": 82.5988391620947, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mim-gold-ner/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005019+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "mim-gold-ner", "languages": "[\"is\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.49163225385785697, \"micro_f1\": 0.296190815236739}, {\"micro_f1_no_misc\": 0.5485885585810643, \"micro_f1\": 0.2877295118674429}, {\"micro_f1_no_misc\": 0.5094532447623915, \"micro_f1\": 0.4261682242990654}, {\"micro_f1_no_misc\": 0.4978618050866532, \"micro_f1\": 0.29699376063528077}, {\"micro_f1_no_misc\": 0.42412140575079876, \"micro_f1\": 0.2804931748128578}, {\"micro_f1_no_misc\": 0.4416737109044801, \"micro_f1\": 0.24909439590880036}, {\"micro_f1_no_misc\": 0.45337536117677957, \"micro_f1\": 0.35739721592748463}, {\"micro_f1_no_misc\": 0.5346011621764395, \"micro_f1\": 0.2916305021698698}, {\"micro_f1_no_misc\": 0.5077171158719188, \"micro_f1\": 0.36275626423690205}, {\"micro_f1_no_misc\": 0.5221932114882506, \"micro_f1\": 0.2786689011252095}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "mim-gold-ner", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 49.31217829656633, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 46.77051755476892, "upper": 51.85383903836374, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "mim-gold-ner", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 31.271227662196523, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 27.991112800259742, "upper": 34.551342524133304, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mlqa-es/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005050+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "mlqa-es", "languages": "[\"es\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 64.9489054055723, \"em\": 37.134052388289675}, {\"f1\": 68.53089471939273, \"em\": 40.184757505773675}, {\"f1\": 71.87668048949996, \"em\": 48.35423197492163}, {\"f1\": 68.71585593268158, \"em\": 41.8026418026418}, {\"f1\": 69.0294019126153, \"em\": 39.93660855784469}, {\"f1\": 67.52168352640737, \"em\": 41.217257318952235}, {\"f1\": 64.55716161715843, \"em\": 32.268121590023384}, {\"f1\": 70.12303977029893, \"em\": 47.62658227848101}, {\"f1\": 67.32753629498974, \"em\": 41.09263657957245}, {\"f1\": 66.3736839584804, \"em\": 40.061871616395976}]"}}, "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": 67.90048436270968, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 66.50260909871406, "upper": 69.29835962670529, "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": 40.96787616128965, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 38.10099488629552, "upper": 43.83475743628379, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mmlu-de/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005080+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "mmlu-de", "languages": "[\"de\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.37411108405803134, \"accuracy\": 0.525390625}, {\"mcc\": 0.3632029519578443, \"accuracy\": 0.521484375}, {\"mcc\": 0.3499290098563147, \"accuracy\": 0.51025390625}, {\"mcc\": 0.33835053039207247, \"accuracy\": 0.501953125}, {\"mcc\": 0.39835065938810593, \"accuracy\": 0.54541015625}, {\"mcc\": 0.3572962365971125, \"accuracy\": 0.51513671875}, {\"mcc\": 0.37196789361808463, \"accuracy\": 0.52001953125}, {\"mcc\": 0.3821837758647882, \"accuracy\": 0.53076171875}, {\"mcc\": 0.33447534713398425, \"accuracy\": 0.49951171875}, {\"mcc\": 0.30627965619958886, \"accuracy\": 0.47216796875}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "mmlu-de", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 35.76147145065927, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 34.11208915136282, "upper": 37.41085374995573, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "mmlu-de", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 51.42089843749999, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 50.179669121398845, "upper": 52.66212775360114, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mmlu-es/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005109+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "mmlu-es", "languages": "[\"es\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.39273948634332123, \"accuracy\": 0.5400390625}, {\"mcc\": 0.41140943795307144, \"accuracy\": 0.5576171875}, {\"mcc\": 0.39171459105511297, \"accuracy\": 0.54150390625}, {\"mcc\": 0.4178816455998159, \"accuracy\": 0.560546875}, {\"mcc\": 0.39272439448077234, \"accuracy\": 0.53955078125}, {\"mcc\": 0.4273216124820846, \"accuracy\": 0.56689453125}, {\"mcc\": 0.4067017379005327, \"accuracy\": 0.5458984375}, {\"mcc\": 0.374869554571089, \"accuracy\": 0.52294921875}, {\"mcc\": 0.4180035128480236, \"accuracy\": 0.5595703125}, {\"mcc\": 0.3759835601844496, \"accuracy\": 0.53076171875}]"}}, "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": 40.093495334182734, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 38.97339090033354, "upper": 41.213599768031926, "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": 54.6533203125, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 53.770629384657575, "upper": 55.536011240342425, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mmlu-fr/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005139+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "mmlu-fr", "languages": "[\"fr\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.4047088291005163, \"accuracy\": 0.55029296875}, {\"mcc\": 0.39346536436956997, \"accuracy\": 0.5400390625}, {\"mcc\": 0.3664373997480413, \"accuracy\": 0.515625}, {\"mcc\": 0.41868691650811496, \"accuracy\": 0.56298828125}, {\"mcc\": 0.41847685394575845, \"accuracy\": 0.55419921875}, {\"mcc\": 0.3669799062875781, \"accuracy\": 0.5205078125}, {\"mcc\": 0.37584735744785747, \"accuracy\": 0.5244140625}, {\"mcc\": 0.3856780868020753, \"accuracy\": 0.533203125}, {\"mcc\": 0.38244155794920476, \"accuracy\": 0.5322265625}, {\"mcc\": 0.4038580336175794, \"accuracy\": 0.54833984375}]"}}, "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": 39.16580305776296, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 37.963241875898646, "upper": 40.36836423962727, "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": 53.818359375, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 52.85014305239546, "upper": 54.78657569760454, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mmlu-it/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005168+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "mmlu-it", "languages": "[\"it\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.40736292055449463, \"accuracy\": 0.546875}, {\"mcc\": 0.4164008578938993, \"accuracy\": 0.5576171875}, {\"mcc\": 0.3684174280685246, \"accuracy\": 0.51904296875}, {\"mcc\": 0.38135620946592413, \"accuracy\": 0.53173828125}, {\"mcc\": 0.397163329866684, \"accuracy\": 0.5419921875}, {\"mcc\": 0.4203452173602965, \"accuracy\": 0.56005859375}, {\"mcc\": 0.34719657190638153, \"accuracy\": 0.4970703125}, {\"mcc\": 0.3725173892872683, \"accuracy\": 0.52490234375}, {\"mcc\": 0.37456091046122064, \"accuracy\": 0.52490234375}, {\"mcc\": 0.36856831558918096, \"accuracy\": 0.5185546875}]"}}, "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": 38.53889150453874, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 37.05854989702202, "upper": 40.01923311205546, "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": 53.22753906249999, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 52.01694181632609, "upper": 54.4381363086739, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mmlu-nl/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005197+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "mmlu-nl", "languages": "[\"nl\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.3775018392778121, \"accuracy\": 0.53125}, {\"mcc\": 0.3819525413211518, \"accuracy\": 0.53076171875}, {\"mcc\": 0.3380802096153692, \"accuracy\": 0.4990234375}, {\"mcc\": 0.3707339444874831, \"accuracy\": 