|
Models,Alignbench,ArenaHard,Fofo_en,Fofo_cn,Wildbench,Average
|
|
qwen2.5-72b-instruct-turbomind,67.2,81.83,50,58,35.74333333,58.55466667
|
|
qwen2.5-32b-instruct-turbomind,65.4,71.63,45,55,19.06,51.218
|
|
qwen2.5-14b-instruct-turbomind,64.8,71.71,44,48,19.62666667,49.62733333
|
|
qwen2.5-7b-instruct-turbomind,60.8,60.93,40,46,18.57333333,45.26066667
|
|
llama-3_1-70b-instruct-turbomind,53.2,59.24,45,38,9.636666667,41.01533333
|
|
internlm2_5-20b-chat-turbomind,60.5,33.58,41,49,5.103333333,37.83666667
|
|
llama-3_1-8b-instruct-turbomind,47.2,38.76,36,31,-1.173333333,30.35733333
|
|
qwen2.5-3b-instruct-turbomind,55.2,38.12,30,30,-3.023333333,30.05933333
|
|
internlm2_5-7b-chat-turbomind,57.2,17.9,34,43,-12.95333333,27.82933333
|
|
qwen2.5-1.5b-instruct-turbomind,47,14.58,16,14,-46.41,9.034
|
|
|