| model,category,task,metric,value,source_artifact | |
| Mimir-2850K,English,boolq,accuracy,0.9162079510703364,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,English,winogrande,accuracy,0.8176795580110497,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,English,hellaswag,accuracy,0.8387771360286795,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,English,mmlu,accuracy,0.674067084460903,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,English,arc,accuracy,0.9035836177474402,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,English,drop,f1,0.8876899400804901,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,English,govreport,rouge1,0.40845739556307536,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,Math/Code,gsm8k,accuracy,0.9173616376042456,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,Math/Code,math,accuracy,0.4844,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,Math/Code,humaneval,accuracy,0.7317073170731707,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,Danish,angry_tweets,macro_f1,0.6330917314034863,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,Danish,dala,macro_f1,0.9682553536301619,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,Danish,gec_dala,exact_match,0.9248046875,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,Danish,piqa,accuracy,0.7314814814814815,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,Danish,daisy,exact_match,0.12331081081081081,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,Danish,multi_wiki_qa,exact_match,0.66943359375,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,Danish,wmt24pp,chrf3pp,0.5457357886179449,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,Danish,nordjylland,rouge1,0.293910232767666,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,Danish,ifeval_da,prompt_strict_acc,0.6635859519408502,runs/dfm11_XL_epoch10_step_2850000_ema_hf/results.csv | |
| Mimir-2850K,Danish,hellaswag_da,accuracy,0.74365234375,runs/dfm11_XL_epoch10_step_2850000_ema_hf/hellaswag_da_letter_only/metrics.csv | |
| Mimir-1650K,English,boolq,accuracy,0.8779816513761468,results_hf.csv | |
| Mimir-1650K,English,winogrande,accuracy,0.7348066298342542,results_hf.csv | |
| Mimir-1650K,English,hellaswag,accuracy,0.6727743477394941,results_hf.csv | |
| Mimir-1650K,English,mmlu,accuracy,0.5748646916393676,results_hf.csv | |
| Mimir-1650K,English,arc,accuracy,0.8156996587030717,results_hf.csv | |
| Mimir-1650K,English,drop,f1,0.8310232963514604,results_hf.csv | |
| Mimir-1650K,English,govreport,rouge1,0.3204,results_hf.csv | |
| Mimir-1650K,Math/Code,gsm8k,accuracy,0.8991660348749052,results_hf.csv | |
| Mimir-1650K,Math/Code,math,accuracy,0.458,results_hf.csv | |
| Mimir-1650K,Math/Code,humaneval,accuracy,0.5670731707317073,results_hf.csv | |
| Mimir-1650K,Danish,angry_tweets,macro_f1,0.657625150346315,results_danish_hf.csv | |
| Mimir-1650K,Danish,dala,macro_f1,0.9614217250301214,results_danish_hf.csv | |
| Mimir-1650K,Danish,gec_dala,exact_match,0.8564453125,results_danish_hf.csv | |
| Mimir-1650K,Danish,piqa,accuracy,0.5370370370370371,results_danish_hf.csv | |
| Mimir-1650K,Danish,daisy,exact_match,0.09628378378378379,results_danish_hf.csv | |
| Mimir-1650K,Danish,multi_wiki_qa,exact_match,0.66796875,results_danish_hf.csv | |
| Mimir-1650K,Danish,wmt24pp,chrf3pp,0.5385458074401283,results_danish_hf.csv | |
| Mimir-1650K,Danish,nordjylland,rouge1,0.23760338544360715,results_summarization.csv | |
| Mimir-1650K,Danish,ifeval_da,prompt_strict_acc,0.5656192236598891,results_danish_hf.csv | |
| Mimir-1650K,Danish,hellaswag_da,accuracy,0.5849609375,runs/hellaswag_da_letter_only_comparison_20260922/results.csv | |
| Qwen3.5-0.8B,English,boolq,accuracy,0.6981651376146789,logs_ie_rerun/Qwen3.5-0.8B/2026-08-12T21-50-36-00-00_boolq-5shot_m2zfpVvuZEHtsJ9BKrwqiP.eval | |
| Qwen3.5-0.8B,English,winogrande,accuracy,0.500394632991318,logs_ie_rerun/Qwen3.5-0.8B/2026-08-12T21-51-14-00-00_winogrande-5shot_bLqb9Py4pzfqybpTdZdBQ9.eval | |
| Qwen3.5-0.8B,English,hellaswag,accuracy,0.36974706233817967,logs_ie_rerun/Qwen3.5-0.8B/2026-08-12T21-51-34-00-00_hellaswag-10shot_k3yW2LJdm7bujftPKNvpgf.eval | |
| Qwen3.5-0.8B,English,mmlu,accuracy,0.5153112092294545,logs_ie_rerun/Qwen3.5-0.8B/2026-08-12T21-53-32-00-00_mmlu-5shot_6onhfi3M9z7CMwY4u6xJWv.eval | |
| Qwen3.5-0.8B,English,arc,accuracy,0.6843003412969283,logs_ie_rerun/Qwen3.5-0.8B/2026-08-12T21-56-25-00-00_arc-25shot_KnvZdY8ZnS5st8eqwMWt6u.eval | |
| Qwen3.5-0.8B,English,drop,f1,0.4522821185107499,logs_drop_rerun/Qwen3.5-0.8B/2026-08-12T23-54-32-00-00_drop_35w9QKhEDU4bP4Ww2jNPRa.eval | |
| Qwen3.5-0.8B,English,govreport,rouge1,0.32508696798050013,logs_ie_rerun/Qwen3.5-0.8B/2026-08-12T22-00-52-00-00_govreport-summarization_jHpMZmtCyonbKsot3PytCb.eval | |
| Qwen3.5-0.8B,Math/Code,gsm8k,accuracy,0.49128127369219105,logs_gsm8k_ie/Qwen3.5-0.8B/2026-08-13T07-25-28-00-00_gsm8k_W74Sihw4FYtkmETmcKpf4m.eval | |
| Qwen3.5-0.8B,Math/Code,math,accuracy,0.3616,logs_math_ie/Qwen3.5-0.8B/chunk0/2026-08-13T07-45-54-00-00_math-ie-chunk0_4biDLsNhgKpWcLMV3BoW9m.eval; logs_math_ie/Qwen3.5-0.8B/chunk1/2026-08-13T08-36-37-00-00_math-ie-chunk1_FZmAwU5nw8XXyb7dwpCiFr.eval | |
| Qwen3.5-0.8B,Math/Code,humaneval,accuracy,0.3048780487804878,logs_humaneval_ie/Qwen3.5-0.8B/2026-08-13T08-56-02-00-00_humaneval-ie_gGtuTsLgTug3UFQ8pvPG5y.eval | |
| Qwen3.5-0.8B,Danish,angry_tweets,macro_f1,0.43614896640897277,logs_new_models_full/Qwen3.5-0.8B/2026-08-12T09-03-49-00-00_angry-tweets_bRLc9zA7YJQH2c9WwCm2QD.eval | |
| Qwen3.5-0.8B,Danish,dala,macro_f1,0.5103060491549432,logs_new_models_full/Qwen3.5-0.8B/2026-08-12T09-04-07-00-00_dala_eFZrkUkhkRwzT2ykQeUg9j.eval | |
| Qwen3.5-0.8B,Danish,gec_dala,exact_match,0.0068359375,logs_new_models_full/Qwen3.5-0.8B/2026-08-12T09-04-36-00-00_gec-dala_GrH79uyhYSWGQCmpc3SzDr.eval | |