0.52685546875}, {\"mcc\": 0.3296767235654302, \"accuracy\": 0.49267578125}, {\"mcc\": 0.36457940385196286, \"accuracy\": 0.5205078125}, {\"mcc\": 0.34449116624930176, \"accuracy\": 0.49951171875}, {\"mcc\": 0.35640153809772945, \"accuracy\": 0.513671875}, {\"mcc\": 0.3672663620249679, \"accuracy\": 0.5224609375}, {\"mcc\": 0.3591984304624234, \"accuracy\": 0.5146484375}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "mmlu-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 35.89882158953632, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 34.841092564000824, "upper": 36.95655061507181, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "mmlu-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 51.513671875, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 50.65328948525638, "upper": 52.37405426474362, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mmlu-pt/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005226+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "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\": 0.41432109562086755, \"accuracy\": 0.55810546875}, {\"mcc\": 0.41861347650635167, \"accuracy\": 0.564453125}, {\"mcc\": 0.3960755862388297, \"accuracy\": 0.54443359375}, {\"mcc\": 0.39275672697410624, \"accuracy\": 0.54296875}, {\"mcc\": 0.4247524080723465, \"accuracy\": 0.56298828125}, {\"mcc\": 0.4186594089280774, \"accuracy\": 0.5634765625}, {\"mcc\": 0.4308991896689303, \"accuracy\": 0.5693359375}, {\"mcc\": 0.42750060853500194, \"accuracy\": 0.56640625}, {\"mcc\": 0.42122175795088307, \"accuracy\": 0.5625}, {\"mcc\": 0.4122193074371417, \"accuracy\": 0.5576171875}]"}}, "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": 41.57019565932536, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 40.79015833233727, "upper": 42.35023298631344, "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": 55.9228515625, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 55.37196019665446, "upper": 56.47374292834554, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mmlu-sv/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005255+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "mmlu-sv", "languages": "[\"sv\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.23074501338347203, \"accuracy\": 0.40966796875}, {\"mcc\": 0.25343923149521447, \"accuracy\": 0.43115234375}, {\"mcc\": 0.2589992932043042, \"accuracy\": 0.43017578125}, {\"mcc\": 0.280655272416353, \"accuracy\": 0.45458984375}, {\"mcc\": 0.24694103293248593, \"accuracy\": 0.42333984375}, {\"mcc\": 0.23678611117849052, \"accuracy\": 0.41552734375}, {\"mcc\": 0.20961250565452305, \"accuracy\": 0.39111328125}, {\"mcc\": 0.26079920629412773, \"accuracy\": 0.4248046875}, {\"mcc\": 0.24110635961198607, \"accuracy\": 0.42333984375}, {\"mcc\": 0.24785863476350709, \"accuracy\": 0.4365234375}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "mmlu-sv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 24.66942660934464, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 23.480888463359214, "upper": 25.857964755330066, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "mmlu-sv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 42.40234375, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 41.36066848961878, "upper": 43.44401901038122, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mmlu/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005284+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "mmlu", "languages": "[\"en\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.4906902365011846, \"accuracy\": 0.61083984375}, {\"mcc\": 0.45055506320125677, \"accuracy\": 0.58203125}, {\"mcc\": 0.4951011075611897, \"accuracy\": 0.6171875}, {\"mcc\": 0.48531267291652425, \"accuracy\": 0.61181640625}, {\"mcc\": 0.49723733259039793, \"accuracy\": 0.61865234375}, {\"mcc\": 0.4500934570532853, \"accuracy\": 0.58349609375}, {\"mcc\": 0.4721749554790173, \"accuracy\": 0.599609375}, {\"mcc\": 0.4966977192946746, \"accuracy\": 0.61767578125}, {\"mcc\": 0.4470300942216961, \"accuracy\": 0.578125}, {\"mcc\": 0.47591657866676207, \"accuracy\": 0.6005859375}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "mmlu", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 47.6080921748599, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 46.3481201202373, "upper": 48.8680642294825, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "mmlu", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 60.20019531250001, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 59.22083333333334, "upper": 61.179557291666676, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "multi-wiki-qa-pt/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005314+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "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\": 75.33755106045882, \"em\": 57.82881002087683}, {\"f1\": 78.94360065397315, \"em\": 59.32203389830509}, {\"f1\": 78.89313297495352, \"em\": 60.788381742738586}, {\"f1\": 77.65778497265296, \"em\": 59.47046843177189}, {\"f1\": 75.43989163064356, \"em\": 57.31958762886598}, {\"f1\": 74.02233416358881, \"em\": 56.46817248459959}, {\"f1\": 78.68103321678173, \"em\": 60.37735849056604}, {\"f1\": 79.72358968807286, \"em\": 62.34309623430963}, {\"f1\": 76.31066814510795, \"em\": 58.09128630705394}, {\"f1\": 76.77142185718908, \"em\": 59.50413223140496}]"}}, "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": 77.17810083634224, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 76.00369121353721, "upper": 78.35251045914727, "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": 59.15133274704925, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 58.05705732536352, "upper": 60.24560816873498, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "multinerd-it/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005344+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "multinerd-it", "languages": "[\"it\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.7387038828243747, \"micro_f1\": 0.5956230460026797}, {\"micro_f1_no_misc\": 0.7412834765032844, \"micro_f1\": 0.6274977085242897}, {\"micro_f1_no_misc\": 0.7053682896379525, \"micro_f1\": 0.6005564031230368}, {\"micro_f1_no_misc\": 0.6375395228513941, \"micro_f1\": 0.553580009610764}, {\"micro_f1_no_misc\": 0.7756410256410257, \"micro_f1\": 0.6287272727272728}, {\"micro_f1_no_misc\": 0.7506856471202821, \"micro_f1\": 0.6225201558112147}, {\"micro_f1_no_misc\": 0.7269950362733868, \"micro_f1\": 0.5459964556146286}, {\"micro_f1_no_misc\": 0.6323065364387678, \"micro_f1\": 0.561904761904762}, {\"micro_f1_no_misc\": 0.7350798722044728, \"micro_f1\": 0.5644546147978643}, {\"micro_f1_no_misc\": 0.7057242676699812, \"micro_f1\": 0.5824751919116269}]"}}, "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": 71.49327557164924, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 68.5884998026425, "upper": 74.39805134065597, "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": 58.833356200281386, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 56.89085809620966, "upper": 60.77585430435311, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "nor-common-sense-qa/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005376+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "nor-common-sense-qa", "languages": "[\"nb\", \"nn\", \"no\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.5093789310353283, \"accuracy\": 0.6016451233842538}, {\"mcc\": 0.5127779559364837, \"accuracy\": 0.6039952996474736}, {\"mcc\": 0.5374778866929351, \"accuracy\": 0.6251468860164512}, {\"mcc\": 0.520134995461231, \"accuracy\": 0.6063454759106933}, {\"mcc\": 0.47122243604246583, \"accuracy\": 0.5675675675675675}, {\"mcc\": 0.5285254056519427, \"accuracy\": 0.6204465334900118}, {\"mcc\": 0.49649483318233045, \"accuracy\": 0.5863689776733255}, {\"mcc\": 0.5034952945948208, \"accuracy\": 0.5922444183313749}, {\"mcc\": 0.4933852759174834, \"accuracy\": 0.5851938895417156}, {\"mcc\": 0.42563686764263364, \"accuracy\": 