{ "HuggingFaceFW/fineweb-edu-classifier": { "en_llama3": { "n": 6000, "spearman": 0.7811745959348265, "pearson": 0.8254685326164869, "f1_ge3": 0.7167381974248928, "acc_round": 0.7331666666666666, "mean_pred": 1.303708251953125 }, "fw2_gemma": { "n": 9750, "spearman": 0.31332828330222384, "pearson": 0.3201400964584369, "f1_ge3": 0.014141414141414142, "acc_round": 0.4175384615384615, "mean_pred": 0.7903328074919872, "by_lang": { "afr_Latn": 0.4783886151902705, "amh_Ethi": 0.0035800511195597565, "arb_Arab": 0.18433856457178072, "azj_Latn": 0.09337074285835445, "ben_Beng": -0.09760323618540227, "bul_Cyrl": 0.20503335722132798, "cat_Latn": 0.6595302771997552, "ces_Latn": 0.3599752431781002, "cmn_Hani": 0.36116549630361733, "dan_Latn": 0.6001897248450279, "deu_Latn": 0.6149203082616248, "ekk_Latn": 0.3708713726345026, "ell_Grek": 0.2641394141294525, "eus_Latn": 0.3617396078726179, "fas_Arab": 0.25725247538293716, "fil_Latn": 0.5192007594329661, "fin_Latn": 0.4594319524209811, "fra_Latn": 0.7030699852374831, "glg_Latn": 0.46222411627307064, "guj_Gujr": 0.17410758233215715, "heb_Hebr": 0.2552741558144449, "hin_Deva": 0.21684813093532157, "hrv_Latn": 0.3901958638082959, "hun_Latn": 0.4679083623541295, "hye_Armn": 0.17378206897576237, "ind_Latn": 0.5425439672915935, "isl_Latn": 0.36410277837656496, "ita_Latn": 0.7114280686997687, "jpn_Jpan": 0.35637333571825525, "kan_Knda": 0.2159835575450683, "kat_Geor": 0.20181702902943727, "kaz_Cyrl": 0.07028438701894076, "khm_Khmr": 0.19854930856895855, "kor_Hang": 0.36423478651136526, "lit_Latn": 0.44426372175382817, "lvs_Latn": 0.42898220014392424, "mal_Mlym": 0.254422574383917, "mar_Deva": -0.02052601043908013, "mkd_Cyrl": 0.17931674439965872, "mya_Mymr": 0.060353023381646796, "nld_Latn": 0.7176838890206896, "nob_Latn": 0.6039381224420028, "npi_Deva": 0.24364382637822735, "pan_Guru": 0.3141409775437518, "pol_Latn": 0.5030397252962449, "por_Latn": 0.6909333335761909, "ron_Latn": 0.5864636995970052, "rus_Cyrl": 0.2812129159232862, "sin_Sinh": 0.3592815174301788, "slk_Latn": 0.4598330329453881, "slv_Latn": 0.5057813338679621, "spa_Latn": 0.6448157099816524, "srp_Cyrl": 0.23893350817449613, "swe_Latn": 0.6506862369110045, "swh_Latn": 0.25299473872794553, "tam_Taml": 0.22364087822978565, "tel_Telu": 0.1593746895000516, "tha_Thai": 0.25103745018468, "tur_Latn": 0.5612733688350385, "ukr_Cyrl": 0.2528674145533893, "urd_Arab": 0.15879523016824826, "uzn_Latn": 0.5122183422461761, "vie_Latn": 0.23123533417387576, "yue_Hani": 0.13726957886753305, "zsm_Latn": 0.6246551025461468 }, "lang_mean_spearman": 0.3550279141795836 } }, "nvidia/nemocurator-fineweb-nemotron-4-edu-classifier": { "en_llama3": { "n": 6000, "spearman": 0.6900049364432077, "pearson": 0.6947466119935968, "f1_ge3": 0.5593952483801296, "acc_round": 0.5658333333333333, "mean_pred": 1.387032918294271 }, "fw2_gemma": { "n": 9750, "spearman": 0.2895303544363772, "pearson": 0.2906974159907195, "f1_ge3": 0.004081632653061225, "acc_round": 0.45066666666666666, "mean_pred": 0.640254885942508, "by_lang": { "afr_Latn": 0.4125513088566815, "amh_Ethi": 0.018373213098583384, "arb_Arab": 0.0462338281457406, "azj_Latn": 0.019992976790920432, "ben_Beng": -0.16789892750113863, "bul_Cyrl": 