MEXA / evals /bible-max-belebele.csv
kargaranamir's picture
upload mexa.
13f2d15
raw
history blame
11.8 kB
,gemma2-9B,gemma-7B,llama3.1-70B,llama3.1-8B,llama3-8B,llama2-7B,llama1-7B,mistral-7B,olmo-7B,avg
eng_Latn,0.9178,0.8467,0.9456,0.8767,0.8689,0.4822,0.4156,0.8389,0.7711,0.7737
fra_Latn,0.9089,0.7727,0.8905,0.7831,0.7761,0.4635,0.3995,0.7575,0.3219,0.6748
rus_Cyrl,0.8732,0.8138,0.9181,0.8001,0.7930,0.4494,0.3954,0.7086,0.1722,0.6582
nld_Latn,0.9000,0.7481,0.9456,0.8512,0.8183,0.4354,0.3874,0.7575,0.0599,0.6559
ita_Latn,0.8643,0.7645,0.9089,0.7575,0.7339,0.4494,0.3874,0.6923,0.1273,0.6317
por_Latn,0.8911,0.7316,0.8722,0.7150,0.7086,0.4213,0.3591,0.6679,0.1647,0.6146
ukr_Cyrl,0.8643,0.6659,0.9181,0.7660,0.7677,0.4307,0.3591,0.6923,0.0150,0.6088
dan_Latn,0.9000,0.7316,0.9181,0.6980,0.6917,0.4401,0.3793,0.6190,0.0524,0.6033
nob_Latn,0.8822,0.7809,0.8997,0.7150,0.6833,0.4354,0.3591,0.5864,0.0524,0.5994
swe_Latn,0.8554,0.6412,0.9089,0.6980,0.6917,0.4447,0.3995,0.6027,0.0674,0.5899
bul_Cyrl,0.8643,0.6659,0.8997,0.7065,0.7086,0.3698,0.3551,0.6923,0.0374,0.5888
spa_Latn,0.8732,0.7234,0.8630,0.7150,0.6580,0.3979,0.3510,0.5701,0.1123,0.5849
pol_Latn,0.8732,0.6905,0.8997,0.6980,0.6411,0.4167,0.3591,0.6353,0.0449,0.5843
ind_Latn,0.8822,0.7234,0.8813,0.8001,0.8098,0.4167,0.1775,0.5050,0.0599,0.5840
cmn_Hani,0.8822,0.7398,0.9456,0.7831,0.7845,0.0889,0.2381,0.6190,0.1198,0.5779
ces_Latn,0.7841,0.7070,0.9089,0.7235,0.6917,0.3886,0.3510,0.5701,0.0225,0.5719
ron_Latn,0.8643,0.6494,0.8997,0.7490,0.7171,0.3418,0.3309,0.5050,0.0449,0.5669
cat_Latn,0.7931,0.7316,0.8630,0.6043,0.6327,0.4167,0.3712,0.5864,0.0449,0.5604
srp_Cyrl,0.8020,0.6741,0.8722,0.6554,0.5990,0.4167,0.3793,0.6271,0.0075,0.5592
afr_Latn,0.8822,0.6494,0.9089,0.6980,0.6917,0.3698,0.3147,0.4724,0.0449,0.5591
mkd_Cyrl,0.8465,0.6494,0.9181,0.7575,0.7086,0.2762,0.2421,0.5131,0.0225,0.5482
deu_Latn,0.7841,0.5672,0.8630,0.7065,0.6664,0.3511,0.3309,0.4724,0.0599,0.5335
hun_Latn,0.7931,0.5836,0.9272,0.7405,0.7002,0.3043,0.2421,0.4724,0.0150,0.5309
zho_Hani,0.8198,0.6741,0.8722,0.6554,0.7086,0.0796,0.2098,0.5131,0.1797,0.5236
ell_Grek,0.8554,0.5836,0.8813,0.6894,0.7255,0.1685,0.1049,0.4480,0.0075,0.4960
arz_Arab,0.7931,0.4028,0.8997,0.7065,0.6664,0.2575,0.1412,0.5538,0.0000,0.4912
slv_Latn,0.7841,0.5179,0.8630,0.5022,0.5146,0.3652,0.3309,0.4968,0.0150,0.4877
kor_Hang,0.8109,0.5754,0.8813,0.6469,0.6749,0.2668,0.0403,0.4317,0.0374,0.4851