0.5276145710928319}]"}}, "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": 49.98529882157655, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 47.99279124512387, "upper": 51.97780639802923, "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": 59.16568742655699, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 57.41626975514239, "upper": 60.9151050979716, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "norec/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005406+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "norec", "languages": "[\"nb\", \"nn\", \"no\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.5278870273188124, \"macro_f1\": 0.6819319179253194}, {\"mcc\": 0.48478597438625876, \"macro_f1\": 0.648090866830715}, {\"mcc\": 0.5214407271733406, \"macro_f1\": 0.6816119009433773}, {\"mcc\": 0.5240727506622735, \"macro_f1\": 0.678405138142043}, {\"mcc\": 0.508838590388664, \"macro_f1\": 0.6720013452809054}, {\"mcc\": 0.5135290970964017, \"macro_f1\": 0.6672915204887645}, {\"mcc\": 0.499821434684663, \"macro_f1\": 0.6590269920841837}, {\"mcc\": 0.5280894490011324, \"macro_f1\": 0.6841410372579325}, {\"mcc\": 0.5012828791696593, \"macro_f1\": 0.6643892799212358}, {\"mcc\": 0.5532474048056574, \"macro_f1\": 0.6949762130936779}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "norec", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 51.62995334686864, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 50.446942718502285, "upper": 52.81296397523499, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "norec", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 67.31866211968153, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 66.46348739134815, "upper": 68.17383684801491, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "norne-nb/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005437+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "norne-nb", "languages": "[\"nb\", \"no\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.7113631760178245, \"micro_f1\": 0.6249796450089561}, {\"micro_f1_no_misc\": 0.7157057654075547, \"micro_f1\": 0.5852070088385796}, {\"micro_f1_no_misc\": 0.7051537270515373, \"micro_f1\": 0.562026133247298}, {\"micro_f1_no_misc\": 0.7218177807191707, \"micro_f1\": 0.6609887057952232}, {\"micro_f1_no_misc\": 0.7379157427937916, \"micro_f1\": 0.6158028887000849}, {\"micro_f1_no_misc\": 0.7323008849557522, \"micro_f1\": 0.5662262326780534}, {\"micro_f1_no_misc\": 0.6849498327759198, \"micro_f1\": 0.5514237855946399}, {\"micro_f1_no_misc\": 0.6357647058823529, \"micro_f1\": 0.4893931919092255}, {\"micro_f1_no_misc\": 0.6816706340618914, \"micro_f1\": 0.5709560039695667}, {\"micro_f1_no_misc\": 0.7232620320855615, \"micro_f1\": 0.5222524977293369}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "norne-nb", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 70.49904281751357, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 68.61227263772119, "upper": 72.38581299730595, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "norne-nb", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 57.492560934709644, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 54.387382143422066, "upper": 60.59773972599722, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "norne-nn/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005468+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "norne-nn", "languages": "[\"nn\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.6321199143468951, \"micro_f1\": 0.5983537712077944}, {\"micro_f1_no_misc\": 0.6443464314354451, \"micro_f1\": 0.5088607594936709}, {\"micro_f1_no_misc\": 0.643088116410671, \"micro_f1\": 0.529126213592233}, {\"micro_f1_no_misc\": 0.6610407876230661, \"micro_f1\": 0.582398483172697}, {\"micro_f1_no_misc\": 0.667457962413452, \"micro_f1\": 0.590034832651825}, {\"micro_f1_no_misc\": 0.6703866082104424, \"micro_f1\": 0.5402056048443881}, {\"micro_f1_no_misc\": 0.6642123619453594, \"micro_f1\": 0.5807926829268292}, {\"micro_f1_no_misc\": 0.6342111086523567, \"micro_f1\": 0.5912249354774668}, {\"micro_f1_no_misc\": 0.667961919564795, \"micro_f1\": 0.5789473684210527}, {\"micro_f1_no_misc\": 0.6457873842082046, \"micro_f1\": 0.5952581133344543}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "norne-nn", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 65.30612594810688, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 64.39621494147492, "upper": 66.21603695473884, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "norne-nn", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 56.952027651224114, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 54.99877528427292, "upper": 58.90528001817531, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "norquad/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005499+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "norquad", "languages": "[\"nb\", \"nn\", \"no\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 74.40282844960228, \"em\": 47.38562091503268}, {\"f1\": 66.43608130295428, \"em\": 40.65040650406504}, {\"f1\": 71.13855332003975, \"em\": 45.129059117402164}, {\"f1\": 68.93347325224656, \"em\": 44.15372035977106}, {\"f1\": 74.05995807932864, \"em\": 48.966087675765095}, {\"f1\": 65.88422104013837, \"em\": 40.0}, {\"f1\": 68.14018841238767, \"em\": 42.10084033613445}, {\"f1\": 71.71623690402107, \"em\": 47.55067567567568}, {\"f1\": 66.92666090515448, \"em\": 41.52823920265781}, {\"f1\": 65.86716252279365, \"em\": 39.817880794701985}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "norquad", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 69.35053641886668, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 67.31936110615669, "upper": 71.38171173157667, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "norquad", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 43.72825305812059, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 41.62417482069145, "upper": 45.832331295549736, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "nqii/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005530+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "nqii", "languages": "[\"is\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 56.60862274777899, \"em\": 29.384615384615383}, {\"f1\": 58.503347382881245, \"em\": 30.529595015576323}, {\"f1\": 51.737300880184236, \"em\": 28.97196261682243}, {\"f1\": 54.06838842098362, \"em\": 31.2406576980568}, {\"f1\": 57.2315975212122, \"em\": 31.34796238244514}, {\"f1\": 57.44283983071845, \"em\": 32.81972265023113}, {\"f1\": 58.32929874464146, \"em\": 31.384615384615383}, {\"f1\": 55.78581843953495, \"em\": 30.67484662576687}, {\"f1\": 56.33095958869829, \"em\": 29.518072289156628}, {\"f1\": 58.64047300623082, \"em\": 34.93975903614458}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "nqii", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 56.46786465628643, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 55.12095684831361, "upper": 57.81477246425925, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "nqii", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 31.08118090834307, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 29.981334850795704, "upper": 32.18102696589044, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "nrk-quiz-qa/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005560+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "nrk-quiz-qa", "languages": "[\"nb\", \"nn\", \"no\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.2598175205534884, \"accuracy\": 0.44140625}, {\"mcc\": 0.26946631534169646, \"accuracy\": 0.45849609375}, {\"mcc\": 0.2904512726055736, \"accuracy\": 0.46630859375}, {\"mcc\": 0.3018335189126933, \"accuracy\": 0.4716796875}, {\"mcc\": 0.30883161008191035, \"accuracy\": 0.4775390625}, {\"mcc\": 0.27862982362301686, \"accuracy\": 0.45263671875}, {\"mcc\": 0.2603380796381612, \"accuracy\": 0.44189453125}, {\"mcc\": 0.3115342864984582, \"accuracy\": 0.48828125}, {\"mcc\": 