| Qwen3.5-0.8B,Danish,piqa,accuracy,0.5648148148148148,logs_new_models_full/Qwen3.5-0.8B/2026-08-12T09-04-51-00-00_piqa_nqjfVQX5EENjeX8GVJu7EN.eval | |
| Qwen3.5-0.8B,Danish,daisy,exact_match,0.006756756756756757,logs_new_models_full/Qwen3.5-0.8B/2026-08-12T09-06-22-00-00_daisy_8fXDUxAWoZNGVMz7qAVB8j.eval | |
| Qwen3.5-0.8B,Danish,multi_wiki_qa,exact_match,0.41552734375,logs_new_models_full/Qwen3.5-0.8B/2026-08-12T09-06-33-00-00_multi-wiki-qa_XHyq8DK2HNA3YrGGZYd3hT.eval | |
| Qwen3.5-0.8B,Danish,wmt24pp,chrf3pp,0.37843962179790885,logs_new_models_full/Qwen3.5-0.8B/2026-08-12T09-07-06-00-00_wmt24pp-en-da_hp6CatCRoqedPvTUaEoozE.eval | |
| Qwen3.5-0.8B,Danish,nordjylland,rouge1,0.19367003239312344,logs_new_models_full/Qwen3.5-0.8B/2026-08-12T09-13-58-00-00_nordjylland-news-summarization_RbNSFuNZD7tR4TMKrouDec.eval | |
| Qwen3.5-0.8B,Danish,ifeval_da,prompt_strict_acc,0.3031423290203327,logs_new_models_full/Qwen3.5-0.8B/2026-08-12T09-07-26-00-00_ifeval-da_3oorwLAYFdhfMCDPM5ZnxE.eval | |
| Qwen3.5-0.8B,Danish,hellaswag_da,accuracy,0.2730712890625,runs/hellaswag_da_letter_only_comparison_20260922/results.csv | |
| Qwen3.5-2B,English,boolq,accuracy,0.807645259938838,logs_ie_rerun/Qwen3.5-2B/2026-08-12T21-50-45-00-00_boolq-5shot_9tKnXcCfC9bAw2L3i86odF.eval | |
| Qwen3.5-2B,English,winogrande,accuracy,0.5698500394632992,logs_ie_rerun/Qwen3.5-2B/2026-08-12T21-51-29-00-00_winogrande-5shot_48ScfGHtbennSbgsgERNgF.eval | |
| Qwen3.5-2B,English,hellaswag,accuracy,0.6459121688906593,logs_ie_rerun/Qwen3.5-2B/2026-08-12T21-51-50-00-00_hellaswag-10shot_Uh6zVj2VcgiexQCLHuwNyD.eval | |
| Qwen3.5-2B,English,mmlu,accuracy,0.6278307933342828,logs_ie_rerun/Qwen3.5-2B/2026-08-12T21-53-58-00-00_mmlu-5shot_KHpVYJtVk2GudAYMbPHnGz.eval | |
| Qwen3.5-2B,English,arc,accuracy,0.8267918088737202,logs_ie_rerun/Qwen3.5-2B/2026-08-12T21-56-47-00-00_arc-25shot_WG6Stb7YQnAGDgQ672ug97.eval | |
| Qwen3.5-2B,English,drop,f1,0.3134525432616675,logs_drop_rerun/Qwen3.5-2B/2026-08-12T23-54-36-00-00_drop_cSSsTkaFntBPdDX3KMjBXg.eval | |
| Qwen3.5-2B,English,govreport,rouge1,0.3151437275685979,logs_ie_rerun/Qwen3.5-2B/2026-08-12T22-01-18-00-00_govreport-summarization_jW37ucBdAohdVTE92gVYNh.eval | |
| Qwen3.5-2B,Math/Code,gsm8k,accuracy,0.7369219105382866,logs_gsm8k_ie/Qwen3.5-2B/2026-08-13T07-25-28-00-00_gsm8k_4WKkufpxESsUTfJBoDPudi.eval | |
| Qwen3.5-2B,Math/Code,math,accuracy,0.5566,logs_math_ie/Qwen3.5-2B/chunk0/2026-08-13T07-45-54-00-00_math-ie-chunk0_grBC7rFTFtWkiUm9HF83Dc.eval; logs_math_ie/Qwen3.5-2B/chunk1/2026-08-13T07-59-38-00-00_math-ie-chunk1_FspN5y2qoFaHTfjVRwttAM.eval | |
| Qwen3.5-2B,Math/Code,humaneval,accuracy,0.47560975609756095,logs_humaneval_ie/Qwen3.5-2B/2026-08-13T08-31-36-00-00_humaneval-ie_N62DUzeUj2UvjGf2bs5HDQ.eval | |
| Qwen3.5-2B,Danish,angry_tweets,macro_f1,0.6249466186718649,logs_danish/Qwen3.5-2B/2026-08-06T11-35-14-00-00_angry-tweets_9EFEjYKdDGE3JczWYphDPu.eval | |
| Qwen3.5-2B,Danish,dala,macro_f1,0.36434799202919604,logs_danish/Qwen3.5-2B/2026-08-06T11-35-14-00-00_dala_W87z9LVUvxCC9E22nSKuaY.eval | |
| Qwen3.5-2B,Danish,gec_dala,exact_match,0.080078125,logs_danish/Qwen3.5-2B/2026-08-06T11-35-16-00-00_gec-dala_cGcnKjAqxxLmcK7uwWbbew.eval | |
| Qwen3.5-2B,Danish,piqa,accuracy,0.25,logs_danish/Qwen3.5-2B/2026-08-06T11-35-14-00-00_piqa_n53jvc2H8Zs6qjHtDSvRRB.eval | |
| Qwen3.5-2B,Danish,daisy,exact_match,0.02533783783783784,logs_danish/Qwen3.5-2B/2026-08-06T11-35-14-00-00_daisy_hR3otwnxs8vWSM3vxyMTpT.eval | |
| Qwen3.5-2B,Danish,multi_wiki_qa,exact_match,0.49365234375,logs_danish/Qwen3.5-2B/2026-08-06T11-35-15-00-00_multi-wiki-qa_dF8hhHLQUG5Rij3TbYNfmU.eval | |
| Qwen3.5-2B,Danish,wmt24pp,chrf3pp,0.456294326802611,logs_danish/Qwen3.5-2B/2026-08-06T11-35-15-00-00_wmt24pp-en-da_6JgwPX8h8RTHpELTyPP97W.eval | |
| Qwen3.5-2B,Danish,nordjylland,rouge1,0.19473693572341574,logs_summarization/Qwen3.5-2B/2026-08-06T14-34-25-00-00_nordjylland-news-summarization_Knx3KXgGAHgPRARCpE3U3n.eval | |
| Qwen3.5-2B,Danish,ifeval_da,prompt_strict_acc,0.4713493530499076,logs_danish/Qwen3.5-2B/2026-08-06T11-35-14-00-00_ifeval-da_GzyYZ39vMfzqcMLHSmEN9A.eval | |
| Qwen3.5-2B,Danish,hellaswag_da,accuracy,0.3123779296875,runs/hellaswag_da_letter_only_comparison_20260922/results.csv | |
| Qwen3.5-4B,English,boolq,accuracy,0.8703363914373089,logs_ie_rerun/Qwen3.5-4B/2026-08-12T21-50-51-00-00_boolq-5shot_nsRf5jp76tUVExnwK38iYx.eval | |
| Qwen3.5-4B,English,winogrande,accuracy,0.7000789265982637,logs_ie_rerun/Qwen3.5-4B/2026-08-12T21-51-42-00-00_winogrande-5shot_NXGFaSB2Cb8qNZVKSPFJsk.eval | |
| Qwen3.5-4B,English,hellaswag,accuracy,0.8315325632344155,logs_ie_rerun/Qwen3.5-4B/2026-08-12T21-52-04-00-00_hellaswag-10shot_YA2pX3oDhenLyooxwQ8rBH.eval | |
| Qwen3.5-4B,English,mmlu,accuracy,0.7579404643213218,logs_ie_rerun/Qwen3.5-4B/2026-08-12T21-54-55-00-00_mmlu-5shot_6dEpv3zLKMXfV4ysLAeTjY.eval | |
| Qwen3.5-4B,English,arc,accuracy,0.9291808873720137,logs_ie_rerun/Qwen3.5-4B/2026-08-12T21-58-21-00-00_arc-25shot_9RwcJBnJyEsFgjto7aZw3x.eval | |
| Qwen3.5-4B,English,drop,f1,0.4803135815416885,logs_drop_rerun/Qwen3.5-4B/2026-08-12T23-54-42-00-00_drop_KLhrVqmPVYVcPwgTifD2Bn.eval | |
| Qwen3.5-4B,English,govreport,rouge1,0.2788940170071621,logs_ie_rerun/Qwen3.5-4B/2026-08-12T22-03-48-00-00_govreport-summarization_SnVc9iYyMJcVLvPPUTJKKC.eval | |
| Qwen3.5-4B,Math/Code,gsm8k,accuracy,0.6050037907505686,logs_gsm8k_ie/Qwen3.5-4B/2026-08-13T07-25-28-00-00_gsm8k_nAHL74TcgtEVprjEmJS5Ff.eval | |
| Qwen3.5-4B,Math/Code,math,accuracy,0.5652,logs_new_models_full/Qwen3.5-4B/2026-08-12T12-10-27-00-00_math-0shot_Pf8H3mLcJT97U8NDjAvMFL.eval | |
| Qwen3.5-4B,Math/Code,humaneval,accuracy,0.7804878048780488,logs_new_models_full/Qwen3.5-4B/2026-08-12T12-10-19-00-00_humaneval_ntdRz6Dj9q2CXfjbJd5wDP.eval | |