slk_Latn,0.7931,0.6576,0.8630,0.5533,0.5146,0.3137,0.2663,0.3502,0.0225,0.4816
hrv_Latn,0.7218,0.6165,0.7895,0.4852,0.4977,0.3886,0.3430,0.4561,0.0225,0.4801
arb_Arab,0.8287,0.4603,0.7987,0.6043,0.5652,0.2668,0.1856,0.5783,0.0150,0.4781
fin_Latn,0.7931,0.5508,0.8722,0.5362,0.5652,0.3605,0.1493,0.3421,0.0299,0.4666
hin_Deva,0.8643,0.6083,0.8354,0.6043,0.6496,0.1264,0.0646,0.3176,0.0075,0.4531
vie_Latn,0.7841,0.5343,0.8446,0.6299,0.6327,0.2388,0.0363,0.3014,0.0449,0.4497
bel_Cyrl,0.8376,0.5179,0.8813,0.6554,0.6327,0.1639,0.1009,0.2362,0.0075,0.4481
tgl_Latn,0.7931,0.5014,0.8538,0.6554,0.6327,0.1919,0.0646,0.2851,0.0299,0.4453
prs_Arab,0.7841,0.6576,0.7803,0.6469,0.6411,0.1404,0.0403,0.2851,0.0299,0.4451
pes_Arab,0.7841,0.6576,0.7803,0.6469,0.6411,0.1404,0.0403,0.2851,0.0299,0.4451
tur_Latn,0.7485,0.5836,0.8538,0.5618,0.5399,0.2013,0.0484,0.3176,0.0075,0.4292
nno_Latn,0.7129,0.4932,0.7987,0.4596,0.4893,0.2715,0.2179,0.3421,0.0449,0.4256
heb_Hebr,0.6950,0.5343,0.6885,0.5022,0.5230,0.1732,0.1009,0.3502,0.0075,0.3972
epo_Latn,0.6683,0.4521,0.8354,0.5447,0.5062,0.1030,0.0726,0.2281,0.0225,0.3814
est_Latn,0.7307,0.5261,0.8354,0.4426,0.4471,0.0936,0.0161,0.1792,0.0150,0.3651
fao_Latn,0.7485,0.3617,0.8171,0.4341,0.4893,0.1498,0.0565,0.1955,0.0225,0.3639
isl_Latn,0.7129,0.3042,0.7069,0.4596,0.5062,0.1639,0.0605,0.3014,0.0150,0.3589
swh_Latn,0.8020,0.5836,0.8171,0.4086,0.4640,0.0281,0.0161,0.0489,0.0150,0.3537
tha_Thai,0.7485,0.2877,0.7987,0.4852,0.4977,0.0375,0.0081,0.2525,0.0075,0.3470
lit_Latn,0.8020,0.5425,0.7895,0.3830,0.3796,0.0421,0.0161,0.1222,0.0075,0.3427
urd_Arab,0.6416,0.3946,0.8630,0.4511,0.4471,0.0468,0.0040,0.1955,0.0075,0.3390
ben_Beng,0.7574,0.3206,0.7895,0.4681,0.4724,0.0094,0.0040,0.1466,0.0075,0.3306
hye_Armn,0.7752,0.4110,0.7436,0.4426,0.4808,0.0094,0.0000,0.0407,0.0000,0.3226
ceb_Latn,0.7485,0.2713,0.7803,0.4000,0.4218,0.0421,0.0202,0.1140,0.0225,0.3134
npi_Deva,0.7663,0.3699,0.6977,0.4000,0.4134,0.0047,0.0040,0.1547,0.0000,0.3123
mar_Deva,0.6772,0.3042,0.7620,0.3575,0.3459,0.0094,0.0040,0.0896,0.0000,0.2833
kat_Geor,0.6237,0.3124,0.6702,0.4171,0.4555,0.0187,0.0081,0.0244,0.0075,0.2820
cym_Latn,0.5970,0.1726,0.8171,0.3660,0.3965,0.0234,0.0121,0.0733,0.0150,0.2748
zsm_Latn,0.4723,0.1644,0.5876,0.4171,0.3796,0.0843,0.0202,0.1466,0.0150,0.2541
tam_Taml,0.7129,0.3453,0.6059,0.2724,0.2953,0.0047,0.0000,0.0489,0.0000,0.2539
