| {"schema_version": "0.2.1", "evaluation_id": "allocine/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.049926+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "allocine", "languages": "[\"fr\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.9412566223435385, \"macro_f1\": 0.9706273807884712}, {\"mcc\": 0.9288185390248295, \"macro_f1\": 0.9643076015135081}, {\"mcc\": 0.9449255410990934, \"macro_f1\": 0.9724288339469982}, {\"mcc\": 0.9521143673539078, \"macro_f1\": 0.9760569506348777}, {\"mcc\": 0.9387521645000044, \"macro_f1\": 0.9692072631566135}, {\"mcc\": 0.9358237863519673, \"macro_f1\": 0.9677557251908397}, {\"mcc\": 0.9599347173506978, \"macro_f1\": 0.9799615066575822}, {\"mcc\": 0.9413527549652895, \"macro_f1\": 0.9706726670593526}, {\"mcc\": 0.9469906595087448, \"macro_f1\": 0.9734943917169974}, {\"mcc\": 0.9450482826745649, \"macro_f1\": 0.9725203950193215}]"}}, "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": 94.35017435172635, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 93.81636616247935, "upper": 94.88398254097335, "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": 97.17032715684562, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 96.90072599733051, "upper": 97.43992831636072, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "angry-tweets/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.049962+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.8.4"}}, "eval_library": {"name": "euroeval", "version": "15.6.1.dev0", "additional_details": {"dataset": "angry-tweets", "languages": "[\"da\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.6.0", "vllm_version": "0.8.4", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.40105862867096914, \"macro_f1\": 0.6024215167077295}, {\"mcc\": 0.3985824204881158, \"macro_f1\": 0.6070001693735362}, {\"mcc\": 0.4600319841799989, \"macro_f1\": 0.6442236290370401}, {\"mcc\": 0.4108294713096052, \"macro_f1\": 0.6048535305335826}, {\"mcc\": 0.39223520634209297, \"macro_f1\": 0.6033073300062475}, {\"mcc\": 0.41296098313930085, \"macro_f1\": 0.5800958548625406}, {\"mcc\": 0.38417192513953635, \"macro_f1\": 0.5930594804205915}, {\"mcc\": 0.3704147248341685, \"macro_f1\": 0.5841415433502294}, {\"mcc\": 0.4619891908866628, \"macro_f1\": 0.6121464449633534}, {\"mcc\": 0.3726120503869182, \"macro_f1\": 0.577804844455951}]"}}, "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": 40.648865853773685, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 38.66182203412321, "upper": 42.63590967342416, "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": 60.090543437108025, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 58.89066869968721, "upper": 61.29041817452884, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "conll-es/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.049994+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "conll-es", "languages": "[\"es\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.5146579804560261, \"micro_f1\": 0.4689056314646916}, {\"micro_f1_no_misc\": 0.3994480855467402, \"micro_f1\": 0.3920454545454546}, {\"micro_f1_no_misc\": 0.5616740088105727, \"micro_f1\": 0.4892512972572276}, {\"micro_f1_no_misc\": 0.5082651011895567, \"micro_f1\": 0.4728400053915622}, {\"micro_f1_no_misc\": 0.3999319843564019, \"micro_f1\": 0.38029465930018413}, {\"micro_f1_no_misc\": 0.4395120298203999, \"micro_f1\": 0.417986838898367}, {\"micro_f1_no_misc\": 0.5464162919862471, \"micro_f1\": 0.5127844241144734}, {\"micro_f1_no_misc\": 0.4836309523809524, \"micro_f1\": 0.43657951820984137}, {\"micro_f1_no_misc\": 0.5297627710668025, \"micro_f1\": 0.4911927528938098}, {\"micro_f1_no_misc\": 0.48867699642431467, \"micro_f1\": 0.4556630918127125}]"}}, "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": 48.719762020380145, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 45.16120084888765, "upper": 52.27832319187264, "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": 45.175436738883235, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 42.44373075892413, "upper": 47.90714271884234, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "danish-citizen-tests/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050028+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.2.0.dev0", "additional_details": {"dataset": "danish-citizen-tests", "languages": "[\"da\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.23142824443098764, \"accuracy\": 0.4419047619047619}, {\"mcc\": 0.29184177373625814, \"accuracy\": 0.4857142857142857}, {\"mcc\": 0.2421391335604608, \"accuracy\": 0.45904761904761904}, {\"mcc\": 0.20273009764840463, \"accuracy\": 0.43238095238095237}, {\"mcc\": 0.12364147344255975, \"accuracy\": 0.28}, {\"mcc\": 0.19318062451497867, \"accuracy\": 0.4380952380952381}, {\"mcc\": 0.21606783434673865, \"accuracy\": 0.42857142857142855}, {\"mcc\": 0.1578566201378191, \"accuracy\": 0.18476190476190477}, {\"mcc\": 0.19329662367091713, \"accuracy\": 0.3657142857142857}, {\"mcc\": 0.1122063274074489, \"accuracy\": 0.3676190476190476}]"}}, "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": 19.643887528965738, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 16.265261995491816, "upper": 23.02251306243966, "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": 38.838095238095235, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 33.08627086192371, "upper": 44.58991961426676, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "dbrd/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050061+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.8.4"}}, "eval_library": {"name": "euroeval", "version": "15.7.0.dev0", "additional_details": {"dataset": "dbrd", "languages": "[\"nl\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.6.0", "vllm_version": "0.8.4", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.9016682303027742, \"macro_f1\": 0.9496906105150688}, {\"mcc\": 0.9073172017752357, \"macro_f1\": 0.9536074300600295}, {\"mcc\": 0.8782726825386247, \"macro_f1\": 0.9359581864399538}, {\"mcc\": 0.9054493581342044, \"macro_f1\": 0.952059925093633}, {\"mcc\": 