update leaderboard

data/bosc_zh_mc.csv

@@ -1,21 +1,21 @@
 name,few_native,few_self_con,few_cot,few_cot_self_con,zero_native,zero_self_con,zero_cot,zero_cot_self_con
-GPT4,52.50,52.50,62.50,62.50,57.50,57.50,57.50,57.50
-Yi-34B-Chat,50.00,50.00,52.50,55.00,55.00,55.00,60.00,67.50
-DevOps-Model-14B-Chat,50.00,50.00,55.00,62.50,35.00,27.50,37.50,52.50
-LLaMA-2-7B,45.00,45.00,45.00,45.00,32.50,32.50,45.00,45.00
-Qwen-72B-Chat,45.00,45.00,60.00,60.00,50.00,50.00,47.50,47.50
-GPT-3.5-turbo,40.00,40.00,50.00,55.00,50.00,47.50,55.00,55.00
-ERNIE-Bot-4.0,52.50,52.50,57.50,57.50,57.50,57.50,60.00,60.00
-Mistral-7B,20.00,20.00,50.00,50.00,0.00,0.00,37.50,37.50
-LLaMA-2-13B,50.00,50.00,42.50,42.50,42.50,42.50,50.00,50.00
-Baichuan2-13B-Chat,37.50,37.50,42.50,45.00,37.50,40.00,47.50,52.50
-Qwen-14B-Chat,50.00,47.50,55.00,57.50,47.50,45.00,50.00,47.50
-LLaMA-2-70B-Chat,25.00,25.00,45.00,45.00,0.00,0.00,57.50,57.50
+GPT4,52.5,52.5,62.5,62.5,57.5,57.5,57.5,57.5
+Yi-34B-Chat,50,50,52.5,55,55,55,60,67.5
+DevOps-Model-14B-Chat,50,50,55,62.5,35,27.5,37.5,52.5
+LLaMA-2-7B,45,45,45,45,32.5,32.5,45,45
+Qwen-72B-Chat,45,45,60,60,50,50,47.5,47.5
+GPT-3.5-turbo,40,40,50,55,50,47.5,55,55
+ERNIE-Bot-4.0,52.5,52.5,57.5,57.5,57.5,57.5,60,60
+Mistral-7B,20,20,50,50,0,0,37.5,37.5
+LLaMA-2-13B,50,50,42.5,42.5,42.5,42.5,50,50
+Baichuan2-13B-Chat,37.5,37.5,42.5,45,37.5,40,47.5,52.5
+Qwen-14B-Chat,50,47.5,55,57.5,47.5,45,50,47.5
+LLaMA-2-70B-Chat,25,25,45,45,0,0,57.5,57.5
 ChatGLM3-6B,47.5,47.5,45,45,35,35,50,50
 InternLM2-Chat-20B,47.5,47.5,,,47.5,47.5,,
 InternLM2-Chat-7B,55,55,62.5,62.5,60,60,57.5,57.5
-gemma_2b,32.5,32.5,40,40 ,37.5,37.5,40,40 
-gemma_7b,40,40,50,50 ,32.5,32.5,62.5,62.5 
-qwen1.5-14b-base,47.5,47.5,45,45 ,47.5,47.5,50,50 
+gemma_2b,32.5,32.5,40,40,37.5,37.5,40,40
+gemma_7b,40,40,50,50,32.5,32.5,62.5,62.5
+qwen1.5-14b-base,47.5,47.5,45,45,47.5,47.5,50,50
 qwen1.5-14b-chat,52.5,55,60,60,45,47.5,60,72.5
-
+Claude-3-Opus,,,,,67.5,67.5,,

data/gtja_zh_mc.csv

@@ -18,3 +18,4 @@ gemma_2b,32.96703,32.96703,29.67033,29.67033,30.76923,30.76923,43.95604,43.95604
 gemma_7b,34.06593,34.06593,50.54945,50.54945,29.67033,29.67033,56.04396,56.04396
 qwen1.5-14b-base,68.13187,68.13187,42.85714,42.85714,53.84615,53.84615,63.73626,63.73626
 qwen1.5-14b-chat,59.34066,57.14286,60.43956,62.63736,56.04396,54.94505,67.03297,68.13187
+Claude-3-Opus,,,,,65.83,65.83,,