guj_Gujr,0.6059,0.3124,0.6794,0.3149,0.3543,0.0047,0.0000,0.0081,0.0000,0.2533
urd_Latn,0.6148,0.2137,0.5692,0.3234,0.2362,0.0515,0.0121,0.2036,0.0075,0.2480
mlt_Latn,0.5792,0.2548,0.6977,0.2639,0.2531,0.0328,0.0202,0.0489,0.0075,0.2398
mal_Mlym,0.7396,0.2795,0.5784,0.2639,0.2784,0.0047,0.0000,0.0000,0.0075,0.2391
gle_Latn,0.4812,0.1151,0.6518,0.3490,0.3037,0.0796,0.0363,0.0570,0.0150,0.2321
kaz_Cyrl,0.4188,0.3370,0.6885,0.2894,0.2868,0.0047,0.0000,0.0489,0.0000,0.2305
tel_Telu,0.6594,0.2795,0.5325,0.2809,0.2953,0.0000,0.0000,0.0081,0.0000,0.2284
hin_Latn,0.4277,0.2466,0.5417,0.3149,0.2615,0.0609,0.0081,0.1222,0.0075,0.2212
gla_Latn,0.4634,0.0740,0.7712,0.2639,0.2784,0.0281,0.0161,0.0733,0.0150,0.2204
asm_Beng,0.5436,0.2302,0.6610,0.2468,0.2362,0.0047,0.0000,0.0244,0.0075,0.2172
war_Latn,0.4366,0.1891,0.6794,0.2639,0.2699,0.0281,0.0081,0.0570,0.0150,0.2163
tgk_Cyrl,0.4544,0.1644,0.6977,0.3149,0.2868,0.0047,0.0000,0.0163,0.0075,0.2163
pap_Latn,0.5257,0.2137,0.6426,0.1787,0.1687,0.0515,0.0363,0.0896,0.0225,0.2144
tpi_Latn,0.6327,0.1808,0.5967,0.1702,0.1940,0.0234,0.0081,0.0652,0.0075,0.2087
pan_Guru,0.6772,0.2137,0.5876,0.2213,0.1518,0.0047,0.0000,0.0000,0.0000,0.2063
mri_Latn,0.3386,0.0904,0.7253,0.2894,0.2699,0.0281,0.0121,0.0896,0.0075,0.2057
bak_Cyrl,0.3386,0.2055,0.6335,0.2979,0.3121,0.0000,0.0000,0.0244,0.0075,0.2022
kir_Cyrl,0.3475,0.2384,0.6702,0.2553,0.2278,0.0047,0.0000,0.0163,0.0000,0.1956
kan_Knda,0.5168,0.2220,0.5233,0.2128,0.2446,0.0047,0.0000,0.0326,0.0000,0.1952
san_Deva,0.4366,0.1397,0.4958,0.2213,0.2193,0.0140,0.0040,0.1547,0.0075,0.1881
mai_Deva,0.3653,0.1891,0.5967,0.2213,0.2278,0.0140,0.0040,0.0489,0.0000,0.1852
hat_Latn,0.4099,0.1315,0.5967,0.1873,0.1603,0.0187,0.0081,0.1059,0.0075,0.1807
aeb_Arab,0.4010,0.0986,0.4866,0.2043,0.2193,0.0468,0.0363,0.1059,0.0000,0.1776
snd_Arab,0.2941,0.1480,0.6610,0.2468,0.2193,0.0047,0.0040,0.0163,0.0000,0.1771
hau_Latn,0.5079,0.2384,0.4866,0.1447,0.1434,0.0140,0.0040,0.0244,0.0075,0.1746
ibo_Latn,0.3742,0.1151,0.5876,0.2043,0.1772,0.0094,0.0040,0.0081,0.0075,0.1653
awa_Deva,0.2584,0.1233,0.5233,0.2383,0.2109,0.0094,0.0000,0.0489,0.0000,0.1569
tat_Cyrl,0.1693,0.1315,0.5692,0.2553,0.2615,0.0047,0.0040,0.0163,0.0000,0.1569
sin_Sinh,0.4544,0.1233,0.4590,0.1787,0.1772,0.0000,0.0000,0.0081,0.0075,0.1565
tuk_Latn,0.2762,0.1480,0.5233,0.1958,0.1772,0.0234,0.0081,0.0326,0.0075,0.1547