0.90143474208258, \"macro_f1\": 0.95019512250947}, {\"mcc\": 0.8791188835612134, \"macro_f1\": 0.9369933168442569}, {\"mcc\": 0.9098676835625585, \"macro_f1\": 0.9535821944198908}, {\"mcc\": 0.8755644119021757, \"macro_f1\": 0.9355463217896425}, {\"mcc\": 0.8989059859050618, \"macro_f1\": 0.9487171537829565}, {\"mcc\": 0.8448594429470583, \"macro_f1\": 0.9177137871689911}]"}}, "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": 89.02458622711487, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 87.7542113898777, "upper": 90.29496106435204, "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": 94.34064048623891, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 93.62055921037651, "upper": 95.06072176210131, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "eltec/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050092+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "eltec", "languages": "[\"fr\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.4837465564738292, \"micro_f1\": 0.4707405489383739}, {\"micro_f1_no_misc\": 0.49760282614181167, \"micro_f1\": 0.4851581508515814}, {\"micro_f1_no_misc\": 0.5394149727317799, \"micro_f1\": 0.5225140712945592}, {\"micro_f1_no_misc\": 0.556762092793682, \"micro_f1\": 0.5403493256688039}, {\"micro_f1_no_misc\": 0.5444416307926057, \"micro_f1\": 0.5343399902581589}, {\"micro_f1_no_misc\": 0.520822880080281, \"micro_f1\": 0.5004677268475212}, {\"micro_f1_no_misc\": 0.5426501519046507, \"micro_f1\": 0.5261726716519374}, {\"micro_f1_no_misc\": 0.46757405924739787, \"micro_f1\": 0.4523570712136409}, {\"micro_f1_no_misc\": 0.4921654251220139, \"micro_f1\": 0.4817378849367391}, {\"micro_f1_no_misc\": 0.49109014675052415, \"micro_f1\": 0.48152679226816736}]"}}, "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": 51.36270742038575, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 49.44583158097827, "upper": 53.279583259793235, "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": 49.953642339294824, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 48.10362730857894, "upper": 51.803657370010704, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "fquad/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050125+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "fquad", "languages": "[\"fr\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 64.06368572553234, \"em\": 35.378787878787875}, {\"f1\": 65.06327349411048, \"em\": 38.43821076573162}, {\"f1\": 65.43830226461867, \"em\": 36.82983682983683}, {\"f1\": 65.50921894027987, \"em\": 38.12785388127854}, {\"f1\": 64.75961710135354, \"em\": 38.93600616808018}, {\"f1\": 66.29031074429776, \"em\": 38.778625954198475}, {\"f1\": 64.71657944113194, \"em\": 38.22152886115445}, {\"f1\": 64.7021170018795, \"em\": 38.600628930817614}, {\"f1\": 62.849133454979125, \"em\": 37.61609907120743}, {\"f1\": 66.58443506306544, \"em\": 39.583333333333336}]"}}, "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": 64.99766732312486, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 64.3326633651781, "upper": 65.66267128107161, "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": 38.051091167442635, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 37.30707020248393, "upper": 38.79511213240134, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "goldenswag-pt/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050155+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.2"}}, "eval_library": {"name": "euroeval", "version": "15.13.0", "additional_details": {"dataset": "goldenswag-pt", "languages": "[\"pt\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.53.2", "torch_version": "2.7.0", "vllm_version": "0.9.2", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.29158706132662876, \"accuracy\": 0.41943359375}, {\"mcc\": 0.1698437349634755, \"accuracy\": 0.3408203125}, {\"mcc\": 0.17689664623494938, \"accuracy\": 0.32861328125}, {\"mcc\": 0.27625392645413294, \"accuracy\": 0.43212890625}, {\"mcc\": 0.2952030525240519, \"accuracy\": 0.4541015625}, {\"mcc\": 0.24784996308017707, \"accuracy\": 0.42822265625}, {\"mcc\": 0.3131421762554874, \"accuracy\": 0.45703125}, {\"mcc\": 0.15690426874703897, \"accuracy\": 0.3486328125}, {\"mcc\": 0.2964610573383719, \"accuracy\": 0.443359375}, {\"mcc\": 0.19600816366138024, \"accuracy\": 0.3818359375}]"}}, "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": 24.20150050585694, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 20.42990984817611, "upper": 27.973091163537774, "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": 40.341796875, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 37.29723392509928, "upper": 43.38635982490072, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "harem/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050185+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.2"}}, "eval_library": {"name": "euroeval", "version": "15.13.0", "additional_details": {"dataset": "harem", "languages": "[\"pt\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.53.2", "torch_version": "2.7.0", "vllm_version": "0.9.2", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.45793000744601636, \"micro_f1\": 0.3617791019365822}, {\"micro_f1_no_misc\": 0.468317247167436, \"micro_f1\": 0.37319683573755236}, {\"micro_f1_no_misc\": 0.39555745407945325, \"micro_f1\": 0.28322309079975944}, {\"micro_f1_no_misc\": 0.4854000758437618, \"micro_f1\": 0.3793016829942225}, {\"micro_f1_no_misc\": 0.4725370531822145, \"micro_f1\": 0.35464566929133856}, {\"micro_f1_no_misc\": 0.38783542039356, \"micro_f1\": 0.2949240459429418}, {\"micro_f1_no_misc\": 0.4918793503480278, \"micro_f1\": 0.41232780761148724}, {\"micro_f1_no_misc\": 0.494945713216024, \"micro_f1\": 0.37112874328129}, {\"micro_f1_no_misc\": 0.4992526158445441, \"micro_f1\": 0.3852040816326531}, {\"micro_f1_no_misc\": 0.47287390029325516, \"micro_f1\": 0.3883575883575884}]"}}, "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": 46.265288378142934, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 43.81115457681022, "upper": 48.71942217947565, "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": 