| Qwen3.5-4B,Danish,angry_tweets,macro_f1,0.688410234844536,logs_new_models_full/Qwen3.5-4B/2026-08-12T12-10-29-00-00_angry-tweets_P4Y7nHjn7V2pkKAXBtvUum.eval | |
| Qwen3.5-4B,Danish,dala,macro_f1,0.5007526635301942,logs_new_models_full/Qwen3.5-4B/2026-08-12T12-10-34-00-00_dala_GDrvvQ62P4TL397kXVWZsh.eval | |
| Qwen3.5-4B,Danish,gec_dala,exact_match,0.42578125,logs_new_models_full/Qwen3.5-4B/2026-08-12T12-10-41-00-00_gec-dala_QjFzrB64Xh43nufz8sADPW.eval | |
| Qwen3.5-4B,Danish,piqa,accuracy,0.7037037037037037,logs_new_models_full/Qwen3.5-4B/2026-08-12T12-10-44-00-00_piqa_QHvG4KMuT5Sd7iqMj6Ee7L.eval | |
| Qwen3.5-4B,Danish,daisy,exact_match,0.0472972972972973,logs_new_models_full/Qwen3.5-4B/2026-08-12T12-20-38-00-00_daisy_Q6gyk3XEcXLms72C5wZD9i.eval | |
| Qwen3.5-4B,Danish,multi_wiki_qa,exact_match,0.5712890625,logs_new_models_full/Qwen3.5-4B/2026-08-12T12-20-49-00-00_multi-wiki-qa_52rSARQxtsd78vMk443XGd.eval | |
| Qwen3.5-4B,Danish,wmt24pp,chrf3pp,0.5213886417995208,logs_new_models_full/Qwen3.5-4B/2026-08-12T12-20-54-00-00_wmt24pp-en-da_RaHKjVCS8mxvJLxuBXLgwN.eval | |
| Qwen3.5-4B,Danish,nordjylland,rouge1,0.23652600246879063,logs_new_models_full/Qwen3.5-4B/2026-08-12T12-21-02-00-00_nordjylland-news-summarization_EpyGEmRud6oeu7BjMZLHRT.eval | |
| Qwen3.5-4B,Danish,ifeval_da,prompt_strict_acc,0.6709796672828097,logs_new_models_full/Qwen3.5-4B/2026-08-12T12-20-53-00-00_ifeval-da_Fvan9C6fbHizGtfZ93jACC.eval | |
| Qwen3.5-4B,Danish,hellaswag_da,accuracy,0.6162109375,runs/hellaswag_da_letter_only_comparison_20260922/results.csv | |
| Qwen3.5-9B,English,boolq,accuracy,0.8929663608562691,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,English,winogrande,accuracy,0.7513812154696132,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,English,hellaswag,accuracy,0.8856303525194185,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,English,mmlu,accuracy,0.7951146560319042,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,English,arc,accuracy,0.9411262798634812,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,English,drop,f1,0.8204960671211327,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,English,govreport,rouge1,0.30706541006589233,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,Math/Code,gsm8k,accuracy,0.9552691432903715,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,Math/Code,math,accuracy,0.7418,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,Math/Code,humaneval,accuracy,0.8780487804878049,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,Danish,angry_tweets,macro_f1,0.6891974837034677,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,Danish,dala,macro_f1,0.7010772018763602,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,Danish,gec_dala,exact_match,0.51953125,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,Danish,piqa,accuracy,0.6203703703703703,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,Danish,daisy,exact_match,0.08445945945945946,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,Danish,multi_wiki_qa,exact_match,0.50439453125,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,Danish,wmt24pp,chrf3pp,0.5481940828649609,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,Danish,nordjylland,rouge1,0.22313398998239148,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,Danish,ifeval_da,prompt_strict_acc,0.7079482439926063,runs/three_model_full_20260922/results.csv | |
| Qwen3.5-9B,Danish,hellaswag_da,accuracy,0.70703125,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E2B,English,boolq,accuracy,0.641131498470948,logs_ie_rerun/Gemma-4-E2B-it/2026-08-12T21-51-19-00-00_boolq-5shot_m9mh77r3nEDMu7WxW8yGk7.eval | |
| Gemma-4-E2B,English,winogrande,accuracy,0.5461720599842147,logs_ie_rerun/Gemma-4-E2B-it/2026-08-12T21-52-00-00-00_winogrande-5shot_Wqovhf5fRfMTXZX9A8u3ah.eval | |
| Gemma-4-E2B,English,hellaswag,accuracy,0.4599183429595698,logs_ie_rerun/Gemma-4-E2B-it/2026-08-12T21-52-20-00-00_hellaswag-10shot_aannuP6cRKXjTqCwvSmQNd.eval | |
| Gemma-4-E2B,English,mmlu,accuracy,0.44069576983335706,logs_ie_rerun/Gemma-4-E2B-it/2026-08-12T21-54-17-00-00_mmlu-5shot_eScK4uLrhHYVTPmwvw2eib.eval | |
| Gemma-4-E2B,English,arc,accuracy,0.6981655290102389,logs_ie_rerun/Gemma-4-E2B-it/2026-08-12T21-57-00-00-00_arc-25shot_BMmT6ZzSsycts4Ae6pamQs.eval | |
| Gemma-4-E2B,English,drop,f1,0.572629260618773,logs_drop_rerun/Gemma-4-E2B-it/2026-08-12T23-55-14-00-00_drop_35a3swGrakdUAa5fTR2GmK.eval | |
| Gemma-4-E2B,English,govreport,rouge1,0.3363182627613803,logs_ie_rerun/Gemma-4-E2B-it/2026-08-12T22-00-01-00-00_govreport-summarization_cCew5e2orV2muUejfb2iHF.eval | |
| Gemma-4-E2B,Math/Code,gsm8k,accuracy,0.8832448824867324,logs_gsm8k_ie/Gemma-4-E2B/2026-08-13T07-25-28-00-00_gsm8k_2ehCQhXHA7kAhGSf4efnkG.eval | |
| Gemma-4-E2B,Math/Code,math,accuracy,0.6422,logs_math_ie/Gemma-4-E2B/chunk0/2026-08-13T07-45-53-00-00_math-ie-chunk0_8GHgDUPRTijXd4TkTB2az7.eval; logs_math_ie/Gemma-4-E2B/chunk1/2026-08-13T07-59-38-00-00_math-ie-chunk1_EBuGftYXui4AyWWqToDiAZ.eval | |
| Gemma-4-E2B,Math/Code,humaneval,accuracy,0.7378048780487805,logs_humaneval_ie/Gemma-4-E2B/2026-08-13T08-31-36-00-00_humaneval-ie_dMp3ZeAcwCkGJY422ZCwUh.eval | |
| Gemma-4-E2B,Danish,angry_tweets,macro_f1,0.6471463928535889,logs_danish/Gemma-4-E2B-it/2026-08-06T11-38-10-00-00_angry-tweets_5gjM8yeawKBDLCqTRhtqPx.eval | |
| Gemma-4-E2B,Danish,dala,macro_f1,0.5666008434411638,logs_danish/Gemma-4-E2B-it/2026-08-06T11-38-10-00-00_dala_bvRNG9dJseaDujkr8CDSG5.eval | |
| Gemma-4-E2B,Danish,gec_dala,exact_match,0.369140625,logs_danish/Gemma-4-E2B-it/2026-08-06T11-38-12-00-00_gec-dala_6d8kydq9bPkXHBVAmzn8Mb.eval | |
| Gemma-4-E2B,Danish,piqa,accuracy,0.46296296296296297,logs_danish/Gemma-4-E2B-it/2026-08-06T11-38-10-00-00_piqa_9BA73LkBoxXoppVcYDWonj.eval | |