hne_Deva,0.2317,0.0822,0.6426,0.1873,0.1434,0.0094,0.0081,0.0407,0.0075,0.1503
kmr_Latn,0.2317,0.0575,0.6059,0.2128,0.2025,0.0094,0.0081,0.0244,0.0000,0.1503
ary_Arab,0.2941,0.0822,0.4498,0.1532,0.1772,0.0328,0.0202,0.0489,0.0000,0.1398
sna_Latn,0.4455,0.1562,0.3489,0.1192,0.1265,0.0140,0.0040,0.0244,0.0075,0.1385
ilo_Latn,0.3208,0.0986,0.4131,0.1617,0.1687,0.0234,0.0121,0.0326,0.0150,0.1385
zul_Latn,0.4812,0.1233,0.3948,0.0851,0.0844,0.0140,0.0081,0.0244,0.0150,0.1367
jav_Latn,0.2851,0.0904,0.4590,0.1447,0.1097,0.0187,0.0081,0.0244,0.0150,0.1284
plt_Latn,0.3742,0.0658,0.4958,0.0766,0.0844,0.0140,0.0121,0.0244,0.0075,0.1283
uig_Arab,0.1337,0.0493,0.5600,0.1787,0.1434,0.0000,0.0040,0.0163,0.0075,0.1214
min_Latn,0.1871,0.1151,0.4131,0.1447,0.1434,0.0234,0.0161,0.0244,0.0150,0.1203
amh_Ethi,0.5792,0.1315,0.3121,0.0255,0.0253,0.0000,0.0000,0.0081,0.0000,0.1202
sun_Latn,0.2495,0.0986,0.3580,0.1277,0.1350,0.0281,0.0202,0.0326,0.0225,0.1191
sot_Latn,0.2851,0.0904,0.4590,0.0766,0.0675,0.0140,0.0121,0.0244,0.0150,0.1160
smo_Latn,0.2406,0.0411,0.5325,0.0766,0.0675,0.0140,0.0081,0.0244,0.0150,0.1133
khm_Khmr,0.3742,0.1069,0.3948,0.0766,0.0422,0.0000,0.0000,0.0163,0.0000,0.1123
nya_Latn,0.3742,0.0822,0.3580,0.0511,0.0506,0.0187,0.0121,0.0244,0.0225,0.1104
xho_Latn,0.3475,0.1233,0.3121,0.0851,0.0506,0.0140,0.0081,0.0326,0.0150,0.1098
lus_Latn,0.4634,0.0329,0.3580,0.0511,0.0422,0.0047,0.0040,0.0163,0.0150,0.1097
tsn_Latn,0.2049,0.0904,0.4131,0.0851,0.0759,0.0187,0.0081,0.0244,0.0075,0.1031
nso_Latn,0.1871,0.0658,0.4682,0.0851,0.0591,0.0140,0.0121,0.0244,0.0075,0.1026
ory_Orya,0.2673,0.0247,0.4682,0.0681,0.0759,0.0000,0.0000,0.0000,0.0075,0.1013
ckb_Arab,0.1247,0.0575,0.4131,0.1192,0.1434,0.0047,0.0000,0.0244,0.0075,0.0994
yor_Latn,0.2406,0.0411,0.3948,0.0766,0.0675,0.0094,0.0121,0.0244,0.0075,0.0971
mya_Mymr,0.2584,0.0658,0.3672,0.0596,0.0591,0.0000,0.0040,0.0081,0.0000,0.0914
ssw_Latn,0.2762,0.0904,0.2662,0.0596,0.0591,0.0140,0.0121,0.0244,0.0075,0.0900
kin_Latn,0.2317,0.0658,0.2479,0.1021,0.1012,0.0140,0.0081,0.0244,0.0075,0.0892
tum_Latn,0.2049,0.0329,0.3397,0.0511,0.0591,0.0187,0.0121,0.0326,0.0150,0.0851
eus_Latn,0.1069,0.0740,0.3030,0.0681,0.0844,0.0375,0.0202,0.0407,0.0075,0.0825
run_Latn,0.2228,0.0575,0.2479,0.0511,0.0759,0.0140,0.0081,0.0326,0.0150,0.0805
som_Latn,0.2049,0.0986,0.2020,0.0851,0.0759,0.0094,0.0081,0.0163,0.0075,0.0786
