Tydiqa
평가 지표
key
model
num
org
rank
time
tydiqagoldp
tydiqagoldparabic
tydiqagoldpbengali
tydiqagoldpenglish
tydiqagoldpfinnish
tydiqagoldpindonesian
tydiqagoldpjapanese
tydiqagoldpkorean
tydiqagoldprussian
tydiqagoldpswahili
tydiqagoldptelugu
tydiqagoldpthai
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | key | model | num | org | rank | time | tydiqagoldp | tydiqagoldparabic | tydiqagoldpbengali | tydiqagoldpenglish | tydiqagoldpfinnish | tydiqagoldpindonesian | tydiqagoldpjapanese | tydiqagoldpkorean | tydiqagoldprussian | tydiqagoldpswahili | tydiqagoldptelugu | tydiqagoldpthai | Paper Title | Repository |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Chat | 1.000000 | WeMix-LLaMA2-70B | 70B | Shanghai AI Lab | 1.000000 | 2023/10/16 | 52.100000 | 78.200000 | 66.000000 | 35.300000 | 42.800000 | 31.000000 | 70.300000 | 84.300000 | 33.400000 | 44.500000 | 27.600000 | 60.100000 | - | - |
0 of 1 row(s) selected.