0.2440826873913503, \"accuracy\": 0.4326171875}, {\"mcc\": 0.2802474101735691, \"accuracy\": 0.45849609375}]"}}, "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": 28.05232524819917, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 26.65020726466949, "upper": 29.454443231728852, "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": 45.8935546875, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 44.8092524063987, "upper": 46.9778569686013, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "sb10k/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005589+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "sb10k", "languages": "[\"de\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.4620691101716077, \"macro_f1\": 0.6293333890093203}, {\"mcc\": 0.5257134067623815, \"macro_f1\": 0.6728919203359656}, {\"mcc\": 0.5387738598850723, \"macro_f1\": 0.6750068013375863}, {\"mcc\": 0.4996745439904581, \"macro_f1\": 0.643027182787364}, {\"mcc\": 0.4993908500622948, \"macro_f1\": 0.6492674068837415}, {\"mcc\": 0.6151592983647364, \"macro_f1\": 0.741022204644119}, {\"mcc\": 0.4912143659941362, \"macro_f1\": 0.5995156029893897}, {\"mcc\": 0.5347306579308234, \"macro_f1\": 0.6812682487243716}, {\"mcc\": 0.5851234472432205, \"macro_f1\": 0.6908757717655702}, {\"mcc\": 0.5536624207906718, \"macro_f1\": 0.6771161312779759}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "sb10k", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 53.05511961195404, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 50.21174631541029, "upper": 55.89849290849779, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "sb10k", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 66.59324659755404, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 64.21016959628754, "upper": 68.97632359882054, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-da/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005634+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "scala-da", "languages": "[\"da\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.2120437235296602, \"macro_f1\": 0.6058736169542192}, {\"mcc\": 0.21445168451826666, \"macro_f1\": 0.607201315583623}, {\"mcc\": 0.22095763655032247, \"macro_f1\": 0.5886746569393781}, {\"mcc\": 0.2427163859036805, \"macro_f1\": 0.6198647087939284}, {\"mcc\": 0.20707616584862595, \"macro_f1\": 0.6021497144432025}, {\"mcc\": 0.2343678544399321, \"macro_f1\": 0.6105333055350348}, {\"mcc\": 0.22591060967707702, \"macro_f1\": 0.5651702830515309}, {\"mcc\": 0.2390693629113974, \"macro_f1\": 0.6184157131361645}, {\"mcc\": 0.21091486833548842, \"macro_f1\": 0.5940791865630172}, {\"mcc\": 0.21983600408138054, \"macro_f1\": 0.6080429836410025}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-da", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 22.273442957958313, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 21.50293343996966, "upper": 23.043952475946966, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-da", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 60.20005484641102, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 59.20133669737797, "upper": 61.198772995444074, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-de/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005666+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "scala-de", "languages": "[\"de\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.4482674430647071, \"macro_f1\": 0.7239219818103257}, {\"mcc\": 0.44026953087842485, \"macro_f1\": 0.7200273410799727}, {\"mcc\": 0.4111630259395346, \"macro_f1\": 0.6819435376975884}, {\"mcc\": 0.418882816261858, \"macro_f1\": 0.7094244439348774}, {\"mcc\": 0.41019035794648046, \"macro_f1\": 0.6965510106756215}, {\"mcc\": 0.4289502037933683, \"macro_f1\": 0.7144505181772689}, {\"mcc\": 0.4084903566959393, \"macro_f1\": 0.6947194146318874}, {\"mcc\": 0.4248421364021652, \"macro_f1\": 0.7114606343803483}, {\"mcc\": 0.3915933057992517, \"macro_f1\": 0.695788523736122}, {\"mcc\": 0.39332721521334113, \"macro_f1\": 0.6958478780961841}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-de", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 41.75976391995071, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 40.61276655774076, "upper": 42.90676128216065, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-de", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 70.44135284220197, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 69.61279334998807, "upper": 71.26991233441586, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-en/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005696+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "scala-en", "languages": "[\"en\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.39755594066701505, \"macro_f1\": 0.6987298222943308}, {\"mcc\": 0.42878355168592464, \"macro_f1\": 0.7124735567854601}, {\"mcc\": 0.4931797761812172, \"macro_f1\": 0.7463715360920755}, {\"mcc\": 0.42444483800842236, \"macro_f1\": 0.7113833764739719}, {\"mcc\": 0.37499246528769886, \"macro_f1\": 0.6873282442748092}, {\"mcc\": 0.44140043898881, \"macro_f1\": 0.7180115511373955}, {\"mcc\": 0.4266938522364162, \"macro_f1\": 0.7082682648883636}, {\"mcc\": 0.4322260054575285, \"macro_f1\": 0.7160225379998801}, {\"mcc\": 0.4250560308542019, \"macro_f1\": 0.7115961123522561}, {\"mcc\": 0.38341704711981967, \"macro_f1\": 0.6904573785064838}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-en", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 42.277499464870544, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 40.219682761048965, "upper": 44.335316168692124, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-en", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 71.00642380805026, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 69.981747702841, "upper": 72.03109991325951, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-es/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005727+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "scala-es", "languages": "[\"es\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.24082681564162664, \"macro_f1\": 0.6012749132772446}, {\"mcc\": 0.3077435280372195, \"macro_f1\": 0.6499567674086586}, {\"mcc\": 0.25658607873909073, \"macro_f1\": 0.6281093236340451}, {\"mcc\": 0.28361517219251836, \"macro_f1\": 0.631125275226154}, {\"mcc\": 0.2260647331844, \"macro_f1\": 0.6098025439313837}, {\"mcc\": 0.253571983260754, \"macro_f1\": 0.6259676448737352}, {\"mcc\": 0.2567253440207415, \"macro_f1\": 0.6282689857876561}, {\"mcc\": 0.21469735644376128, \"macro_f1\": 0.5628672673438193}, {\"mcc\": 0.26760363925758945, \"macro_f1\": 0.6336996336996337}, {\"mcc\": 0.253510356731119, \"macro_f1\": 0.6243684673786762}]"}}, "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": 25.6094500750882, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 23.95408301292013, "upper": 27.264817137256273, "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": 61.95440822561007, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 60.476895117875266, "upper": 63.43192133334487, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-fi/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005757+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "scala-fi", "languages": "[\"fi\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.09602590537179025, \"macro_f1\": 0.4794706141960046}, {\"mcc\": 0.11353967750420424, \"macro_f1\": 0.553796023276623}, {\"mcc\": 0.09349548058166801, \"macro_f1\": 0.5132657565046156}, {\"mcc\": 0.11252977301425494, \"macro_f1\": 0.5225336137170602}, {\"mcc\": 0.03446645424020029, \"macro_f1\": 0.4167654749926264}, {\"mcc\": 0.0969668630468198, \"macro_f1\": 0.5344895102726049}, {\"mcc\": 0.12201008389977117, \"macro_f1\": 0.5610049081846393}, {\"mcc\": 0.061116561867978675, \"macro_f1\": 0.4544621983655305}, {\"mcc\": 0.1304845015471332, \"macro_f1\": 0.5380535841998129}, {\"mcc\": 0.1065073092186327, \"macro_f1\": 0.5429691602198341}]"}}, "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": 