0.2971403726411454, "cat_Latn": 0.6147170553906413, "ces_Latn": 0.39892159831065555, "cmn_Hani": 0.33236056343520864, "dan_Latn": 0.627986710030984, "deu_Latn": 0.5421583888861886, "ekk_Latn": 0.3412602251624262, "ell_Grek": 0.2877695026495254, "eus_Latn": 0.26273050172930285, "fas_Arab": 0.24343030252432032, "fil_Latn": 0.46762500797401985, "fin_Latn": 0.5002472399939247, "fra_Latn": 0.6700508212975463, "glg_Latn": 0.5633083561358194, "guj_Gujr": 0.14136444259530326, "heb_Hebr": 0.04724066128936813, "hin_Deva": 0.22134439322375482, "hrv_Latn": 0.3966049006476282, "hun_Latn": 0.45954093494157644, "hye_Armn": 0.16936739322102382, "ind_Latn": 0.5748003182538665, "isl_Latn": 0.30026748669376563, "ita_Latn": 0.6741036997984878, "jpn_Jpan": 0.3174746581217568, "kan_Knda": 0.023717881864377573, "kat_Geor": 0.21079149629341118, "kaz_Cyrl": 0.033985861656622506, "khm_Khmr": 0.1334958353366269, "kor_Hang": 0.3697988953836682, "lit_Latn": 0.5016548732038005, "lvs_Latn": 0.42824583647664066, "mal_Mlym": 0.22060159988132563, "mar_Deva": 0.012161465310395518, "mkd_Cyrl": 0.2016088441163244, "mya_Mymr": 0.04140935967384132, "nld_Latn": 0.6911094076936222, "nob_Latn": 0.6496771853598793, "npi_Deva": 0.23923633067121167, "pan_Guru": 0.31902012692687165, "pol_Latn": 0.5516762448979281, "por_Latn": 0.6629914217097714, "ron_Latn": 0.5406291022067823, "rus_Cyrl": 0.2241661254766134, "sin_Sinh": 0.43543983599659747, "slk_Latn": 0.4690493972306032, "slv_Latn": 0.42703517488655535, "spa_Latn": 0.6779816003990441, "srp_Cyrl": 0.25743830692710934, "swe_Latn": 0.6697583783089793, "swh_Latn": 0.2949237410105869, "tam_Taml": 0.2864941876005439, "tel_Telu": 0.24945242629027456, "tha_Thai": 0.23070699677653075, "tur_Latn": 0.5232767110609888, "ukr_Cyrl": 0.17294253430222284, "urd_Arab": 0.09084790133296561, "uzn_Latn": 0.36802535578818296, "vie_Latn": 0.3066835352546123, "yue_Hani": 0.2059018457197195, "zsm_Latn": 0.6224283932948171 }, "lang_mean_spearman": 0.34039126385629354 } }, "nvidia/nemocurator-fineweb-mixtral-edu-classifier": { "en_llama3": { "n": 6000, "spearman": 0.7175490136043337, "pearson": 0.7287184005488518, "f1_ge3": 0.614963503649635, "acc_round": 0.6028333333333333, "mean_pred": 1.3429691162109374 }, "fw2_gemma": { "n": 9750, "spearman": 0.2819134647436298, "pearson": 0.28562988667839534, "f1_ge3": 0.002044989775051125, "acc_round": 0.45374358974358975, "mean_pred": 0.47195639272836537, "by_lang": { "afr_Latn": 0.47159183192913195, "amh_Ethi": 0.019598498538088625, "arb_Arab": 0.06822991834984035, "azj_Latn": 0.06953770032467291, "ben_Beng": -0.03358448985760162, "bul_Cyrl": 0.27245858557578745, "cat_Latn": 0.5538705546867907, "ces_Latn": 0.35157906715040116, "cmn_Hani": 0.3077231124197137, "dan_Latn": 0.6222795229134043, "deu_Latn": 0.6118166183216837, "ekk_Latn": 0.40074372684756604, "ell_Grek": 0.19232566498760245, "eus_Latn": 0.3155052398487781, "fas_Arab": 0.25391343265204913, "fil_Latn": 0.4646692271862731, "fin_Latn": 0.4759450597456664, "fra_Latn": 0.663792113652442, "glg_Latn": 0.5322872358954756, "guj_Gujr": 0.20596184394454778, "heb_Hebr": 0.10716405578859328, "hin_Deva": 0.1838808075368145, "hrv_Latn": 0.3139358872501065, "hun_Latn": 0.5081555792186178, "hye_Armn": 