data/huaweicloud_zh_mc.csv

@@ -1,21 +1,21 @@
 name,few_native,few_self_con,few_cot,few_cot_self_con,zero_native,zero_self_con,zero_cot,zero_cot_self_con
-GPT4,43.33,43.33,46.67,46.67,20.00,20.00,20.00,20.00
-Yi-34B-Chat,50.00,46.67,30.00,43.33,36.67,40.00,36.67,30.00
-DevOps-Model-14B-Chat,40.00,40.00,20.00,23.33,16.67,16.67,33.33,13.33
-LLaMA-2-7B,16.67,16.67,33.33,33.33,10.00,10.00,26.67,26.67
+GPT4,43.33,43.33,46.67,46.67,20,20,20,20
+Yi-34B-Chat,50,46.67,30,43.33,36.67,40,36.67,30
+DevOps-Model-14B-Chat,40,40,20,23.33,16.67,16.67,33.33,13.33
+LLaMA-2-7B,16.67,16.67,33.33,33.33,10,10,26.67,26.67
 Qwen-72B-Chat,43.33,43.33,33.33,36.67,36.67,36.67,33.33,33.33
-GPT-3.5-turbo,20.00,20.00,16.67,23.33,13.33,13.33,20.00,26.67
-ERNIE-Bot-4.0,36.67,36.67,23.33,23.33,16.67,16.67,20.00,20.00
-Mistral-7B,0.00,0.00,16.67,16.67,0.00,0.00,23.33,23.33
-LLaMA-2-13B,26.67,26.67,13.33,13.33,10.00,10.00,20.00,20.00
-Baichuan2-13B-Chat,16.67,20.00,26.67,30.00,6.67,10.00,23.33,23.33
-Qwen-14B-Chat,40.00,30.00,26.67,33.33,13.33,13.33,20.00,26.67
-LLaMA-2-70B-Chat,23.33,23.33,16.67,16.67,3.33,3.33,20.00,20.00
+GPT-3.5-turbo,20,20,16.67,23.33,13.33,13.33,20,26.67
+ERNIE-Bot-4.0,36.67,36.67,23.33,23.33,16.67,16.67,20,20
+Mistral-7B,0,0,16.67,16.67,0,0,23.33,23.33
+LLaMA-2-13B,26.67,26.67,13.33,13.33,10,10,20,20
+Baichuan2-13B-Chat,16.67,20,26.67,30,6.67,10,23.33,23.33
+Qwen-14B-Chat,40,30,26.67,33.33,13.33,13.33,20,26.67
+LLaMA-2-70B-Chat,23.33,23.33,16.67,16.67,3.33,3.33,20,20
 ChatGLM3-6B,6.666666667,6.666666667,13.33333333,13.33333333,13.33333333,13.33333333,16.66666667,16.66666667
 InternLM2-Chat-20B,16.66666667,16.66666667,,,13.33333333,13.33333333,20,20
 InternLM2-Chat-7B,30,30,40,40,43.33333333,43.33333333,23.33333333,23.33333333
-gemma_2b,26.66667,26.66667,20,20 ,26.66667,26.66667,10,10 
-gemma_7b,13.33333,13.33333,30,30 ,3.333333,3.333333,23.33333,23.33333 
-qwen1.5-14b-base,20,20,30,30 ,20,20,33.33333,33.33333 
+gemma_2b,26.66667,26.66667,20,20,26.66667,26.66667,10,10
+gemma_7b,13.33333,13.33333,30,30,3.333333,3.333333,23.33333,23.33333
+qwen1.5-14b-base,20,20,30,30,20,20,33.33333,33.33333
 qwen1.5-14b-chat,26.66667,26.66667,20,30,23.33333,26.66667,13.33333,13.33333
-
+Claude-3-Opus,,,,,60,60,,