9.671426102924533, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 7.874780761711971, "upper": 11.468071444137095, "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": 51.168108439293505, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 48.25787977104701, "upper": 54.07833710754, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-fo/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005788+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "scala-fo", "languages": "[\"fo\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.028741979534608296, \"macro_f1\": 0.5126009297773428}, {\"mcc\": -0.013843847342456793, \"macro_f1\": 0.49290823789391125}, {\"mcc\": 0.07012419371741686, \"macro_f1\": 0.49270596171683956}, {\"mcc\": 0.03000592592297697, \"macro_f1\": 0.49677206284416414}, {\"mcc\": 0.09373191397311256, \"macro_f1\": 0.5308906389969332}, {\"mcc\": 0.0729323987144488, \"macro_f1\": 0.5217628415696465}, {\"mcc\": 0.020249627869660697, \"macro_f1\": 0.49031674208144793}, {\"mcc\": 0.03027351558031712, \"macro_f1\": 0.5068216505884575}, {\"mcc\": 0.026055904900832556, \"macro_f1\": 0.5075272891557485}, {\"mcc\": 0.0309023850375922, \"macro_f1\": 0.49971048060220036}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-fo", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 3.8917399790850924, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 1.9585931281449094, "upper": 5.824886830025275, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-fo", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 50.52016835226693, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 49.686810726706426, "upper": 51.35352597782743, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-fr/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005819+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "scala-fr", "languages": "[\"fr\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.1715352503967849, \"macro_f1\": 0.44051284907607063}, {\"mcc\": 0.18453098860096923, \"macro_f1\": 0.41773886562618956}, {\"mcc\": 0.15682031644184682, \"macro_f1\": 0.40758568023511443}, {\"mcc\": 0.24128556846842994, \"macro_f1\": 0.49396620612659603}, {\"mcc\": 0.11137908895022659, \"macro_f1\": 0.37302299418456325}, {\"mcc\": 0.1039940460845732, \"macro_f1\": 0.3811414493491874}, {\"mcc\": 0.09595262328327032, \"macro_f1\": 0.3611132538107784}, {\"mcc\": 0.18632184285487152, \"macro_f1\": 0.4490411806226592}, {\"mcc\": 0.17288943192655423, \"macro_f1\": 0.40574907225447077}, {\"mcc\": 0.0783564049715932, \"macro_f1\": 0.35301964350161474}]"}}, "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": 15.030655619791197, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 11.860808006456576, "upper": 18.20050323312582, "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": 40.82891194787244, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 38.103886915480444, "upper": 43.55393698026444, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-is/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005850+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "scala-is", "languages": "[\"is\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": -0.0039032867270460056, \"macro_f1\": 0.32985749639953044}, {\"mcc\": 0.01490015648822481, \"macro_f1\": 0.3418115509264789}, {\"mcc\": 0.0199779663888682, \"macro_f1\": 0.38039014434982904}, {\"mcc\": -0.012488699821648266, \"macro_f1\": 0.33469557799511973}, {\"mcc\": 0.05985807651332, \"macro_f1\": 0.34304526916037487}, {\"mcc\": 0.03240518034779101, \"macro_f1\": 0.44925893180160537}, {\"mcc\": 0.04080798640204835, \"macro_f1\": 0.3355523553305178}, {\"mcc\": 0.019629711946873723, \"macro_f1\": 0.33033246466082283}, {\"mcc\": -0.011689952568322733, \"macro_f1\": 0.33847124435359727}, {\"mcc\": 0.024183099525625567, \"macro_f1\": 0.3479296263615963}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-is", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 1.8368023849573465, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 0.4018953001899561, "upper": 3.271709469724737, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-is", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 35.31344661339472, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 33.034656150392095, "upper": 37.59223707639734, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-it/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005881+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "scala-it", "languages": "[\"it\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.16408068131726714, \"macro_f1\": 0.4933184671564148}, {\"mcc\": 0.19545729192830913, \"macro_f1\": 0.5038263018745582}, {\"mcc\": 0.1995158291054873, \"macro_f1\": 0.5507672784953547}, {\"mcc\": 0.2037110800929873, \"macro_f1\": 0.48604942586079836}, {\"mcc\": 0.17523492823404238, \"macro_f1\": 0.5211861524858872}, {\"mcc\": 0.19929469415013762, \"macro_f1\": 0.5580574348974909}, {\"mcc\": 0.23862406436565609, \"macro_f1\": 0.5100774526464437}, {\"mcc\": 0.21474393810422499, \"macro_f1\": 0.5333524785661029}, {\"mcc\": 0.17015220749217236, \"macro_f1\": 0.467967832294208}, {\"mcc\": 0.18121660734794112, \"macro_f1\": 0.5213736201058736}]"}}, "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": 19.420313221382255, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 18.025860759343697, "upper": 20.814765683420813, "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": 51.45976444383133, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 49.70466018044455, "upper": 53.214868707218116, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-nb/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005911+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "scala-nb", "languages": "[\"nb\", \"no\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.27415708856148885, \"macro_f1\": 0.6149732620320856}, {\"mcc\": 0.2634238038787003, \"macro_f1\": 0.5891797654723754}, {\"mcc\": 0.2633939270730102, \"macro_f1\": 0.6048854598496464}, {\"mcc\": 0.18379567568261854, \"macro_f1\": 0.4734841300948696}, {\"mcc\": 0.1621020991662665, \"macro_f1\": 0.528456984733026}, {\"mcc\": 0.23249280682078804, \"macro_f1\": 0.5920217262456604}, {\"mcc\": 0.21064300830935112, \"macro_f1\": 0.5660036166365281}, {\"mcc\": 0.2047904206868231, \"macro_f1\": 0.5535489549495963}, {\"mcc\": 0.23744750575901905, \"macro_f1\": 0.6182437649395021}, {\"mcc\": 0.16942467071364473, \"macro_f1\": 0.512251281837687}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-nb", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 22.016710066517103, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 19.511662317319125, "upper": 24.52175781571508, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-nb", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 56.53048946790976, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 53.54638720956, "upper": 59.51459172625952, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-nl/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005941+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "scala-nl", "languages": "[\"nl\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.3651192147130131, \"macro_f1\": 0.6195869777886016}, {\"mcc\": 0.30645869134641945, \"macro_f1\": 0.5803473876823679}, {\"mcc\": 0.2976379705567591, \"macro_f1\": 0.5327138969692315}, {\"mcc\": 0.3727214015167716, \"macro_f1\": 0.6398712893723091}, {\"mcc\": 0.40242227284698, \"macro_f1\": 0.6557357684793966}, {\"mcc\": 0.26266086055579924, \"macro_f1\": 0.5227095742132466}, {\"mcc\": 0.3556054472117256, \"macro_f1\": 0.6134633532557408}, {\"mcc\": 0.414775217432715, \"macro_f1\": 0.6484057483736545}, {\"mcc\": 0.27937867155326024, \"macro_f1\": 0.5197170170371863}, {\"mcc\": 0.4038087241113363, \"macro_f1\": 0.6619933232191366}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 34.6058847184478, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 31.166509802559744, "upper": 38.04525963433585, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 