| Gemma-4-E2B,Danish,daisy,exact_match,0.05574324324324324,logs_danish/Gemma-4-E2B-it/2026-08-06T11-38-10-00-00_daisy_mdfnuqnxzy6Ztka2Jv48gb.eval | |
| Gemma-4-E2B,Danish,multi_wiki_qa,exact_match,0.44091796875,logs_danish/Gemma-4-E2B-it/2026-08-06T11-38-12-00-00_multi-wiki-qa_FL28fN9QCzP2rstv3R7AcY.eval | |
| Gemma-4-E2B,Danish,wmt24pp,chrf3pp,0.5521017413094839,logs_danish/Gemma-4-E2B-it/2026-08-06T11-38-12-00-00_wmt24pp-en-da_SY8aukT6asqfMQ2Mi5nDNZ.eval | |
| Gemma-4-E2B,Danish,nordjylland,rouge1,0.2052833291613201,logs_summarization/Gemma-4-E2B-it/2026-08-06T14-38-35-00-00_nordjylland-news-summarization_gJbhSFxEdeSd7ZDBVtfbMi.eval | |
| Gemma-4-E2B,Danish,ifeval_da,prompt_strict_acc,0.6950092421441775,logs_danish/Gemma-4-E2B-it/2026-08-06T11-38-11-00-00_ifeval-da_FCSXGCCAyeHitW3JCoexPG.eval | |
| Gemma-4-E2B,Danish,hellaswag_da,accuracy,0.4483642578125,runs/hellaswag_da_letter_only_comparison_20260922/results.csv | |
| Gemma-4-E4B,English,boolq,accuracy,0.8524464831804281,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,English,winogrande,accuracy,0.6397000789265983,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,English,hellaswag,accuracy,0.4457528380800637,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,English,mmlu,accuracy,0.3539737929069933,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,English,arc,accuracy,0.4980375426621161,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,English,drop,f1,0.7404006292606187,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,English,govreport,rouge1,0.3121701357479731,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,Math/Code,gsm8k,accuracy,0.9196360879454132,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,Math/Code,math,accuracy,0.7184,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,Math/Code,humaneval,accuracy,0.8475609756097561,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,Danish,angry_tweets,macro_f1,0.6973573228500932,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,Danish,dala,macro_f1,0.6303027860320995,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,Danish,gec_dala,exact_match,0.494140625,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,Danish,piqa,accuracy,0.7129629629629629,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,Danish,daisy,exact_match,0.07939189189189189,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,Danish,multi_wiki_qa,exact_match,0.53515625,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,Danish,wmt24pp,chrf3pp,0.5729689850903782,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,Danish,nordjylland,rouge1,0.22014119194434706,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,Danish,ifeval_da,prompt_strict_acc,0.7726432532347505,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B,Danish,hellaswag_da,accuracy,0.6429443359375,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,English,boolq,accuracy,0.8842507645259939,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,English,winogrande,accuracy,0.760457774269929,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,English,hellaswag,accuracy,0.6981676956781517,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,English,mmlu,accuracy,0.68601338840621,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,English,arc,accuracy,0.8880119453924915,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,English,drop,f1,0.7993099108547457,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,English,govreport,rouge1,0.3419552412870043,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,Math/Code,gsm8k,accuracy,0.9378316906747536,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,Math/Code,math,accuracy,0.753,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,Math/Code,humaneval,accuracy,0.774390243902439,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,Danish,angry_tweets,macro_f1,0.6990160416730107,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,Danish,dala,macro_f1,0.7255081940580388,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,Danish,gec_dala,exact_match,0.396484375,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,Danish,piqa,accuracy,0.6944444444444444,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,Danish,daisy,exact_match,0.07601351351351351,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,Danish,multi_wiki_qa,exact_match,0.60595703125,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,Danish,wmt24pp,chrf3pp,0.5751515125358806,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,Danish,nordjylland,rouge1,0.2141142875267328,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,Danish,ifeval_da,prompt_strict_acc,0.8040665434380776,runs/three_model_full_20260922/results.csv | |
| Gemma-4-E4B-thinking,Danish,hellaswag_da,accuracy,0.661865234375,runs/three_model_full_20260922/results.csv | |
| Gemma-3-1B,English,boolq,accuracy,0.6238532110091743,logs_ie_rerun/Gemma-3-1b-it/2026-08-12T21-49-54-00-00_boolq-5shot_9F6w4fte9orBNndtuA4cKY.eval | |
| Gemma-3-1B,English,winogrande,accuracy,0.5169692186266772,logs_ie_rerun/Gemma-3-1b-it/2026-08-12T21-50-35-00-00_winogrande-5shot_T9mzuP6iGfXRhtySwuQySH.eval | |
| Gemma-3-1B,English,hellaswag,accuracy,0.30561641107349136,logs_ie_rerun/Gemma-3-1b-it/2026-08-12T21-50-56-00-00_hellaswag-10shot_QufKebx6bWeSFVmgxj2YtN.eval | |
| Gemma-3-1B,English,mmlu,accuracy,0.37523144851160806,logs_ie_rerun/Gemma-3-1b-it/2026-08-12T21-53-07-00-00_mmlu-5shot_nNnd9qi4SnnVrfHZBapnd3.eval | |
| Gemma-3-1B,English,arc,accuracy,0.4351535836177474,logs_ie_rerun/Gemma-3-1b-it/2026-08-12T21-56-07-00-00_arc-25shot_8SY7GEA44YLbwDvnVTXtis.eval | |
| Gemma-3-1B,English,drop,f1,0.06962873623492397,logs_drop_rerun/Gemma-3-1b-it/2026-08-12T23-53-44-00-00_drop_XHY4s2n3Um5A2bbcG9KJZk.eval | |
| Gemma-3-1B,English,govreport,rouge1,0.2946425399902126,logs_ie_rerun/Gemma-3-1b-it/2026-08-12T21-59-51-00-00_govreport-summarization_MPWyXumJJjVuSsZKH2dKwh.eval | |