lug_Latn,0.1426,0.0247,0.3213,0.0596,0.0675,0.0047,0.0121,0.0081,0.0075,0.0720
fij_Latn,0.1604,0.0164,0.3489,0.0426,0.0337,0.0047,0.0040,0.0081,0.0075,0.0696
bem_Latn,0.1604,0.0658,0.2479,0.0426,0.0337,0.0094,0.0081,0.0244,0.0150,0.0675
tso_Latn,0.1158,0.0329,0.3121,0.0426,0.0422,0.0094,0.0081,0.0244,0.0150,0.0669
pag_Latn,0.1337,0.0575,0.1836,0.0426,0.0422,0.0234,0.0202,0.0326,0.0225,0.0620
ban_Latn,0.1247,0.0493,0.2112,0.0511,0.0506,0.0094,0.0040,0.0244,0.0075,0.0591
twi_Latn,0.0891,0.0411,0.2479,0.0426,0.0337,0.0140,0.0121,0.0163,0.0075,0.0560
lin_Latn,0.0713,0.0164,0.1285,0.0596,0.0591,0.0187,0.0121,0.0244,0.0075,0.0442
ace_Latn,0.0356,0.0411,0.1744,0.0511,0.0422,0.0094,0.0081,0.0244,0.0075,0.0438
kik_Latn,0.0713,0.0164,0.1377,0.0340,0.0337,0.0140,0.0081,0.0326,0.0075,0.0395
quy_Latn,0.0624,0.0247,0.1193,0.0426,0.0337,0.0094,0.0081,0.0163,0.0075,0.0360
ayr_Latn,0.0446,0.0164,0.0918,0.0426,0.0253,0.0140,0.0161,0.0244,0.0150,0.0323
wol_Latn,0.0267,0.0164,0.0918,0.0426,0.0422,0.0140,0.0081,0.0081,0.0075,0.0286
bug_Latn,0.0267,0.0082,0.0826,0.0426,0.0422,0.0094,0.0081,0.0163,0.0075,0.0271
sag_Latn,0.0178,0.0247,0.0551,0.0340,0.0253,0.0140,0.0121,0.0244,0.0225,0.0256
ewe_Latn,0.0267,0.0164,0.0734,0.0255,0.0253,0.0140,0.0040,0.0163,0.0150,0.0241
dyu_Latn,0.0356,0.0082,0.0918,0.0170,0.0169,0.0140,0.0081,0.0163,0.0075,0.0239
bam_Latn,0.0356,0.0164,0.0459,0.0340,0.0337,0.0187,0.0081,0.0081,0.0075,0.0231
luo_Latn,0.0267,0.0247,0.0459,0.0255,0.0337,0.0140,0.0121,0.0163,0.0075,0.0229
tir_Ethi,0.1158,0.0247,0.0367,0.0085,0.0084,0.0000,0.0000,0.0081,0.0000,0.0225
kab_Latn,0.0267,0.0082,0.0734,0.0340,0.0169,0.0094,0.0081,0.0163,0.0075,0.0223
fuv_Latn,0.0267,0.0164,0.0551,0.0426,0.0337,0.0047,0.0081,0.0081,0.0000,0.0217
kac_Latn,0.0178,0.0000,0.0643,0.0255,0.0253,0.0094,0.0040,0.0081,0.0075,0.0180
shn_Mymr,0.0089,0.0000,0.0918,0.0255,0.0253,0.0047,0.0000,0.0000,0.0000,0.0174
mos_Latn,0.0178,0.0082,0.0275,0.0426,0.0253,0.0047,0.0040,0.0163,0.0075,0.0171
taq_Latn,0.0089,0.0164,0.0459,0.0255,0.0169,0.0047,0.0000,0.0163,0.0000,0.0150
dik_Latn,0.0089,0.0164,0.0275,0.0255,0.0084,0.0094,0.0081,0.0163,0.0075,0.0142
fon_Latn,0.0178,0.0000,0.0275,0.0170,0.0169,0.0047,0.0081,0.0163,0.0075,0.0129
kbp_Latn,0.0267,0.0082,0.0275,0.0170,0.0169,0.0047,0.0040,0.0081,0.0000,0.0126
nus_Latn,0.0089,0.0000,0.0184,0.0170,0.0084,0.0094,0.0040,0.0081,0.0075,0.0091