59.945443363908716, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 56.44067498705425, "upper": 63.45021174076318, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-nn/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.005972+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "scala-nn", "languages": "[\"nn\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.12089069101912392, \"macro_f1\": 0.5594540978512871}, {\"mcc\": 0.19019826350495633, \"macro_f1\": 0.5942050287738321}, {\"mcc\": 0.18561458019901514, \"macro_f1\": 0.5304116211414385}, {\"mcc\": 0.16246209391128089, \"macro_f1\": 0.564822236056798}, {\"mcc\": 0.08584544865656725, \"macro_f1\": 0.46738437382777787}, {\"mcc\": 0.16362794390895385, \"macro_f1\": 0.5604299496412908}, {\"mcc\": 0.14977375428102815, \"macro_f1\": 0.5706813448206401}, {\"mcc\": 0.12795223164553113, \"macro_f1\": 0.5609290047309716}, {\"mcc\": 0.15972898520780254, \"macro_f1\": 0.5733719547887588}, {\"mcc\": 0.14935539112307988, \"macro_f1\": 0.5619687731644931}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-nn", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 14.954493834573391, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 13.019961277855266, "upper": 16.889026391291516, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-nn", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 55.43658384797288, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 53.30677240934556, "upper": 57.56639528660019, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-pt/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.006002+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "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\": 0.07980167967757935, \"macro_f1\": 0.38624346235406803}, {\"mcc\": 0.14775291944191551, \"macro_f1\": 0.5103635192196078}, {\"mcc\": 0.11432083046023289, \"macro_f1\": 0.4396303747148631}, {\"mcc\": 0.161323557821365, \"macro_f1\": 0.4785386999171485}, {\"mcc\": 0.10902210981557402, \"macro_f1\": 0.4475087437003109}, {\"mcc\": 0.1787917508640964, \"macro_f1\": 0.535784408320545}, {\"mcc\": 0.14022618178898605, \"macro_f1\": 0.5339754087211299}, {\"mcc\": 0.1302635670511642, \"macro_f1\": 0.43721666939756404}, {\"mcc\": 0.14602551886198933, \"macro_f1\": 0.4864620462316944}, {\"mcc\": 0.11851959461084323, \"macro_f1\": 0.4433840055295405}]"}}, "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": 13.26047710393746, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 11.49428147062541, "upper": 15.026672737249509, "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": 46.99107338106472, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 44.02433786675531, "upper": 49.957808895374136, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-sv/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.006033+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "scala-sv", "languages": "[\"sv\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.1435023788432527, \"macro_f1\": 0.5098154971854946}, {\"mcc\": 0.20955085338853546, \"macro_f1\": 0.5581721492041309}, {\"mcc\": 0.21094582826373956, \"macro_f1\": 0.5872221099779318}, {\"mcc\": 0.1863566032423336, \"macro_f1\": 0.533025886917887}, {\"mcc\": 0.19258910481759012, \"macro_f1\": 0.5672455776700006}, {\"mcc\": 0.19347840392225044, \"macro_f1\": 0.5948554174920292}, {\"mcc\": 0.19299264492231064, \"macro_f1\": 0.5431867578937539}, {\"mcc\": 0.22348202924316143, \"macro_f1\": 0.5899161725802023}, {\"mcc\": 0.2502894719818384, \"macro_f1\": 0.5715489852817222}, {\"mcc\": 0.18942176592043197, \"macro_f1\": 0.5724307992893805}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-sv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 19.926090845454443, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 18.207118549910984, "upper": 21.6450631409979, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-sv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 56.274193534925324, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 54.589625235682824, "upper": 57.958761834167824, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scandiqa-da/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.006063+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "scandiqa-da", "languages": "[\"da\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 65.85235471599108, \"em\": 58.63636363636363}, {\"f1\": 65.62848237601838, \"em\": 58.83244882486732}, {\"f1\": 67.94869312061356, \"em\": 61.22766122766123}, {\"f1\": 66.62927224009118, \"em\": 60.273972602739725}, {\"f1\": 67.43399428586847, \"em\": 61.680801850424054}, {\"f1\": 65.66550761359686, \"em\": 57.86259541984733}, {\"f1\": 65.94973523921858, \"em\": 58.03432137285491}, {\"f1\": 64.39958057440825, \"em\": 57.704402515723274}, {\"f1\": 66.37778152993242, \"em\": 60.139318885448915}, {\"f1\": 67.29333222252613, \"em\": 58.7962962962963}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "scandiqa-da", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 66.31787339182651, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 65.66813351508225, "upper": 66.96761326857077, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "scandiqa-da", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 59.31881826322267, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 58.43838346092886, "upper": 60.19925306551647, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scandiqa-sv/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.006092+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "scandiqa-sv", "languages": "[\"sv\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 65.38168649532287, \"em\": 59.24242424242424}, {\"f1\": 63.7713363325458, \"em\": 55.724033358605006}, {\"f1\": 64.51888179160906, \"em\": 58.35275835275835}, {\"f1\": 65.12292909486034, \"em\": 58.44748858447488}, {\"f1\": 65.04539500038162, \"em\": 58.134155744024675}, {\"f1\": 63.67233924505921, \"em\": 57.93893129770992}, {\"f1\": 65.59076371646445, \"em\": 57.176287051482056}, {\"f1\": 65.17229247258985, \"em\": 58.0188679245283}, {\"f1\": 66.55140781253846, \"em\": 59.28792569659443}, {\"f1\": 65.56603730573173, \"em\": 57.94753086419753}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "scandiqa-sv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 65.03930692671034, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 64.50225541720955, "upper": 65.57635843621112, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "scandiqa-sv", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 58.02704031167995, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 57.39350548013341, "upper": 58.66057514322648, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scandisent-fi/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.006122+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "scandisent-fi", "languages": "[\"fi\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.9193776706944911, \"macro_f1\": 0.9593010129015962}, {\"mcc\": 0.9151989383111448, \"macro_f1\": 0.957028627235549}, {\"mcc\": 0.896665308113475, \"macro_f1\": 0.9476459478862926}, {\"mcc\": 0.9178597981022387, \"macro_f1\": 0.9582811588194201}, {\"mcc\": 0.9098712277829433, \"macro_f1\": 0.9545893132391807}, {\"mcc\": 0.917015824959446, \"macro_f1\": 0.9579807233514648}, {\"mcc\": 0.903951881168056, \"macro_f1\": 0.9511584136786968}, {\"mcc\": 0.9137457277071387, \"macro_f1\": 0.9564492594161584}, {\"mcc\": 0.9243625290797913, \"macro_f1\": 0.9618834915317327}, {\"mcc\": 0.9247729342961707, \"macro_f1\": 0.9623752081405224}]"}}, "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": 91.42821840214894, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 90.88333701946213, "upper": 91.97309978483575, "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": 95.66693156200614, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 95.38419319700813, "upper": 