data/lenovo_en_mc.csv

@@ -2,8 +2,8 @@ name,zero_native,zero_self_con,zero_cot,zero_cot_self_con,few_native,few_self_co
 ChatGLM3-6B,60,60,60,60,55,55,60,60
 InternLM2-Chat-20B,62.5,62.5,,,75,75,,
 InternLM2-Chat-7B,65,65,67.5,67.5,75,75,57.5,57.5
-gemma_2b,22.5,22.5,47.5,47.5 ,30,30,37.5,37.5 
-gemma_7b,32.5,32.5,65,65 ,35,35,65,65 
-qwen1.5-14b-base,67.5,67.5,70,70 ,72.5,72.5,50,50 
+gemma_2b,22.5,22.5,47.5,47.5,30,30,37.5,37.5
+gemma_7b,32.5,32.5,65,65,35,35,65,65
+qwen1.5-14b-base,67.5,67.5,70,70,72.5,72.5,50,50
 qwen1.5-14b-chat,67.5,67.5,70,70,72.5,65,77.5,77.5
-
+Claude-3-Opus,80,80,,,,,,

data/lenovo_zh_mc.csv

@@ -1,15 +1,15 @@
 name,few_native,few_self_con,few_cot,few_cot_self_con,zero_native,zero_self_con,zero_cot,zero_cot_self_con
-GPT4,77.50,77.50,82.50,82.50,77.50,77.50,82.50,82.50
-Yi-34B-Chat,62.50,57.50,52.50,52.50,75.00,75.00,87.50,82.50
-DevOps-Model-14B-Chat,67.50,70.00,62.50,70.00,60.00,67.50,65.00,57.50
-LLaMA-2-7B,60.00,60.00,55.00,55.00,32.50,32.50,45.00,45.00
-Qwen-72B-Chat,75.00,75.00,75.00,75.00,72.50,72.50,75.00,75.00
-GPT-3.5-turbo,57.50,57.50,62.50,62.50,60.00,62.50,65.00,70.00
-ERNIE-Bot-4.0,75.00,75.00,82.50,82.50,75.00,75.00,77.50,77.50
-Mistral-7B,35.00,35.00,60.00,60.00,47.50,47.50,62.50,62.50
-LLaMA-2-13B,60.00,60.00,55.00,55.00,45.00,45.00,62.50,62.50
-ChatGLM3-6B,55.00,55.00,60.00,60.00,60.00,60.00,60.00,60.00
-Baichuan2-13B-Chat,62.50,60.00,70.00,67.50,65.00,60.00,72.50,67.50
-Qwen-14B-Chat,70.00,65.00,65.00,67.50,70.00,67.50,70.00,67.50
-LLaMA-2-70B-Chat,20.00,20.00,57.50,57.50,22.50,22.50,75.00,75.00
-
+GPT4,77.5,77.5,82.5,82.5,77.5,77.5,82.5,82.5
+Yi-34B-Chat,62.5,57.5,52.5,52.5,75,75,87.5,82.5
+DevOps-Model-14B-Chat,67.5,70,62.5,70,60,67.5,65,57.5
+LLaMA-2-7B,60,60,55,55,32.5,32.5,45,45
+Qwen-72B-Chat,75,75,75,75,72.5,72.5,75,75
+GPT-3.5-turbo,57.5,57.5,62.5,62.5,60,62.5,65,70
+ERNIE-Bot-4.0,75,75,82.5,82.5,75,75,77.5,77.5
+Mistral-7B,35,35,60,60,47.5,47.5,62.5,62.5
+LLaMA-2-13B,60,60,55,55,45,45,62.5,62.5
+ChatGLM3-6B,55,55,60,60,60,60,60,60
+Baichuan2-13B-Chat,62.5,60,70,67.5,65,60,72.5,67.5
+Qwen-14B-Chat,70,65,65,67.5,70,67.5,70,67.5
+LLaMA-2-70B-Chat,20,20,57.5,57.5,22.5,22.5,75,75
+Claude-3-Opus,,,,,80,80,,