| Gemma-3-1B,Math/Code,gsm8k,accuracy,0.4965883244882487,logs_gsm8k_ie/Gemma-3-1B/2026-08-13T07-25-28-00-00_gsm8k_HRbxEfpeG7GAxGqy9eC9zW.eval | |
| Gemma-3-1B,Math/Code,math,accuracy,0.3722,logs_math_ie/Gemma-3-1B/chunk0/2026-08-13T07-45-54-00-00_math-ie-chunk0_n2t2LhV2diACCWGFUyVRZC.eval; logs_math_ie/Gemma-3-1B/chunk1/2026-08-13T07-59-37-00-00_math-ie-chunk1_2vE5DqXKZrZpgAYmATTLLb.eval | |
| Gemma-3-1B,Math/Code,humaneval,accuracy,0.4268292682926829,logs_humaneval_ie/Gemma-3-1B/2026-08-13T08-31-36-00-00_humaneval-ie_kMvxvFuKNAYVKkBUnZTGek.eval | |
| Gemma-3-1B,Danish,angry_tweets,macro_f1,0.5068524041510094,logs_new_models_full/Gemma-3-1b-it/2026-08-12T09-04-44-00-00_angry-tweets_QTJuPwe4tJ3QFWGsFaAP4G.eval | |
| Gemma-3-1B,Danish,dala,macro_f1,0.41031113204482145,logs_new_models_full/Gemma-3-1b-it/2026-08-12T09-05-00-00-00_dala_ipnvtiWVfkmBRXdpQHfuxv.eval | |
| Gemma-3-1B,Danish,gec_dala,exact_match,0.033203125,logs_new_models_full/Gemma-3-1b-it/2026-08-12T09-05-30-00-00_gec-dala_Z34RVSJ4HYjdkpo8rzCUMg.eval | |
| Gemma-3-1B,Danish,piqa,accuracy,0.7222222222222222,logs_new_models_full/Gemma-3-1b-it/2026-08-12T09-05-47-00-00_piqa_DDtgpkCzUPP9VMUxjqewvd.eval | |
| Gemma-3-1B,Danish,daisy,exact_match,0.013513513513513514,logs_new_models_full/Gemma-3-1b-it/2026-08-12T09-05-53-00-00_daisy_DNpc3PjweFSVhNLCCrC3am.eval | |
| Gemma-3-1B,Danish,multi_wiki_qa,exact_match,0.42626953125,logs_new_models_full/Gemma-3-1b-it/2026-08-12T09-06-04-00-00_multi-wiki-qa_oL964vakUGLkV4QqcaYxr5.eval | |
| Gemma-3-1B,Danish,wmt24pp,chrf3pp,0.4512909156851684,logs_new_models_full/Gemma-3-1b-it/2026-08-12T09-06-35-00-00_wmt24pp-en-da_XsNv3jr3aU7SsD4VeTbrLa.eval | |
| Gemma-3-1B,Danish,nordjylland,rouge1,0.21728517164838382,logs_new_models_full/Gemma-3-1b-it/2026-08-12T09-09-27-00-00_nordjylland-news-summarization_EpjyqVAa34hMVgQLhcQck8.eval | |
| Gemma-3-1B,Danish,ifeval_da,prompt_strict_acc,0.3733826247689464,logs_new_models_full/Gemma-3-1b-it/2026-08-12T09-06-52-00-00_ifeval-da_Wpy48ezHznKjukg5yrPcx8.eval | |
| Gemma-3-1B,Danish,hellaswag_da,accuracy,0.245849609375,runs/hellaswag_da_letter_only_comparison_20260922/results.csv | |
| OLMo-2-1B,English,boolq,accuracy,0.671559633027523,logs_ie_rerun/OLMo-2-1B-Instruct/2026-08-12T21-49-52-00-00_boolq-5shot_n9qWbaSPpYLLoCcX3HnCJd.eval | |
| OLMo-2-1B,English,winogrande,accuracy,0.5035516969218626,logs_ie_rerun/OLMo-2-1B-Instruct/2026-08-12T21-50-29-00-00_winogrande-5shot_Z7WVmfaFb5UPhLCTKgLSdM.eval | |
| OLMo-2-1B,English,hellaswag,accuracy,0.4237203744274049,logs_ie_rerun/OLMo-2-1B-Instruct/2026-08-12T21-50-49-00-00_hellaswag-10shot_JQED9qB8io2Fa3BiuHuMbz.eval | |
| OLMo-2-1B,English,mmlu,accuracy,0.4161088164079191,logs_ie_rerun/OLMo-2-1B-Instruct/2026-08-12T21-52-38-00-00_mmlu-5shot_i4HBEpRGyTnkUPJ82epwve.eval | |
| OLMo-2-1B,English,arc,accuracy,0.4812286689419795,logs_ie_rerun/OLMo-2-1B-Instruct/2026-08-12T21-55-09-00-00_arc-25shot_g86mXikkeJbubYBJia7GwY.eval | |
| OLMo-2-1B,English,drop,f1,0.12380597797587835,logs_drop_rerun/OLMo-2-1B-Instruct/2026-08-12T23-53-43-00-00_drop_9ktTGyXUGMtsAVB3ogFWqh.eval | |
| OLMo-2-1B,English,govreport,rouge1,0.37722454353306173,logs_ie_rerun/OLMo-2-1B-Instruct/2026-08-12T21-58-43-00-00_govreport-summarization_MhpUDXHF9i6nLHLS5bQDm9.eval | |
| OLMo-2-1B,Math/Code,gsm8k,accuracy,0.5936315390447309,logs_gsm8k_ie/OLMo-2-1B/2026-08-13T07-25-28-00-00_gsm8k_L5HCQRphWpME3Hfk33rL2X.eval | |
| OLMo-2-1B,Math/Code,math,accuracy,0.1884,logs_math_ie/OLMo-2-1B/chunk0/2026-08-13T07-45-53-00-00_math-ie-chunk0_PNW2sR3iakqcxurQENiLmF.eval; logs_math_ie/OLMo-2-1B/chunk1/2026-08-13T07-59-38-00-00_math-ie-chunk1_UxPBHsovmjmvSDozN86mTw.eval | |
| OLMo-2-1B,Math/Code,humaneval,accuracy,0.15853658536585366,logs_humaneval_ie/OLMo-2-1B/2026-08-13T08-31-36-00-00_humaneval-ie_9U6JrKUX8jAFJfKXcqYxKp.eval | |
| OLMo-2-1B,Danish,angry_tweets,macro_f1,0.26546108788123335,logs_new_models_full/OLMo-2-1B-Instruct/2026-08-12T08-50-14-00-00_angry-tweets_DiaZ87sjRp6AhpX5y2pCU2.eval | |
| OLMo-2-1B,Danish,dala,macro_f1,0.487017430811512,logs_new_models_full/OLMo-2-1B-Instruct/2026-08-12T08-50-28-00-00_dala_4YXRaJ2wzfuPrLWcyk3WLZ.eval | |
| OLMo-2-1B,Danish,gec_dala,exact_match,0.001953125,logs_new_models_full/OLMo-2-1B-Instruct/2026-08-12T08-50-53-00-00_gec-dala_RppeToupBEknS7yi3QiQoc.eval | |
| OLMo-2-1B,Danish,piqa,accuracy,0.75,logs_new_models_full/OLMo-2-1B-Instruct/2026-08-12T08-51-08-00-00_piqa_g4adUETL9E38JQyexSRNpp.eval | |
| OLMo-2-1B,Danish,daisy,exact_match,0.0,logs_new_models_full/OLMo-2-1B-Instruct/2026-08-12T08-51-16-00-00_daisy_KuYsMp3t7csDdM85KZ7azr.eval | |
| OLMo-2-1B,Danish,multi_wiki_qa,exact_match,0.083984375,logs_new_models_full/OLMo-2-1B-Instruct/2026-08-12T08-51-27-00-00_multi-wiki-qa_KpAYM2yJ4hcoMtbw6hzamb.eval | |
| OLMo-2-1B,Danish,wmt24pp,chrf3pp,0.2997191232553838,logs_new_models_full/OLMo-2-1B-Instruct/2026-08-12T08-51-56-00-00_wmt24pp-en-da_j7iTxyDThCdUEoc4XNnEZC.eval | |
| OLMo-2-1B,Danish,nordjylland,rouge1,0.19298607601957996,logs_new_models_full/OLMo-2-1B-Instruct/2026-08-12T08-52-44-00-00_nordjylland-news-summarization_FLrB4vmmJq2f5wQApBrWnv.eval | |
| OLMo-2-1B,Danish,ifeval_da,prompt_strict_acc,0.24214417744916822,logs_new_models_full/OLMo-2-1B-Instruct/2026-08-12T08-52-10-00-00_ifeval-da_NVC8gXLgcQVpfaMtwgymhY.eval | |
| OLMo-2-1B,Danish,hellaswag_da,accuracy,0.2490234375,runs/hellaswag_da_letter_only_comparison_20260922/results.csv | |
| SmolLM3-3B,English,boolq,accuracy,0.8434250764525993,logs_ie_rerun/SmolLM3-3B/2026-08-12T21-50-13-00-00_boolq-5shot_MDexksaFRDYjcaAYyDwQYS.eval | |
| SmolLM3-3B,English,winogrande,accuracy,0.6029992107340174,logs_ie_rerun/SmolLM3-3B/2026-08-12T21-50-53-00-00_winogrande-5shot_hhjvvMYDDprpNaVivHwDtr.eval | |