95.94966992700415, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "sentiment-headlines-es/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.006153+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "sentiment-headlines-es", "languages": "[\"es\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.3670182091287875, \"macro_f1\": 0.5180904982090554}, {\"mcc\": 0.44748047047923106, \"macro_f1\": 0.6280508823589799}, {\"mcc\": 0.46253019201830836, \"macro_f1\": 0.6261034768849726}, {\"mcc\": 0.33299924526800767, \"macro_f1\": 0.50121987255332}, {\"mcc\": 0.40534987690661667, \"macro_f1\": 0.566452897393626}, {\"mcc\": 0.429489819335752, \"macro_f1\": 0.6069676622343497}, {\"mcc\": 0.36435602632996905, \"macro_f1\": 0.4870488558439822}, {\"mcc\": 0.43093323226363933, \"macro_f1\": 0.5908263558876987}, {\"mcc\": 0.3821493992170224, \"macro_f1\": 0.5738076343476605}, {\"mcc\": 0.40505793653117395, \"macro_f1\": 0.5544935346292306}]"}}, "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": 40.273644074785075, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 37.73182527159274, "upper": 42.81546287797741, "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": 56.53061670342876, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 53.419813094638975, "upper": 59.64142031221855, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "sentipolc16/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.006182+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "sentipolc16", "languages": "[\"it\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.5604059034635583, \"macro_f1\": 0.6503712231409673}, {\"mcc\": 0.5556853309168753, \"macro_f1\": 0.6402827689590734}, {\"mcc\": 0.5361186589676173, \"macro_f1\": 0.602024094103666}, {\"mcc\": 0.5309061060309535, \"macro_f1\": 0.5871892949523861}, {\"mcc\": 0.483472251554503, \"macro_f1\": 0.5335811151208579}, {\"mcc\": 0.5333792779397029, \"macro_f1\": 0.585950203351779}, {\"mcc\": 0.5460821250497293, \"macro_f1\": 0.6166373299185056}, {\"mcc\": 0.5456107957503291, \"macro_f1\": 0.6258728176892322}, {\"mcc\": 0.5222575951599262, \"macro_f1\": 0.6115676468026842}, {\"mcc\": 0.4696452577867943, \"macro_f1\": 0.5544038619046406}]"}}, "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": 52.83563302619989, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 50.99041796310133, "upper": 54.68084808929846, "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": 60.07880355943793, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 57.80713345090046, "upper": 62.3504736679754, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "squad-it/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.006212+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "squad-it", "languages": "[\"it\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 73.82306705251032, \"em\": 59.166666666666664}, {\"f1\": 73.89705459040914, \"em\": 56.10310841546626}, {\"f1\": 71.32666992073554, \"em\": 55.78865578865579}, {\"f1\": 73.42710589542854, \"em\": 57.534246575342465}, {\"f1\": 71.98117533036378, \"em\": 54.51040863531226}, {\"f1\": 73.61069972362704, \"em\": 57.099236641221374}, {\"f1\": 75.0509165253939, \"em\": 58.65834633385335}, {\"f1\": 72.28203345550267, \"em\": 52.75157232704402}, {\"f1\": 73.14678626404137, \"em\": 57.89473684210526}, {\"f1\": 72.77881700438229, \"em\": 54.398148148148145}]"}}, "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": 73.13243257623945, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 72.46320821964193, "upper": 73.80165693283698, "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": 56.39051263738155, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 55.11501863455411, "upper": 57.666006640208984, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "squad-nl/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.006242+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "squad-nl", "languages": "[\"nl\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 80.02937761081301, \"em\": 65.37878787878788}, {\"f1\": 77.45311962579477, \"em\": 63.07808946171342}, {\"f1\": 76.7663288436668, \"em\": 63.63636363636363}, {\"f1\": 77.08269645394365, \"em\": 63.31811263318112}, {\"f1\": 78.0018430487908, \"em\": 63.68542791056284}, {\"f1\": 80.72589481363232, \"em\": 65.0381679389313}, {\"f1\": 75.85365525415517, \"em\": 61.38845553822153}, {\"f1\": 78.98997112910061, \"em\": 66.11635220125787}, {\"f1\": 77.797913870114, \"em\": 65.3250773993808}, {\"f1\": 79.25173393750616, \"em\": 62.885802469135804}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "squad-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 78.19525345875174, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 77.24792859609252, "upper": 79.14257832141095, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "squad-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 63.985063706753614, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 63.088803915150635, "upper": 64.8813234983566, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "squad/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.006271+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "squad", "languages": "[\"en\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 89.38949560283899, \"em\": 82.65151515151516}, {\"f1\": 87.27383813328278, \"em\": 77.8620166793025}, {\"f1\": 89.38141607743991, \"em\": 80.88578088578089}, {\"f1\": 87.55594868485177, \"em\": 79.68036529680366}, {\"f1\": 89.0654760525255, \"em\": 81.72706245181188}, {\"f1\": 85.13090889425894, \"em\": 74.80916030534351}, {\"f1\": 86.88430827235591, \"em\": 76.98907956318253}, {\"f1\": 86.95527718960264, \"em\": 77.59433962264151}, {\"f1\": 86.3425100483854, \"em\": 75.15479876160991}, {\"f1\": 85.99682754093115, \"em\": 76.00308641975309}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "squad", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 87.3976006496473, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 86.48766513187304, "upper": 88.30753616742156, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "squad", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 78.33572051377446, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 76.61928420871948, "upper": 80.05215681882945, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "sst2-pt/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.006302+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "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\": 0.7909572236211772, \"macro_f1\": 0.8892682702760637}, {\"mcc\": 0.8317244842369953, \"macro_f1\": 0.9136590282808075}, {\"mcc\": 0.8205028290051564, \"macro_f1\": 0.906278330621301}, {\"mcc\": 0.8292795443808995, \"macro_f1\": 0.9110614802407098}, {\"mcc\": 0.7891724497931797, \"macro_f1\": 0.8889186483079851}, {\"mcc\": 0.7928216307093814, \"macro_f1\": 0.8920880912951223}, {\"mcc\": 0.8155730586398396, \"macro_f1\": 0.9054286966635987}, {\"mcc\": 0.8319029386119076, \"macro_f1\": 0.912534574768227}, {\"mcc\": 0.836507518312273, \"macro_f1\": 0.9171414529021391}, {\"mcc\": 0.7870291948076285, \"macro_f1\": 0.8868419560509824}]"}}, "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": 81.25470872118437, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 79.99431685621421, "upper": 82.51510058615453, "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": 90.23220529406937, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 89.50218369732082, "upper": 90.96222689081793, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "sst5/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.006332+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "sst5", "languages": "[\"en\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.6788675171077196, \"macro_f1\": 0.6331714019126877}, {\"mcc\": 0.6979625269002177, \"macro_f1\": 0.6595346210782775}, {\"mcc\": 0.696602391173382, \"macro_f1\": 0.6704272817417379}, {\"mcc\": 0.6987529765259739, \"macro_f1\": 0.6595893841418953}, {\"mcc\": 0.6711677122726, \"macro_f1\": 0.6340092408394153}, {\"mcc\": 0.6873548295419842, \"macro_f1\": 0.6473379129260949}, {\"mcc\": 