36.04088647585416, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 33.50987159902113, "upper": 38.571901352687185, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "hellaswag-es/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050215+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "hellaswag-es", "languages": "[\"es\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.39044227925742364, \"accuracy\": 0.5322265625}, {\"mcc\": 0.27230529523148866, \"accuracy\": 0.4091796875}, {\"mcc\": 0.2968144036652805, \"accuracy\": 0.453125}, {\"mcc\": 0.3634990986253651, \"accuracy\": 0.515625}, {\"mcc\": 0.3366425750606613, \"accuracy\": 0.48876953125}, {\"mcc\": 0.338855539203195, \"accuracy\": 0.49365234375}, {\"mcc\": 0.3680043253223694, \"accuracy\": 0.5224609375}, {\"mcc\": 0.3008625676741764, \"accuracy\": 0.4423828125}, {\"mcc\": 0.4061376817428374, \"accuracy\": 0.53955078125}, {\"mcc\": 0.2672230492077776, \"accuracy\": 0.41015625}]"}}, "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": 33.40786814990575, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 30.400205004033474, "upper": 36.41553129577803, "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": 48.0712890625, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 45.03239878031321, "upper": 51.11017934468679, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "hellaswag-fi/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050247+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "hellaswag-fi", "languages": "[\"fi\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": -0.029724904756487, \"accuracy\": 0.25375826819001807}, {\"mcc\": 0.012079643789568347, \"accuracy\": 0.22850270595309682}, {\"mcc\": -0.024341636540020653, \"accuracy\": 0.24413710162357186}, {\"mcc\": 0.005633540951275163, \"accuracy\": 0.25676488274203246}, {\"mcc\": 0.015009644905165095, \"accuracy\": 0.2579675285628382}, {\"mcc\": 0.004493334996723861, \"accuracy\": 0.2579675285628382}, {\"mcc\": 0.010974634247305862, \"accuracy\": 0.25917017438364404}, {\"mcc\": 0.019141768283891972, \"accuracy\": 0.26638604930847865}, {\"mcc\": -0.011060398898691122, \"accuracy\": 0.2627781118460613}, {\"mcc\": 0.022588870622802973, \"accuracy\": 0.22248947684906795}]"}}, "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": 0.24794497601534501, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": -0.8755570056633725, "upper": 1.3714469576940624, "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": 25.09921828021648, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 24.18777310082181, "upper": 26.01066345961115, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "hellaswag-fr/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050277+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "hellaswag-fr", "languages": "[\"fr\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.32556109012142237, \"accuracy\": 0.49365234375}, {\"mcc\": 0.22608125364142534, \"accuracy\": 0.37255859375}, {\"mcc\": 0.20275752785823736, \"accuracy\": 0.36865234375}, {\"mcc\": 0.34167620422737605, \"accuracy\": 0.50439453125}, {\"mcc\": 0.3484034876997632, \"accuracy\": 0.49462890625}, {\"mcc\": 0.2869025260364617, \"accuracy\": 0.45654296875}, {\"mcc\": 0.35545089070620517, \"accuracy\": 0.49951171875}, {\"mcc\": 0.2760534302031242, \"accuracy\": 0.41357421875}, {\"mcc\": 0.30060359162883005, \"accuracy\": 0.47509765625}, {\"mcc\": 0.22933995329318319, \"accuracy\": 0.3916015625}]"}}, "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": 28.928299554160287, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 25.51356550225097, "upper": 32.3430336060696, "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": 44.7021484375, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 41.29207032768883, "upper": 48.11222654731117, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "hellaswag-it/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050306+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "hellaswag-it", "languages": "[\"it\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.3303925268482278, \"accuracy\": 0.478515625}, {\"mcc\": 0.2710553432723915, \"accuracy\": 0.41162109375}, {\"mcc\": 0.2342380408942016, \"accuracy\": 0.4072265625}, {\"mcc\": 0.3631058833262649, \"accuracy\": 0.51123046875}, {\"mcc\": 0.305576834962474, \"accuracy\": 0.4619140625}, {\"mcc\": 0.2104435174852811, \"accuracy\": 0.3642578125}, {\"mcc\": 0.4030653307627481, \"accuracy\": 0.54345703125}, {\"mcc\": 0.3010019885343087, \"accuracy\": 0.46142578125}, {\"mcc\": 0.32366379074741997, \"accuracy\": 0.49072265625}, {\"mcc\": 0.28485558749045753, \"accuracy\": 0.42822265625}]"}}, "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": 30.273988443237748, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 26.728026594102403, "upper": 33.81995029237309, "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": 45.5859375, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 42.25377634694979, "upper": 48.91809865305021, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "icelandic-knowledge/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050335+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.2.0.dev0", "additional_details": {"dataset": "icelandic-knowledge", "languages": "[\"is\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": -0.02476372023214276, \"accuracy\": 0.23046875}, {\"mcc\": 0.003916780158102947, \"accuracy\": 0.2412109375}, {\"mcc\": 0.0, \"accuracy\": 0.240234375}, {\"mcc\": -0.012426135741128809, \"accuracy\": 0.2451171875}, {\"mcc\": 0.023394352121291182, \"accuracy\": 0.2626953125}, {\"mcc\": -0.02719791453680392, \"accuracy\": 0.248046875}, {\"mcc\": -0.013842950827011353, \"accuracy\": 0.251953125}, {\"mcc\": 0.010863200882665229, \"accuracy\": 0.2626953125}, {\"mcc\": -0.009118319940281843, \"accuracy\": 0.25}, {\"mcc\": 0.005846654370286423, \"accuracy\": 0.265625}]"}}, "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": -0.43328053745022904, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": -1.4260990880700133, "upper": 