| SmolLM3-3B,English,hellaswag,accuracy,0.6509659430392352,logs_ie_rerun/SmolLM3-3B/2026-08-12T21-51-12-00-00_hellaswag-10shot_2y8LgLArqQFvgK4d7xafC9.eval | |
| SmolLM3-3B,English,mmlu,accuracy,0.6016237003275887,logs_ie_rerun/SmolLM3-3B/2026-08-12T21-53-11-00-00_mmlu-5shot_FySWLxKtks4xYwXtUhTmrx.eval | |
| SmolLM3-3B,English,arc,accuracy,0.7954351535836177,logs_ie_rerun/SmolLM3-3B/2026-08-12T21-55-56-00-00_arc-25shot_AqDnhLei9mizjxc3RaGQ5p.eval | |
| SmolLM3-3B,English,drop,f1,0.5396088096486629,logs_drop_rerun/SmolLM3-3B/2026-08-12T23-54-05-00-00_drop_RZaAz7fXnYSpJXkVy5DYxg.eval | |
| SmolLM3-3B,English,govreport,rouge1,0.38133203812101507,logs_ie_rerun/SmolLM3-3B/2026-08-12T21-59-49-00-00_govreport-summarization_4ET2FUKomiSMsXagyV5Z2s.eval | |
| SmolLM3-3B,Math/Code,gsm8k,accuracy,0.7998483699772555,logs_gsm8k_ie/SmolLM3-3B/2026-08-13T07-25-28-00-00_gsm8k_2d8uXASBdsMsHtAsiYZjpx.eval | |
| SmolLM3-3B,Math/Code,math,accuracy,0.6222,logs_math_ie/SmolLM3-3B/chunk0/2026-08-13T07-45-54-00-00_math-ie-chunk0_EXkJYiirMLiSqs4CGoUvmJ.eval; logs_math_ie/SmolLM3-3B/chunk1/2026-08-13T07-59-38-00-00_math-ie-chunk1_bi6n9XSdigh49o4kSXP59g.eval | |
| SmolLM3-3B,Math/Code,humaneval,accuracy,0.6158536585365854,logs_humaneval_ie/SmolLM3-3B/2026-08-13T08-31-36-00-00_humaneval-ie_YBnfMT29yaAyoYHEEUnFPg.eval | |
| SmolLM3-3B,Danish,angry_tweets,macro_f1,0.6270140085057085,logs_new_models_full/SmolLM3-3B/2026-08-12T08-55-46-00-00_angry-tweets_hemCJEX6p2LgbsWGEkxmhx.eval | |
| SmolLM3-3B,Danish,dala,macro_f1,0.3350615617976958,logs_new_models_full/SmolLM3-3B/2026-08-12T08-56-01-00-00_dala_SiB2cucPTPGLqYwKcYryjk.eval | |
| SmolLM3-3B,Danish,gec_dala,exact_match,0.033203125,logs_new_models_full/SmolLM3-3B/2026-08-12T08-56-29-00-00_gec-dala_dZLP6su8V65DUUe8uJtj5z.eval | |
| SmolLM3-3B,Danish,piqa,accuracy,0.5185185185185185,logs_new_models_full/SmolLM3-3B/2026-08-12T08-56-48-00-00_piqa_Efqx4muCzfL5VLGFhwZLtp.eval | |
| SmolLM3-3B,Danish,daisy,exact_match,0.02195945945945946,logs_new_models_full/SmolLM3-3B/2026-08-12T08-58-26-00-00_daisy_AECcsqjTMpoTA65KCXMmr2.eval | |
| SmolLM3-3B,Danish,multi_wiki_qa,exact_match,0.0029296875,logs_new_models_full/SmolLM3-3B/2026-08-12T08-58-37-00-00_multi-wiki-qa_CwuhTfMwAubXGDT4nbonvE.eval | |
| SmolLM3-3B,Danish,wmt24pp,chrf3pp,0.3727262940064309,logs_new_models_full/SmolLM3-3B/2026-08-12T08-59-09-00-00_wmt24pp-en-da_35P4a3yWE4jmqgxTionDQA.eval | |
| SmolLM3-3B,Danish,nordjylland,rouge1,0.18827710999394406,logs_new_models_full/SmolLM3-3B/2026-08-12T09-05-39-00-00_nordjylland-news-summarization_QGjpqYsVfhtNfVv8wyzfgA.eval | |
| SmolLM3-3B,Danish,ifeval_da,prompt_strict_acc,0.41035120147874304,logs_new_models_full/SmolLM3-3B/2026-08-12T08-59-29-00-00_ifeval-da_8gfdcVJFzcwTkXZ4EPsWs6.eval | |
| SmolLM3-3B,Danish,hellaswag_da,accuracy,0.37158203125,runs/hellaswag_da_letter_only_comparison_20260922/results.csv | |
| EuroLLM-9B,English,boolq,accuracy,0.8535168195718654,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,English,winogrande,accuracy,0.6124704025256511,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,English,hellaswag,accuracy,0.586337382991436,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,English,mmlu,accuracy,0.582538099985757,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,English,arc,accuracy,0.765358361774744,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,English,drop,f1,0.5475395909805977,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,English,govreport,rouge1,0.2949662259274597,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,Math/Code,gsm8k,accuracy,0.0,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,Math/Code,math,accuracy,0.2994,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,Math/Code,humaneval,accuracy,0.21951219512195122,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,Danish,angry_tweets,macro_f1,0.646684591941585,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,Danish,dala,macro_f1,0.37759603683960197,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,Danish,gec_dala,exact_match,0.4765625,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,Danish,piqa,accuracy,0.7129629629629629,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,Danish,daisy,exact_match,0.14864864864864866,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,Danish,multi_wiki_qa,exact_match,0.5087890625,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,Danish,wmt24pp,chrf3pp,0.5676644925315261,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,Danish,nordjylland,rouge1,0.23176235409557233,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,Danish,ifeval_da,prompt_strict_acc,0.5027726432532348,runs/three_model_full_20260922/results.csv | |
| EuroLLM-9B,Danish,hellaswag_da,accuracy,0.400390625,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,English,boolq,accuracy,0.7966360856269113,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,English,winogrande,accuracy,0.5603788476716653,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,English,hellaswag,accuracy,0.6686914957179845,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,English,mmlu,accuracy,0.6214214499359065,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,English,arc,accuracy,0.7926621160409556,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,English,drop,f1,0.5247456738332459,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,English,govreport,rouge1,0.34964717279400975,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,Math/Code,gsm8k,accuracy,0.6671721000758151,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,Math/Code,math,accuracy,0.2536,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,Math/Code,humaneval,accuracy,0.4024390243902439,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,Danish,angry_tweets,macro_f1,0.6346919907173152,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,Danish,dala,macro_f1,0.5145800661711945,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,Danish,gec_dala,exact_match,0.3759765625,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,Danish,piqa,accuracy,0.6944444444444444,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,Danish,daisy,exact_match,0.10810810810810811,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,Danish,multi_wiki_qa,exact_match,0.59375,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,Danish,wmt24pp,chrf3pp,0.5577900517565848,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,Danish,nordjylland,rouge1,0.21271944106221985,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,Danish,ifeval_da,prompt_strict_acc,0.5600739371534196,runs/three_model_full_20260922/results.csv | |