0.12716098990970462, "ind_Latn": 0.5621676785379013, "isl_Latn": 0.24641095943858662, "ita_Latn": 0.658190727051437, "jpn_Jpan": 0.2598441397658701, "kan_Knda": 0.17806570191716214, "kat_Geor": 0.0701215725725029, "kaz_Cyrl": 0.10190875695164618, "khm_Khmr": 0.1593273479867589, "kor_Hang": 0.24812461710892444, "lit_Latn": 0.44872328247117094, "lvs_Latn": 0.45462607107025493, "mal_Mlym": 0.24630664840221128, "mar_Deva": -0.07545268867603293, "mkd_Cyrl": 0.30128833130178045, "mya_Mymr": 0.09942915864528967, "nld_Latn": 0.6984457525965199, "nob_Latn": 0.6136533102913947, "npi_Deva": 0.1824949802899655, "pan_Guru": 0.2549241058903939, "pol_Latn": 0.5444900316379813, "por_Latn": 0.6894638747639885, "ron_Latn": 0.5337841174706431, "rus_Cyrl": 0.28276913928432285, "sin_Sinh": 0.36221079195463884, "slk_Latn": 0.5251382460522451, "slv_Latn": 0.4324206374112496, "spa_Latn": 0.6301397510276678, "srp_Cyrl": 0.2410437691136725, "swe_Latn": 0.626292385430151, "swh_Latn": 0.3046579614341224, "tam_Taml": 0.1746132945264641, "tel_Telu": 0.2719895557887898, "tha_Thai": 0.18303644114058565, "tur_Latn": 0.5260531985897241, "ukr_Cyrl": 0.2415192086179947, "urd_Arab": 0.09887985837154838, "uzn_Latn": 0.43560234566036277, "vie_Latn": 0.3548488051997094, "yue_Hani": 0.1843154325260853, "zsm_Latn": 0.63176129857042 }, "lang_mean_spearman": 0.3391411135846501 } }, "lapa-llm/fineweb-nemotron-edu-score": { "en_llama3": { "n": 6000, "spearman": 0.40435173649634193, "pearson": 0.4554141865972126, "f1_ge3": 0.0, "acc_round": 0.12883333333333333, "mean_pred": 0.1276990892092387 }, "fw2_gemma": { "n": 9750, "spearman": 0.5349173487614419, "pearson": 0.562077935847803, "f1_ge3": 0.0, "acc_round": 0.4177435897435897, "mean_pred": 0.19270957252306817, "by_lang": { "afr_Latn": 0.48389042201036964, "amh_Ethi": 0.3822232362514379, "arb_Arab": 0.6781892347769921, "azj_Latn": 0.38443635733657094, "ben_Beng": 0.5281859315473573, "bul_Cyrl": 0.48416152951960584, "cat_Latn": 0.6253514204117694, "ces_Latn": 0.5902868972407341, "cmn_Hani": 0.6736600224465833, "dan_Latn": 0.6767123462816199, "deu_Latn": 0.46482435883639295, "ekk_Latn": 0.5720293642062684, "ell_Grek": 0.5321063476860347, "eus_Latn": 0.6167297891091834, "fas_Arab": 0.6654732838260431, "fil_Latn": 0.3046322173530426, "fin_Latn": 0.4976454311956763, "fra_Latn": 0.4741827081021615, "glg_Latn": 0.4788506407702441, "guj_Gujr": 0.5375404269294075, "heb_Hebr": 0.6232003990837884, "hin_Deva": 0.4683015882094025, "hrv_Latn": 0.6515306767013056, "hun_Latn": 0.5487119820727876, "hye_Armn": 0.5343386111543995, "ind_Latn": 0.6399088599480961, "isl_Latn": 0.46881074934543976, "ita_Latn": 0.49199121937179136, "jpn_Jpan": 0.5072588635254016, "kan_Knda": 0.5728007384491273, "kat_Geor": 0.3114576309330108, "kaz_Cyrl": 0.6849515903763737, "khm_Khmr": 0.5585335415841745, "kor_Hang": 0.518389228774535, "lit_Latn": 0.48353769727687057, "lvs_Latn": 0.46027063501806825, "mal_Mlym": 0.5056591355491, "mar_Deva": 0.6576983043650662, "mkd_Cyrl": 0.6161256356836985, "mya_Mymr": 0.439066691648072, "nld_Latn": 0.5930061490179646, "nob_Latn": 0.6455107316809844, "npi_Deva": 0.342032804852713, "pan_Guru": 0.7212425124428427, "pol_Latn": 0.644092344107793, "por_Latn": 0.4978996668679927, "ron_Latn": 