0.5595380131695551, "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": 24.98046875, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 24.27934220153855, "upper": 25.68159529846145, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "idioms-no/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050364+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "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": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.017899153336076064, \"accuracy\": 0.248046875}, {\"mcc\": -0.013080330383818638, \"accuracy\": 0.2421875}, {\"mcc\": 0.03370085258596593, \"accuracy\": 0.26708984375}, {\"mcc\": 0.0009166867629854564, \"accuracy\": 0.24951171875}, {\"mcc\": 0.030561519630114546, \"accuracy\": 0.27490234375}, {\"mcc\": 0.03378745333309022, \"accuracy\": 0.2734375}, {\"mcc\": -0.004043204457232986, \"accuracy\": 0.255859375}, {\"mcc\": -0.005569321557575823, \"accuracy\": 0.2490234375}, {\"mcc\": 0.0057637021916064814, \"accuracy\": 0.251953125}, {\"mcc\": -0.007056671916334288, \"accuracy\": 0.24169921875}]"}}, "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": 0.9287983952487696, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": -0.19739672596498858, "upper": 2.054993516462528, "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": 25.537109375, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 24.779098735900764, "upper": 26.295120014099236, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "life-in-the-uk/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050394+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "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": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.596084375399966, \"accuracy\": 0.705078125}, {\"mcc\": 0.6106079821343688, \"accuracy\": 0.712890625}, {\"mcc\": 0.6615087285243956, \"accuracy\": 0.75390625}, {\"mcc\": 0.585844143906438, \"accuracy\": 0.685546875}, {\"mcc\": 0.6279720576803661, \"accuracy\": 0.716796875}, {\"mcc\": 0.6208413106075856, \"accuracy\": 0.708984375}, {\"mcc\": 0.618171256048874, \"accuracy\": 0.716796875}, {\"mcc\": 0.6140534801340243, \"accuracy\": 0.72265625}, {\"mcc\": 0.5943894470868453, \"accuracy\": 0.693359375}, {\"mcc\": 0.6086763779736942, \"accuracy\": 0.712890625}]"}}, "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": 61.38149159496559, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 60.06598529791851, "upper": 62.69699789201267, "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": 71.2890625, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 70.15489185820712, "upper": 72.42323314179288, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mlqa-es/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050424+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "mlqa-es", "languages": "[\"es\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 58.455986368518765, \"em\": 28.043143297380585}, {\"f1\": 60.5834216106254, \"em\": 32.10161662817552}, {\"f1\": 64.75600788077128, \"em\": 38.793103448275865}, {\"f1\": 59.307329566365404, \"em\": 31.235431235431236}, {\"f1\": 62.717516579974465, \"em\": 34.54833597464342}, {\"f1\": 60.326692711121765, \"em\": 32.973805855161785}, {\"f1\": 57.505852898534364, \"em\": 26.188620420888544}, {\"f1\": 62.12978024824503, \"em\": 36.70886075949367}, {\"f1\": 61.21312106897404, \"em\": 34.045922406967534}, {\"f1\": 61.880720715694224, \"em\": 35.80819798917247}]"}}, "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": 60.88764296488247, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 59.56149227593299, "upper": 62.21379365383194, "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": 33.044703801559066, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 30.6570427459178, "upper": 35.432364857200334, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mmlu-es/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050454+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "mmlu-es", "languages": "[\"es\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.17944109851168774, \"accuracy\": 0.38427734375}, {\"mcc\": 0.23058721081042582, \"accuracy\": 0.4189453125}, {\"mcc\": 0.17164630816763235, \"accuracy\": 0.37158203125}, {\"mcc\": 0.18470797164503847, \"accuracy\": 0.38916015625}, {\"mcc\": 0.19706622000983504, \"accuracy\": 0.39990234375}, {\"mcc\": 0.19209583805710403, \"accuracy\": 0.3896484375}, {\"mcc\": 0.2072152878019228, \"accuracy\": 0.40966796875}, {\"mcc\": 0.218784629030617, \"accuracy\": 0.412109375}, {\"mcc\": 0.20205948039784113, \"accuracy\": 0.40283203125}, {\"mcc\": 0.22971029177616192, \"accuracy\": 0.42236328125}]"}}, "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": 20.133143362082663, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 18.86944652612949, "upper": 21.396840198035836, "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": 40.0048828125, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 38.99557398332906, "upper": 41.01419164167094, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mmlu-fr/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050483+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "mmlu-fr", "languages": "[\"fr\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.22616330902881426, \"accuracy\": 0.4169921875}, {\"mcc\": 0.21714155368996416, \"accuracy\": 0.40625}, {\"mcc\": 0.19295877075841095, \"accuracy\": 0.3857421875}, {\"mcc\": 0.24308241333853894, \"accuracy\": 0.4296875}, {\"mcc\": 0.22724054819082046, \"accuracy\": 0.4189453125}, {\"mcc\": 0.24107778034661967, \"accuracy\": 0.42822265625}, {\"mcc\": 0.21934003978365382, \"accuracy\": 0.4111328125}, {\"mcc\": 0.1585920064443684, \"accuracy\": 0.357421875}, {\"mcc\": 0.230291719115293, \"accuracy\": 0.4208984375}, {\"mcc\": 0.23192705511934417, \"accuracy\": 0.419921875}]"}}, "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": 21.878151958158277, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 20.30314621624382, "upper": 23.453157700072733, "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": 