0.6956946988005535, \"macro_f1\": 0.6477897030733737}, {\"mcc\": 0.685471520387633, \"macro_f1\": 0.6379292139710803}, {\"mcc\": 0.6965364119064966, \"macro_f1\": 0.648315336782638}, {\"mcc\": 0.6775065882151683, \"macro_f1\": 0.6284509126898036}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "sst5", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 68.85917172831728, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 68.23898448276033, "upper": 69.47935897387423, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "sst5", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 64.66555009157004, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 63.82580305974926, "upper": 65.50529712339082, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "suc3/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.006363+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "suc3", "languages": "[\"sv\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.6448598130841121, \"micro_f1\": 0.2919766206163656}, {\"micro_f1_no_misc\": 0.6317195325542571, \"micro_f1\": 0.5391032325338895}, {\"micro_f1_no_misc\": 0.6172177539469765, \"micro_f1\": 0.3959971408148677}, {\"micro_f1_no_misc\": 0.6837853433352568, \"micro_f1\": 0.4315808107629669}, {\"micro_f1_no_misc\": 0.662141314409133, \"micro_f1\": 0.4771446462116468}, {\"micro_f1_no_misc\": 0.6146978021978021, \"micro_f1\": 0.3822937625754527}, {\"micro_f1_no_misc\": 0.6080340839926962, \"micro_f1\": 0.4522591645353794}, {\"micro_f1_no_misc\": 0.5708006279434851, \"micro_f1\": 0.36925484060238606}, {\"micro_f1_no_misc\": 0.590738423028786, \"micro_f1\": 0.4499661170092613}, {\"micro_f1_no_misc\": 0.6057661159701976, \"micro_f1\": 0.35400959561343387}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "suc3", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 62.29760810462703, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 60.214129593716194, "upper": 64.38108661553787, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "suc3", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 41.4358593127565, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 37.07644346396713, "upper": 45.79527516154587, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "swerec/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.006394+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "swerec", "languages": "[\"sv\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.7873283226154085, \"macro_f1\": 0.7796206532598878}, {\"mcc\": 0.7935489277220236, \"macro_f1\": 0.7869817732662195}, {\"mcc\": 0.7971066204904177, \"macro_f1\": 0.7689655737927666}, {\"mcc\": 0.7712640447576834, \"macro_f1\": 0.7607465969101025}, {\"mcc\": 0.7848358925056141, \"macro_f1\": 0.7930966571439497}, {\"mcc\": 0.803937940507179, \"macro_f1\": 0.8037330864970493}, {\"mcc\": 0.8060021966776854, \"macro_f1\": 0.769301060455955}, {\"mcc\": 0.781448290375713, \"macro_f1\": 0.7587982361893023}, {\"mcc\": 0.7987760308379248, \"macro_f1\": 0.7910316582313929}, {\"mcc\": 0.7904356361938262, \"macro_f1\": 0.7868919078050781}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "swerec", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 79.14683902683475, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 78.48472643676827, "upper": 79.80895161690124, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "swerec", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 77.99167203551704, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 77.06558924017547, "upper": 78.91775483085861, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "turku-ner-fi/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.006424+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "turku-ner-fi", "languages": "[\"fi\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.5733788395904437, \"micro_f1\": 0.32799999999999996}, {\"micro_f1_no_misc\": 0.5347442680776014, \"micro_f1\": 0.29975515914655476}, {\"micro_f1_no_misc\": 0.5438005390835579, \"micro_f1\": 0.32111492936235203}, {\"micro_f1_no_misc\": 0.56687662097073, \"micro_f1\": 0.2981186685962373}, {\"micro_f1_no_misc\": 0.5304532577903683, \"micro_f1\": 0.2529251482609392}, {\"micro_f1_no_misc\": 0.5881946841560235, \"micro_f1\": 0.3463271302644466}, {\"micro_f1_no_misc\": 0.5387647831800263, \"micro_f1\": 0.2843182165216064}, {\"micro_f1_no_misc\": 0.584089323098395, \"micro_f1\": 0.3822555727212536}, {\"micro_f1_no_misc\": 0.5880885562831306, \"micro_f1\": 0.34023521616697033}, {\"micro_f1_no_misc\": 0.5279106858054226, \"micro_f1\": 0.22725390031754797}]"}}, "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": 55.76301558035699, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 54.218567450215716, "upper": 57.30746371049827, "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": 30.803039413579082, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 27.964715689074374, "upper": 33.64136313808379, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "tydiqa-fi/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.006455+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "tydiqa-fi", "languages": "[\"fi\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 70.87775118396142, \"em\": 53.18181818181818}, {\"f1\": 68.48313815445752, \"em\": 52.69143290371493}, {\"f1\": 73.04656670976426, \"em\": 56.64335664335665}, {\"f1\": 71.23925610510638, \"em\": 54.10958904109589}, {\"f1\": 71.79904358544998, \"em\": 54.51040863531226}, {\"f1\": 69.34234205253895, \"em\": 50.534351145038165}, {\"f1\": 69.74328952593302, \"em\": 53.74414976599064}, {\"f1\": 71.60379644952518, \"em\": 55.660377358490564}, {\"f1\": 70.54858310022458, \"em\": 55.3405572755418}, {\"f1\": 72.40212415573829, \"em\": 55.324074074074076}]"}}, "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": 70.90858910226996, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 70.0317685754538, "upper": 71.78540962908612, "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": 54.17401150244332, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 53.086213844174246, "upper": 55.261809160712396, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "winogrande-is/CohereForAI/aya-23-35B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.006486+00:00", "retrieved_timestamp": "1781766557", "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/aya-23-35B", "id": "CohereForAI/aya-23-35B", "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/aya-23-35B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0.dev0", "additional_details": {"dataset": "winogrande-is", "languages": "[\"is\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.52.4", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": -0.020570474480932494, \"accuracy\": 0.5234375}, {\"mcc\": 0.00030878059236219243, \"accuracy\": 0.47433035714285715}, {\"mcc\": -0.07093144483940146, \"accuracy\": 0.5}, {\"mcc\": -0.00036696418569727283, \"accuracy\": 0.5022321428571429}, {\"mcc\": 0.018819436834144457, \"accuracy\": 0.5089285714285714}, {\"mcc\": -0.0034897728928942567, \"accuracy\": 0.4810267857142857}, {\"mcc\": 0.011072907423152291, \"accuracy\": 0.5457589285714286}, {\"mcc\": 0.06939584572626656, \"accuracy\": 0.5323660714285714}, {\"mcc\": -0.07326066865814246, \"accuracy\": 0.5379464285714286}, {\"mcc\": 0.04019593133708423, \"accuracy\": 0.4732142857142857}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "winogrande-is", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": -0.2882642314405822, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": -3.033751631427454, "upper": 2.4572231685462897, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "winogrande-is", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 50.792410714285715, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 49.14945403785599, "upper": 52.43536739071544, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
Xet Storage Details
- Size:
- 233 kB
- Xet hash:
- 7a2b7a472e077a92111c4ea35df9c311fcdb3fffcf9c93b3cfbb49e2c36a2fd3
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.