data/network_en_mc.csv

@@ -13,16 +13,16 @@ GPT-4,/,/,/,/,/,/,88.7,88.7
 AquilaChat2-34B,36.63,36.63,44.83,44.83,46.65,46.65,NULL,NULL
 Yi-34B-Chat,57.75,59.14,65.11,68.79,68.16,68.37,78.09,80.06
 DevOps-Model-14B-Chat,30.69,30.59,55.77,63.63,63.85,61.96,41.15,44.01
-Qwen-72B-Chat,70.41,70.50,72.38,72.56,70.32,70.32,70.13,70.22
-Mistral-7B,29.27,29.27,46.30,46.30,47.22,47.22,45.58,45.58
-Qwen-14B-Chat,43.78,47.81,56.58,59.40,62.09,59.70,49.06,55.88
+Qwen-72B-Chat,70.41,70.5,72.38,72.56,70.32,70.32,70.13,70.22
+Mistral-7B,29.27,29.27,46.3,46.3,47.22,47.22,45.58,45.58
+Qwen-14B-Chat,43.78,47.81,56.58,59.4,62.09,59.7,49.06,55.88
 LLaMA-2-70B-Chat,25.29,25.29,57.97,58.06,52.97,52.97,58.55,58.55
-ERNIE-Bot-4.0,61.15,61.15,70.00,70.00,60.00,60.00,70.00,70.00
+ERNIE-Bot-4.0,61.15,61.15,70,70,60,60,70,70
 ChatGLM3-6B,43.38487973,43.38487973,44.58762887,44.58762887,42.09621993,42.09621993,43.47079038,43.47079038
 InternLM2-Chat-20B,56.35738832,56.35738832,26.18025751,26.18025751,60.48109966,60.48109966,45.10309278,45.10309278
 InternLM2-Chat-7B,49.74226804,49.74226804,56.18556701,56.18556701,48.19587629,48.19587629,49.74226804,49.74226804
-gemma_2b,26.46048,26.46048,33.41924,33.41924 ,26.6323,26.6323,37.54296,37.54296 
-gemma_7b,25.08591,25.08591,50.85911,50.85911 ,30.24055,30.24055,51.55747,51.55747 
-qwen1.5-14b-base,34.87973,34.87973,60.82474,60.82474 ,65.54983,65.54983,47.07904,47.07904 
+gemma_2b,26.46048,26.46048,33.41924,33.41924,26.6323,26.6323,37.54296,37.54296
+gemma_7b,25.08591,25.08591,50.85911,50.85911,30.24055,30.24055,51.55747,51.55747
+qwen1.5-14b-base,34.87973,34.87973,60.82474,60.82474,65.54983,65.54983,47.07904,47.07904
 qwen1.5-14b-chat,54.89691,56.4433,64.08935,67.09622,52.23368,53.52234,59.53608,64.17526
-
+Claude-3-Opus,75.43,75.43,,,,,,