40.9521484375, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 39.57676951533654, "upper": 42.32752735966346, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mmlu-it/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050512+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "mmlu-it", "languages": "[\"it\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.19138824225087822, \"accuracy\": 0.39208984375}, {\"mcc\": 0.19080973640161306, \"accuracy\": 0.37646484375}, {\"mcc\": 0.15750834307384712, \"accuracy\": 0.36376953125}, {\"mcc\": 0.20643612544030732, \"accuracy\": 0.40576171875}, {\"mcc\": 0.19305329236955873, \"accuracy\": 0.400390625}, {\"mcc\": 0.1656532864396209, \"accuracy\": 0.36865234375}, {\"mcc\": 0.20278318678096935, \"accuracy\": 0.40234375}, {\"mcc\": 0.21912010503454868, \"accuracy\": 0.40771484375}, {\"mcc\": 0.21134043874838665, \"accuracy\": 0.4013671875}, {\"mcc\": 0.1743550573757673, \"accuracy\": 0.37841796875}]"}}, "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": 19.12447813915497, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 17.880294719258078, "upper": 20.368661559051862, "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": 38.9697265625, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 37.95414548998242, "upper": 39.98530763501758, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "mmlu-pt/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050541+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.2"}}, "eval_library": {"name": "euroeval", "version": "15.13.0", "additional_details": {"dataset": "mmlu-pt", "languages": "[\"pt\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "4.53.2", "torch_version": "2.7.0", "vllm_version": "0.9.2", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.22935704416040084, \"accuracy\": 0.4208984375}, {\"mcc\": 0.16829352190868171, \"accuracy\": 0.37255859375}, {\"mcc\": 0.16337148345863078, \"accuracy\": 0.36474609375}, {\"mcc\": 0.2208294213344168, \"accuracy\": 0.41357421875}, {\"mcc\": 0.16599275794490526, \"accuracy\": 0.35693359375}, {\"mcc\": 0.2006851902744328, \"accuracy\": 0.38232421875}, {\"mcc\": 0.17297685064744997, \"accuracy\": 0.3798828125}, {\"mcc\": 0.20538121557504213, \"accuracy\": 0.39892578125}, {\"mcc\": 0.17770146355022992, \"accuracy\": 0.37548828125}, {\"mcc\": 0.22494827829833502, \"accuracy\": 0.4130859375}]"}}, "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": 19.295372271525252, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 17.670953699387454, "upper": 20.91979084366305, "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": 38.7841796875, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 37.40075909839962, "upper": 40.16760027660038, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "multi-wiki-qa-pt/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050571+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.2"}}, "eval_library": {"name": "euroeval", "version": "15.13.0", "additional_details": {"dataset": "multi-wiki-qa-pt", "languages": "[\"pt\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.53.2", "torch_version": "2.7.0", "vllm_version": "0.9.2", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 70.98241955816415, \"em\": 52.81837160751566}, {\"f1\": 71.4024636978021, \"em\": 51.483050847457626}, {\"f1\": 69.70758655956303, \"em\": 50.20746887966805}, {\"f1\": 68.7889840725078, \"em\": 48.676171079429736}, {\"f1\": 67.98534978954628, \"em\": 50.103092783505154}, {\"f1\": 69.32404369177975, \"em\": 50.718685831622174}, {\"f1\": 71.55287710329884, \"em\": 51.9916142557652}, {\"f1\": 73.18327305170563, \"em\": 55.23012552301255}, {\"f1\": 69.50435240226284, \"em\": 50.829875518672196}, {\"f1\": 69.42463539781754, \"em\": 50.20661157024794}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "multi-wiki-qa-pt", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 70.1855985324448, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 69.22147801353957, "upper": 71.14971905135003, "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": 51.22650678968963, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 50.10485893374073, "upper": 52.34815464563853, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "multinerd-it/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050602+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "multinerd-it", "languages": "[\"it\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.4490061909416748, \"micro_f1\": 0.37974142536595795}, {\"micro_f1_no_misc\": 0.45770097670924115, \"micro_f1\": 0.42554570996325913}, {\"micro_f1_no_misc\": 0.4976434710285556, \"micro_f1\": 0.4415696420871065}, {\"micro_f1_no_misc\": 0.5564516129032259, \"micro_f1\": 0.49248938153941785}, {\"micro_f1_no_misc\": 0.6065671641791045, \"micro_f1\": 0.519317714755446}, {\"micro_f1_no_misc\": 0.5568826515377725, \"micro_f1\": 0.4812797032572157}, {\"micro_f1_no_misc\": 0.5954995981784089, \"micro_f1\": 0.5229048124216414}, {\"micro_f1_no_misc\": 0.5491424310216257, \"micro_f1\": 0.484186313973548}, {\"micro_f1_no_misc\": 0.5510612735282339, \"micro_f1\": 0.4689498658964308}, {\"micro_f1_no_misc\": 0.46578332034294617, \"micro_f1\": 0.399091343854615}]"}}, "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": 52.85738690370789, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 49.31956205109823, "upper": 56.39521175631755, "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": 46.15075913114638, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 43.13518722919342, "upper": 49.16633103309934, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "nor-common-sense-qa/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050633+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.2.0.dev0", "additional_details": {"dataset": "nor-common-sense-qa", "languages": "[\"nb\", \"nn\", \"no\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.17633447218645432, \"accuracy\": 0.2925969447708578}, {\"mcc\": 0.12633708670263583, \"accuracy\": 0.29142185663924797}, {\"mcc\": 0.11437158612793949, \"accuracy\": 0.2596944770857814}, {\"mcc\": 