| Apertus-8B,Danish,hellaswag_da,accuracy,0.39990234375,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,English,boolq,accuracy,0.882262996941896,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,English,winogrande,accuracy,0.6716653512233622,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,English,hellaswag,accuracy,0.6760605457080263,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,English,mmlu,accuracy,0.7392821535393819,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,English,arc,accuracy,0.9010238907849829,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,English,drop,f1,0.8103125327739905,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,English,govreport,rouge1,0.3132415813365658,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,Math/Code,gsm8k,accuracy,0.9166034874905231,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,Math/Code,math,accuracy,0.6144,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,Math/Code,humaneval,accuracy,0.7560975609756098,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,Danish,angry_tweets,macro_f1,0.6392830722014208,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,Danish,dala,macro_f1,0.5890850722311396,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,Danish,gec_dala,exact_match,0.1787109375,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,Danish,piqa,accuracy,0.6296296296296297,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,Danish,daisy,exact_match,0.07263513513513513,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,Danish,multi_wiki_qa,exact_match,0.4873046875,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,Danish,wmt24pp,chrf3pp,0.5019232344680641,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,Danish,nordjylland,rouge1,0.1843271529330982,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,Danish,ifeval_da,prompt_strict_acc,0.48613678373382624,runs/three_model_full_20260922/results.csv | |
| Ministral-3-8B,Danish,hellaswag_da,accuracy,0.4544677734375,runs/three_model_full_20260922/results.csv | |
| Munin-Apertus-8B,Danish,angry_tweets,macro_f1,0.6142041110145482,logs_danish/Munin-Apertus-8b/2026-08-06T11-51-54-00-00_angry-tweets_deNeCA7R6GfhX9GoAapmvq.eval | |
| Munin-Apertus-8B,Danish,dala,macro_f1,0.46078826592203426,logs_danish/Munin-Apertus-8b/2026-08-06T11-51-00-00-00_dala_jkk9mGZ6juvAHCPVtvKvy5.eval | |
| Munin-Apertus-8B,Danish,gec_dala,exact_match,0.4208984375,logs_danish/Munin-Apertus-8b/2026-08-06T11-51-03-00-00_gec-dala_itWmt8t6DGmDugVHsS5FUt.eval | |
| Munin-Apertus-8B,Danish,piqa,accuracy,0.8148148148148148,logs_danish/Munin-Apertus-8b/2026-08-06T11-51-02-00-00_piqa_J4PREd6pSeWfX6xk3XG5wE.eval | |
| Munin-Apertus-8B,Danish,daisy,exact_match,0.125,logs_danish/Munin-Apertus-8b/2026-08-06T11-51-03-00-00_daisy_aE8c5gFdEm6rxCMniGig7n.eval | |
| Munin-Apertus-8B,Danish,multi_wiki_qa,exact_match,0.4990234375,logs_danish/Munin-Apertus-8b/2026-08-06T11-51-06-00-00_multi-wiki-qa_6DjYQfXjqeqn3hHZ3qF7S4.eval | |
| Munin-Apertus-8B,Danish,wmt24pp,chrf3pp,0.5584896191926343,logs_danish/Munin-Apertus-8b/2026-08-06T11-51-06-00-00_wmt24pp-en-da_bPnWd78TGi2DWSUdFtKKJT.eval | |
| Munin-Apertus-8B,Danish,nordjylland,rouge1,0.1265888424264116,logs_summarization/Munin-Apertus-8b/2026-08-06T14-33-49-00-00_nordjylland-news-summarization_9deybKu7c7kq2qDd3ci3Zv.eval | |
| Munin-Apertus-8B,Danish,ifeval_da,prompt_strict_acc,0.43807763401109057,logs_danish/Munin-Apertus-8b/2026-08-06T11-51-06-00-00_ifeval-da_dXbp5XvXHT6jMxjPn9EZrR.eval | |
| Munin-Apertus-8B,Danish,hellaswag_da,accuracy,0.37744140625,runs/hellaswag_da_letter_only_comparison_20260922/results.csv | |
| Munin-Mistral-8B,Danish,angry_tweets,macro_f1,0.5930874408554814,logs_danish/Munin-Mistral3-8B-fixed/2026-08-06T15-40-45-00-00_angry-tweets_QsMaAmuEeW8KXkAPAc4C7C.eval | |
| Munin-Mistral-8B,Danish,dala,macro_f1,0.4884984376717383,logs_danish/Munin-Mistral3-8B-fixed/2026-08-06T15-28-40-00-00_dala_QR4jugPe3sMLNmRXnSzHSS.eval | |
| Munin-Mistral-8B,Danish,gec_dala,exact_match,0.263671875,logs_danish/Munin-Mistral3-8B-fixed/2026-08-06T15-31-51-00-00_gec-dala_KyWmskH4w3ZkJjHosc7QVc.eval | |
| Munin-Mistral-8B,Danish,piqa,accuracy,0.7685185185185185,logs_danish/Munin-Mistral3-8B-fixed/2026-08-06T15-39-27-00-00_piqa_gEozwvLLPnmYR8YYeSvQGp.eval | |
| Munin-Mistral-8B,Danish,daisy,exact_match,0.08445945945945946,logs_danish/Munin-Mistral3-8B-fixed/2026-08-06T15-39-27-00-00_daisy_9w9SRQKJkw2QUTTUR4kByB.eval | |
| Munin-Mistral-8B,Danish,multi_wiki_qa,exact_match,0.48388671875,logs_danish/Munin-Mistral3-8B-fixed/2026-08-06T15-39-29-00-00_multi-wiki-qa_THL3hSXcm6GxCBSXE68fVb.eval | |
| Munin-Mistral-8B,Danish,wmt24pp,chrf3pp,0.5181061407394355,logs_danish/Munin-Mistral3-8B-fixed/2026-08-06T15-39-29-00-00_wmt24pp-en-da_GyngsgEpX6c4RRn7spJznK.eval | |
| Munin-Mistral-8B,Danish,nordjylland,rouge1,0.160895459195255,logs_danish/Munin-Mistral3-8B-fixed/2026-08-06T15-40-44-00-00_nordjylland-news-summarization_74gBosqMQtXkjMQjzzuLu2.eval | |