0.5688079965194102, "rus_Cyrl": 0.5835212681138919, "sin_Sinh": 0.5163239082658436, "slk_Latn": 0.3903792269394212, "slv_Latn": 0.5715113878665266, "spa_Latn": 0.5381107050499219, "srp_Cyrl": 0.5831102400119055, "swe_Latn": 0.44876467976597684, "swh_Latn": 0.4479382379994304, "tam_Taml": 0.629789225785611, "tel_Telu": 0.678583433741731, "tha_Thai": 0.5951537073862054, "tur_Latn": 0.745334937300227, "ukr_Cyrl": 0.6728853453790729, "urd_Arab": 0.40202281132559226, "uzn_Latn": 0.6915804088792905, "vie_Latn": 0.5662923896778848, "yue_Hani": 0.4409938684986199, "zsm_Latn": 0.6690450331407745 }, "lang_mean_spearman": 0.5473475194696251 } }, "hotchpotch/fineweb-2-edu-japanese-classifier": { "en_llama3": { "n": 6000, "spearman": 0.5921578182237801, "pearson": 0.5077444923946944, "f1_ge3": 0.17989417989417988, "acc_round": 0.07183333333333333, "mean_pred": 2.7901276041666665 }, "fw2_gemma": { "n": 9750, "spearman": 0.5499382217361815, "pearson": 0.4203910799363762, "f1_ge3": 0.21786941580756014, "acc_round": 0.09753846153846153, "mean_pred": 2.7127336738782053, "by_lang": { "afr_Latn": 0.5116149862577334, "amh_Ethi": 0.5064297055669538, "arb_Arab": 0.5099635720859134, "azj_Latn": 0.47582135322997676, "ben_Beng": 0.629888278412506, "bul_Cyrl": 0.5763550433470112, "cat_Latn": 0.5371870739031886, "ces_Latn": 0.6359393476583343, "cmn_Hani": 0.7934241923026797, "dan_Latn": 0.5932684884828309, "deu_Latn": 0.6200653239781251, "ekk_Latn": 0.6441123351958554, "ell_Grek": 0.5666255428792976, "eus_Latn": 0.5705360935004703, "fas_Arab": 0.6509585545132225, "fil_Latn": 0.6806891768731289, "fin_Latn": 0.6201138974162479, "fra_Latn": 0.5822901397136012, "glg_Latn": 0.4674084841492625, "guj_Gujr": 0.47720265526183564, "heb_Hebr": 0.47699062883410864, "hin_Deva": 0.5098192382858678, "hrv_Latn": 0.5136587261418535, "hun_Latn": 0.6202557558487989, "hye_Armn": 0.423231753717233, "ind_Latn": 0.6207925246234596, "isl_Latn": 0.4463491772204554, "ita_Latn": 0.6264924596415915, "jpn_Jpan": 0.7896990661983702, "kan_Knda": 0.4984784498274562, "kat_Geor": 0.48444127752189386, "kaz_Cyrl": 0.3465341923924144, "khm_Khmr": 0.6382914448173299, "kor_Hang": 0.7989747457588643, "lit_Latn": 0.560250793614278, "lvs_Latn": 0.5238597331244348, "mal_Mlym": 0.6142332586223039, "mar_Deva": 0.5178096821445864, "mkd_Cyrl": 0.6245294420022526, "mya_Mymr": 0.6614666436063987, "nld_Latn": 0.6589492341211373, "nob_Latn": 0.5884598745905916, "npi_Deva": 0.5057900274710645, "pan_Guru": 0.48239238889222125, "pol_Latn": 0.6431501842808603, "por_Latn": 0.6774251610323179, "ron_Latn": 0.5720068345901783, "rus_Cyrl": 0.6598487846963305, "sin_Sinh": 0.5681730728940162, "slk_Latn": 0.5433020799375309, "slv_Latn": 0.5532141047294149, "spa_Latn": 0.6671276675142975, "srp_Cyrl": 0.3244343644279143, "swe_Latn": 0.6699832323601396, "swh_Latn": 0.4209064301683013, "tam_Taml": 0.5554827292258321, "tel_Telu": 0.5806660381234184, "tha_Thai": 0.7152391004088681, "tur_Latn": 0.7131602490856848, "ukr_Cyrl": 0.5066338460868683, "urd_Arab": 0.49444220274143674, "uzn_Latn": 0.42703751159186915, "vie_Latn": 0.577798064164233, "yue_Hani": 0.663907562897532, "zsm_Latn": 0.683626270718332 }, "lang_mean_spearman": 0.5753724654680388 } } }