0.1403703785407864, \"accuracy\": 0.3019976498237368}, {\"mcc\": 0.12215606090503318, \"accuracy\": 0.29142185663924797}, {\"mcc\": 0.09763720626007287, \"accuracy\": 0.25851938895417154}, {\"mcc\": 0.19358486617531462, \"accuracy\": 0.34665099882491185}, {\"mcc\": 0.23591034139084707, \"accuracy\": 0.38425381903642775}, {\"mcc\": 0.19921523321645127, \"accuracy\": 0.3196239717978848}, {\"mcc\": 0.06893079246815874, \"accuracy\": 0.24324324324324326}]"}}, "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": 14.748480239736935, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 11.524955871350613, "upper": 17.972004608123257, "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": 29.894242068155112, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 27.24671742827774, "upper": 32.54176670803248, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "nrk-quiz-qa/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050663+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "15.2.0.dev0", "additional_details": {"dataset": "nrk-quiz-qa", "languages": "[\"nb\", \"nn\", \"no\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.172669416963327, \"accuracy\": 0.39013671875}, {\"mcc\": 0.1377748808190997, \"accuracy\": 0.37744140625}, {\"mcc\": 0.1649863482032874, \"accuracy\": 0.3642578125}, {\"mcc\": 0.15193196860378202, \"accuracy\": 0.37353515625}, {\"mcc\": 0.10860541710124554, \"accuracy\": 0.34716796875}, {\"mcc\": 0.14767549873665697, \"accuracy\": 0.376953125}, {\"mcc\": 0.14334782433415721, \"accuracy\": 0.37109375}, {\"mcc\": 0.16614116603954057, \"accuracy\": 0.38037109375}, {\"mcc\": 0.13407741562646033, \"accuracy\": 0.34912109375}, {\"mcc\": 0.11914033894256937, \"accuracy\": 0.35546875}]"}}, "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": 14.46350275370126, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 13.184336700366678, "upper": 15.742668807035841, "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": 36.85546875, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 35.976272337634796, "upper": 37.734665162365204, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-es/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050693+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "scala-es", "languages": "[\"es\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.06122662489004263, \"macro_f1\": 0.40169442009932804}, {\"mcc\": 0.06505897868307597, \"macro_f1\": 0.35637725580380747}, {\"mcc\": 0.10805297987237883, \"macro_f1\": 0.5539438770410479}, {\"mcc\": 0.0715328525473166, \"macro_f1\": 0.35072128266395697}, {\"mcc\": 0.09393354827617344, \"macro_f1\": 0.4781952221023169}, {\"mcc\": 0.03840577418999028, \"macro_f1\": 0.4387784500144051}, {\"mcc\": 0.0, \"macro_f1\": 0.33159268929503916}, {\"mcc\": 0.018944897768956942, \"macro_f1\": 0.34639771954079335}, {\"mcc\": 0.04716502009025369, \"macro_f1\": 0.3437909853140707}, {\"mcc\": 0.1952966356560061, \"macro_f1\": 0.5965676734089245}]"}}, "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": 6.996173119741946, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 3.6107925272961285, "upper": 10.381553712187763, "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": 41.9805957528369, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 36.097711132427854, "upper": 47.86348037324594, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-fi/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050722+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "scala-fi", "languages": "[\"fi\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.0, \"macro_f1\": 0.3311561071195297}, {\"mcc\": 0.0, \"macro_f1\": 0.33635774465327284}, {\"mcc\": 0.0, \"macro_f1\": 0.330718954248366}, {\"mcc\": 0.0, \"macro_f1\": 0.34169077467052394}, {\"mcc\": 0.0, \"macro_f1\": 0.33159268929503916}, {\"mcc\": 0.0, \"macro_f1\": 0.3263157894736842}, {\"mcc\": 0.031510491534269096, \"macro_f1\": 0.3372472876143644}, {\"mcc\": 0.0, \"macro_f1\": 0.32874467387741724}, {\"mcc\": 0.0, \"macro_f1\": 0.3339837398373984}, {\"mcc\": 0.0, \"macro_f1\": 0.3342002600780234}]"}}, "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": 0.31510491534269097, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": -0.30250071872898326, "upper": 0.9327105494143653, "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": 33.32008020867619, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 33.04272599267859, "upper": 33.597434424673786, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-fr/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050751+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "scala-fr", "languages": "[\"fr\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.15099505097594393, \"macro_f1\": 0.5171520145579342}, {\"mcc\": 0.16206736401021402, \"macro_f1\": 0.5495000223466253}, {\"mcc\": 0.20474198657224452, \"macro_f1\": 0.5829457193373253}, {\"mcc\": 0.13619152003001855, \"macro_f1\": 0.525223602440744}, {\"mcc\": 0.1971169059266011, \"macro_f1\": 0.5984122137404579}, {\"mcc\": 0.15279696137554993, \"macro_f1\": 0.5750781990046618}, {\"mcc\": 0.11563647444145903, \"macro_f1\": 0.4451609586129024}, {\"mcc\": 0.19266161778008747, \"macro_f1\": 0.5962345572931584}, {\"mcc\": 0.11861135350029064, \"macro_f1\": 0.4990989967462895}, {\"mcc\": 0.1414231401536861, \"macro_f1\": 0.5696558469344092}]"}}, "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": 15.722423747660951, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 13.751610904345036, "upper": 17.693236590976866, "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": 54.584621310145074, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 51.54224973467858, "upper": 57.62699288561157, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-it/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050782+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "scala-it", "languages": "[\"it\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.07193998738572542, \"macro_f1\": 0.49748626092991405}, {\"mcc\": 0.1313891835601349, \"macro_f1\": 0.5281728755624293}, {\"mcc\": 