| Munin-Mistral-8B,Danish,ifeval_da,prompt_strict_acc,0.5914972273567468,logs_danish/Munin-Mistral3-8B-fixed/2026-08-06T15-40-45-00-00_ifeval-da_eQjNeETHdV35MaxrWWQWUH.eval | |
| Munin-Mistral-8B,Danish,hellaswag_da,accuracy,0.2606201171875,runs/hellaswag_da_letter_only_comparison_20260922/results.csv | |
| Munin-Qwen-9B,Danish,angry_tweets,macro_f1,0.6822337060463216,logs_danish/Munin-Qwen3.5-9B/2026-08-06T11-52-10-00-00_angry-tweets_2RxU9Dm8pRg2AqyCAw2edg.eval | |
| Munin-Qwen-9B,Danish,dala,macro_f1,0.6062153241170991,logs_danish/Munin-Qwen3.5-9B/2026-08-06T11-52-11-00-00_dala_Gqzpr9TkSmRUqj8HPNHhyY.eval | |
| Munin-Qwen-9B,Danish,gec_dala,exact_match,0.1142578125,logs_danish/Munin-Qwen3.5-9B/2026-08-06T11-52-14-00-00_gec-dala_QJToo2DS8d2qH2EhUw2dht.eval | |
| Munin-Qwen-9B,Danish,piqa,accuracy,0.3888888888888889,logs_danish/Munin-Qwen3.5-9B/2026-08-06T11-52-13-00-00_piqa_UHU8eVNLCKe4B6aiEYLVga.eval | |
| Munin-Qwen-9B,Danish,daisy,exact_match,0.05405405405405406,logs_danish/Munin-Qwen3.5-9B/2026-08-06T11-52-13-00-00_daisy_8t7Nefm6QyvKtd7uJnASgS.eval | |
| Munin-Qwen-9B,Danish,multi_wiki_qa,exact_match,0.556640625,logs_danish/Munin-Qwen3.5-9B/2026-08-06T11-52-16-00-00_multi-wiki-qa_7oBFpwpxSup9cJTP5AniuE.eval | |
| Munin-Qwen-9B,Danish,wmt24pp,chrf3pp,0.560522070881221,logs_danish/Munin-Qwen3.5-9B/2026-08-06T11-52-17-00-00_wmt24pp-en-da_izHUxjsQDhs76Gz42U9zuQ.eval | |
| Munin-Qwen-9B,Danish,nordjylland,rouge1,0.19874683739219898,logs_summarization/Munin-Qwen3.5-9B/2026-08-06T14-38-37-00-00_nordjylland-news-summarization_bu9Bc8Mb487MhRGy6WoHHG.eval | |
| Munin-Qwen-9B,Danish,ifeval_da,prompt_strict_acc,0.6487985212569316,logs_danish/Munin-Qwen3.5-9B/2026-08-06T11-52-16-00-00_ifeval-da_Nscf7vi4AFCdhngVQ9Vcqu.eval | |
| Munin-Qwen-9B,Danish,hellaswag_da,accuracy,0.66943359375,runs/hellaswag_da_letter_only_comparison_20260922/results.csv | |
| Ouro-1.4B,English,boolq,accuracy,0.8388379204892966,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,English,winogrande,accuracy,0.5595895816890292,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,English,hellaswag,accuracy,0.5963951404102769,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,English,mmlu,accuracy,0.6704885343968096,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,English,arc,accuracy,0.8694539249146758,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,English,drop,f1,0.3887393812270582,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,English,govreport,rouge1,0.32398799555321783,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,Math/Code,gsm8k,accuracy,0.6345716451857468,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,Math/Code,math,accuracy,0.5156,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,Math/Code,humaneval,accuracy,0.5487804878048781,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,Danish,angry_tweets,macro_f1,0.18770927251303124,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,Danish,dala,macro_f1,0.3562276075724269,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,Danish,gec_dala,exact_match,0.0029296875,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,Danish,piqa,accuracy,0.8611111111111112,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,Danish,daisy,exact_match,0.005067567567567568,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,Danish,multi_wiki_qa,exact_match,0.12451171875,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,Danish,wmt24pp,chrf3pp,0.27691011701336,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,Danish,nordjylland,rouge1,0.18977789397989486,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,Danish,ifeval_da,prompt_strict_acc,0.2255083179297597,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-1.4B,Danish,hellaswag_da,accuracy,0.2501220703125,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,English,boolq,accuracy,0.8902140672782874,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,English,winogrande,accuracy,0.7166535122336227,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,English,hellaswag,accuracy,0.7837084246166103,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,English,mmlu,accuracy,0.7448547215496368,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,English,arc,accuracy,0.9300341296928327,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,English,drop,f1,0.5195018353434715,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,English,govreport,rouge1,0.3308324708782202,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,Math/Code,gsm8k,accuracy,0.7399545109931767,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,Math/Code,math,accuracy,0.5902,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,Math/Code,humaneval,accuracy,0.49390243902439024,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,Danish,angry_tweets,macro_f1,0.17780673410006187,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,Danish,dala,macro_f1,0.3333333333333333,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,Danish,gec_dala,exact_match,0.0078125,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,Danish,piqa,accuracy,0.7592592592592593,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,Danish,daisy,exact_match,0.013513513513513514,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,Danish,multi_wiki_qa,exact_match,0.24755859375,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,Danish,wmt24pp,chrf3pp,0.29972832371268227,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,Danish,nordjylland,rouge1,0.1905467605361224,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,Danish,ifeval_da,prompt_strict_acc,0.2680221811460259,runs/ouro_full_20260925/macro_inputs.json | |
| Ouro-2.6B,Danish,hellaswag_da,accuracy,0.24169921875,runs/ouro_full_20260925/macro_inputs.json | |