0.092334395313135, \"macro_f1\": 0.439959275884845}, {\"mcc\": 0.07837547145655546, \"macro_f1\": 0.4041431132340223}, {\"mcc\": 0.0461183844093593, \"macro_f1\": 0.48739013968746503}, {\"mcc\": 0.06753410563916461, \"macro_f1\": 0.48933490559809545}, {\"mcc\": 0.11916031760868571, \"macro_f1\": 0.5106443140925198}, {\"mcc\": 0.12963353018341375, \"macro_f1\": 0.5448035709253358}, {\"mcc\": 0.09766286349781003, \"macro_f1\": 0.46066565726205044}, {\"mcc\": 0.052780300985133095, \"macro_f1\": 0.4503796620294016}]"}}, "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": 8.869285400391174, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 6.96919703908927, "upper": 10.769373761693078, "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": 48.12979775206078, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 45.4760588171151, "upper": 50.78353668700646, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scala-pt/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050813+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.2"}}, "eval_library": {"name": "euroeval", "version": "15.13.0", "additional_details": {"dataset": "scala-pt", "languages": "[\"pt\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "4.53.2", "torch_version": "2.7.0", "vllm_version": "0.9.2", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.08449452222144921, \"macro_f1\": 0.41721933813335}, {\"mcc\": 0.0908660063050403, \"macro_f1\": 0.4688883855443835}, {\"mcc\": 0.04243216509977186, \"macro_f1\": 0.34522105096688493}, {\"mcc\": 0.06674932045850873, \"macro_f1\": 0.45537760643250913}, {\"mcc\": 0.06874134554249536, \"macro_f1\": 0.3489455039646653}, {\"mcc\": 0.06119806290797264, \"macro_f1\": 0.35693286148825176}, {\"mcc\": 0.07790794922271195, \"macro_f1\": 0.4993076527991782}, {\"mcc\": 0.11329616206414032, \"macro_f1\": 0.4412602080023152}, {\"mcc\": 0.11359747117589875, \"macro_f1\": 0.5553578926326884}, {\"mcc\": 0.03634938595274743, \"macro_f1\": 0.3394009816433955}]"}}, "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": 7.556323909507364, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 5.935347099136957, "upper": 9.177300719877772, "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": 42.279114816076216, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 37.67094987432473, "upper": 46.887279757827706, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "scandisent-fi/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050843+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "scandisent-fi", "languages": "[\"fi\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.8868619769218811, \"macro_f1\": 0.9431372549019608}, {\"mcc\": 0.8079685909663942, \"macro_f1\": 0.8974769478103264}, {\"mcc\": 0.8151100090342128, \"macro_f1\": 0.9036170498857066}, {\"mcc\": 0.8431317526639845, \"macro_f1\": 0.9179990660661703}, {\"mcc\": 0.8505617964584054, \"macro_f1\": 0.9252630155394368}, {\"mcc\": 0.8746801760976005, \"macro_f1\": 0.937325708165178}, {\"mcc\": 0.8647441671617506, \"macro_f1\": 0.9316239316239316}, {\"mcc\": 0.8365300788623892, \"macro_f1\": 0.9149060242156035}, {\"mcc\": 0.8518878916794645, \"macro_f1\": 0.9235387088158513}, {\"mcc\": 0.8016586501532059, \"macro_f1\": 0.8983434921260665}]"}}, "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": 84.33135089999288, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 82.56716415959144, "upper": 86.09553764039433, "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": 91.93231199150232, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 90.9456025261483, "upper": 92.91902145685633, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "sentiment-headlines-es/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050887+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "sentiment-headlines-es", "languages": "[\"es\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.3601257779609711, \"macro_f1\": 0.5181657326550738}, {\"mcc\": 0.40310135958343285, \"macro_f1\": 0.5547060381674481}, {\"mcc\": 0.42146827241809764, \"macro_f1\": 0.5854182836445541}, {\"mcc\": 0.31143023711557877, \"macro_f1\": 0.503092712627022}, {\"mcc\": 0.2956002504898307, \"macro_f1\": 0.46123084420587884}, {\"mcc\": 0.3601545133167502, \"macro_f1\": 0.5294771619294314}, {\"mcc\": 0.33823104316171804, \"macro_f1\": 0.5084233328250933}, {\"mcc\": 0.29468999565168924, \"macro_f1\": 0.4782080486442492}, {\"mcc\": 0.2672508272031499, \"macro_f1\": 0.43195900464162446}, {\"mcc\": 0.3758429248949847, \"macro_f1\": 0.5392265194690286}]"}}, "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": 34.27895201796203, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 31.161165511538137, "upper": 37.39673852438592, "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": 51.099076788094045, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 48.28847416319235, "upper": 53.90967941299574, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "sentipolc16/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050918+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "sentipolc16", "languages": "[\"it\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.4903707960888792, \"macro_f1\": 0.6196858156439152}, {\"mcc\": 0.5018179582932822, \"macro_f1\": 0.6087396745490049}, {\"mcc\": 0.45054013775703844, \"macro_f1\": 0.523294603613891}, {\"mcc\": 0.4613032653638894, \"macro_f1\": 0.5184736177661998}, {\"mcc\": 0.39307606219834146, \"macro_f1\": 0.5086122485009251}, {\"mcc\": 0.4783244550940787, \"macro_f1\": 0.5637122865976804}, {\"mcc\": 0.498491396661916, \"macro_f1\": 0.5572479611442788}, {\"mcc\": 0.49648164968951536, \"macro_f1\": 0.6208354469098726}, {\"mcc\": 0.44562058568101814, \"macro_f1\": 0.5057539135226617}, {\"mcc\": 0.46410417458272407, \"macro_f1\": 0.558470197236438}]"}}, "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": 46.80130481410683, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 44.738288115248466, "upper": 48.86432151296519, "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": 55.848257654848666, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 53.05380512166602, "upper": 58.642710188031316, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "squad-it/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050948+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "squad-it", "languages": "[\"it\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 64.13130373173226, \"em\": 48.333333333333336}, {\"f1\": 65.12451846453435, \"em\": 47.53601213040182}, {\"f1\": 63.94111438957976, \"em\": 47.63014763014763}, {\"f1\": 64.47268478455419, \"em\": 46.57534246575342}, {\"f1\": 65.19102615940504, \"em\": 47.64841942945258}, {\"f1\": 66.6500759997794, \"em\": 50.0763358778626}, {\"f1\": 65.51084198273418, \"em\": 48.28393135725429}, {\"f1\": 63.972897872926104, \"em\": 44.418238993710695}, {\"f1\": 65.90785285273036, \"em\": 51.0061919504644}, {\"f1\": 62.862120683406786, \"em\": 44.21296296296296}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "squad-it", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 64.77644369213826, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 64.08688978019646, "upper": 65.46599760408006, "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": 47.572091613134376, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 46.242995332044885, "upper": 48.90118789422387, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "sst2-pt/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.050979+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.2"}}, "eval_library": {"name": "euroeval", "version": "15.13.0", "additional_details": {"dataset": "sst2-pt", "languages": "[\"pt\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.53.2", "torch_version": "2.7.0", "vllm_version": "0.9.2", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.6836989037043564, \"macro_f1\": 0.8247821232290715}, {\"mcc\": 0.7864438666315836, \"macro_f1\": 0.8922895826699446}, {\"mcc\": 0.76297854362967, \"macro_f1\": 0.8773021305665081}, {\"mcc\": 0.790756125712115, \"macro_f1\": 0.8953232313678734}, {\"mcc\": 0.778720227897269, \"macro_f1\": 0.8880334348848408}, {\"mcc\": 0.6882588137834387, \"macro_f1\": 0.8291542580276823}, {\"mcc\": 0.7573090665883884, \"macro_f1\": 0.8768785930389296}, {\"mcc\": 0.7850095628242413, \"macro_f1\": 0.8920737614872287}, {\"mcc\": 0.7680688898922345, \"macro_f1\": 0.8833007534267314}, {\"mcc\": 0.7623973905909108, \"macro_f1\": 0.8798534798534798}]"}}, "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": 75.63641391254208, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 73.23195461971122, "upper": 78.04087320537295, "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": 87.3899134855229, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 85.80483162071437, "upper": 88.97499535033143, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "turku-ner-fi/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.051009+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "turku-ner-fi", "languages": "[\"fi\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.38972370334464373, \"micro_f1\": 0.27676240208877284}, {\"micro_f1_no_misc\": 0.36165163739914574, \"micro_f1\": 0.3076923076923077}, {\"micro_f1_no_misc\": 0.37123420796890183, \"micro_f1\": 0.30241051862673485}, {\"micro_f1_no_misc\": 0.3464566929133858, \"micro_f1\": 0.2426067907995619}, {\"micro_f1_no_misc\": 0.3717728055077453, \"micro_f1\": 0.22822822822822825}, {\"micro_f1_no_misc\": 0.3689604685212299, \"micro_f1\": 0.2924951892238615}, {\"micro_f1_no_misc\": 0.39353099730458213, \"micro_f1\": 0.2826892535733192}, {\"micro_f1_no_misc\": 0.334755808440019, \"micro_f1\": 0.2833644859813084}, {\"micro_f1_no_misc\": 0.33603707995365006, \"micro_f1\": 0.19628556823990456}, {\"micro_f1_no_misc\": 0.42236024844720504, \"micro_f1\": 0.2325225052671902}]"}}, "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": 36.964836498005084, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 35.27265856312474, "upper": 38.657014432885425, "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": 26.450572497211894, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 24.150475372622953, "upper": 28.750669621800835, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
| {"schema_version": "0.2.1", "evaluation_id": "tydiqa-fi/CohereForAI/aya-23-8B/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.051041+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-23-8B", "id": "CohereForAI/aya-23-8B", "additional_details": {"num_model_parameters": "8028033024", "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-23-8B"}, "inference_engine": {"name": "vllm", "version": "0.9.1"}}, "eval_library": {"name": "euroeval", "version": "15.10.0", "additional_details": {"dataset": "tydiqa-fi", "languages": "[\"fi\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.3", "torch_version": "2.7.0", "vllm_version": "0.9.1", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 56.289556771428366, \"em\": 36.43939393939394}, {\"f1\": 56.0172093600064, \"em\": 38.81728582259287}, {\"f1\": 60.699129379004134, \"em\": 44.52214452214452}, {\"f1\": 55.4833321821386, \"em\": 38.73668188736682}, {\"f1\": 57.191641208031754, \"em\": 38.62760215882806}, {\"f1\": 57.45387293392003, \"em\": 39.69465648854962}, {\"f1\": 54.93340225113484, \"em\": 39.46957878315133}, {\"f1\": 55.144157034639946, \"em\": 38.83647798742138}, {\"f1\": 57.034481276342895, \"em\": 41.95046439628483}, {\"f1\": 54.17422044976955, \"em\": 35.49382716049383}]"}}, "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": 56.442100284641654, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 55.30511535909856, "upper": 57.57908521018475, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "tydiqa-fi", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 39.25881131462272, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 37.6806274629192, "upper": 40.83699516632624, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]} | |
Xet Storage Details
- Size:
- 106 kB
- Xet hash:
- c3355a138e06dff6cc6a53b2b7fd326116a91d19b07d1da88571bcafd418adbc
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.