data/network_zh_mc.csv

@@ -8,24 +8,24 @@ ChatGLM2-6B,33.8,33.7,42.1,42.2,36,36,39.5,39.5
 Chinese-LLaMA-2-13B,22.5,22.5,38.8,38.8,41.8,41.8,32.2,32.2
 InternLM-7B,41.7,41.7,38.4,38.4,42.6,42.6,41.3,41.3
 LLaMA-2-7B,29.8,30.2,50.1,55.6,38.6,40.8,45.6,50.4
-Baichuan2-13B-Chat,35.6,35.9,30.5,30.5,34.6,35.6,30.2,32.0
+Baichuan2-13B-Chat,35.6,35.9,30.5,30.5,34.6,35.6,30.2,32
 GPT-4,/,/,/,/,/,/,86,86
 AquilaChat2-34B,34.66,34.66,47.74,47.74,44.48,44.48,NULL,NULL
 Yi-34B-Chat,61.61,62.56,68.11,69.75,65.73,65.37,69.88,71.21
 DevOps-Model-14B-Chat,47.59,46.57,52.52,56.01,62.07,60.08,50.59,55.79
-Qwen-72B-Chat,65.77,65.86,68.13,68.30,69.40,69.40,69.99,70.08
-Mistral-7B,1.90,1.90,45.61,45.61,15.00,15.00,35.97,35.97
-Qwen-14B-Chat,48.35,48.81,55.35,57.40,58.53,56.12,52.12,54.99
+Qwen-72B-Chat,65.77,65.86,68.13,68.3,69.4,69.4,69.99,70.08
+Mistral-7B,1.9,1.9,45.61,45.61,15,15,35.97,35.97
+Qwen-14B-Chat,48.35,48.81,55.35,57.4,58.53,56.12,52.12,54.99
 LLaMA-2-70B-Chat,38.55,38.55,57.49,57.49,49.09,49.09,48.57,48.57
-ERNIE-Bot-4.0,67.54,67.54,71.96,71.96,72.00,72.00,78.00,78.00
-Hunyuan-13B,60.00,60.00,70.00,70.00,,,,
+ERNIE-Bot-4.0,67.54,67.54,71.96,71.96,72,72,78,78
+Hunyuan-13B,60,60,70,70,,,,
 ChatGLM3-6B,41.39414802,41.39414802,49.22547332,49.22547332,38.81239243,38.81239243,42.85714286,42.85714286
 InternLM2-Chat-20B,57.48709122,57.48709122,57.14285714,57.14285714,59.1222031,59.1222031,50.77452668,50.77452668
 InternLM2-Chat-7B,54.30292599,54.30292599,59.81067126,59.81067126,58.51979346,58.51979346,51.63511188,51.63511188
 GLM3-turbo,59.63855422,59.63855422,,,,,,
 GLM4,67.383821,67.383821,,,,,,
-gemma_2b,29.69019,29.69019,39.15663,39.15663 ,29.77625,29.77625,38.64028,38.64028 
-gemma_7b,31.58348,31.58348,47.59036,47.59036 ,34.68158,34.68158,48.88124,48.88124 
-qwen1.5-14b-base,45.18072,45.18072,59.1222,59.1222 ,61.10155,61.10155,52.4957,52.4957 
+gemma_2b,29.69019,29.69019,39.15663,39.15663,29.77625,29.77625,38.64028,38.64028
+gemma_7b,31.58348,31.58348,47.59036,47.59036,34.68158,34.68158,48.88124,48.88124
+qwen1.5-14b-base,45.18072,45.18072,59.1222,59.1222,61.10155,61.10155,52.4957,52.4957
 qwen1.5-14b-chat,54.04475,53.87263,62.56454,63.85542,58.77797,58.0895,63.42513,65.57659
-
+Claude-3-Opus,69.07,69.07,,,,,,

data/oracle_en_mc.csv

@@ -1,28 +1,28 @@
 name,zero_native,zero_self_con,zero_cot,zero_cot_self_con,few_native,few_self_con,few_cot,few_cot_self_con
-Baichuan-13B-Chat,12.47,11.67,16.50,19.52,24.55,22.54,26.36,28.77
-Chinese-Alpaca-2-13B,23.14,23.14,28.97,28.97,16.30,16.30,14.29,14.29
+Baichuan-13B-Chat,12.47,11.67,16.5,19.52,24.55,22.54,26.36,28.77
+Chinese-Alpaca-2-13B,23.14,23.14,28.97,28.97,16.3,16.3,14.29,14.29
 GPT-3.5-turbo,38.63,38.83,40.04,42.05,36.62,37.63,42.66,43.86
-LLaMA-2-13B,16.10,20.32,23.94,29.58,20.12,22.33,24.35,33.80
-Qwen-7B-Chat,18.91,19.11,22.13,23.94,26.76,25.55,34.81,33.40
+LLaMA-2-13B,16.1,20.32,23.94,29.58,20.12,22.33,24.35,33.8
+Qwen-7B-Chat,18.91,19.11,22.13,23.94,26.76,25.55,34.81,33.4
 ChatGLM2-6B,20.72,20.52,19.92,19.72,20.12,20.12,22.94,22.74
-Chinese-LLaMA-2-13B,13.88,13.88,20.52,20.52,16.90,16.90,23.34,23.34
+Chinese-LLaMA-2-13B,13.88,13.88,20.52,20.52,16.9,16.9,23.34,23.34
 InternLM-7B,26.36,26.36,25.55,25.55,25.55,25.55,27.97,27.97
-LLaMA-2-7B,22.13,23.74,23.74,26.56,19.32,20.52,28.77,33.60
+LLaMA-2-7B,22.13,23.74,23.74,26.56,19.32,20.52,28.77,33.6
 Baichuan2-13B-Chat,17.1,19.1,18.7,22.9,25.9,26.5,20.9,24.5
 GPT-4,/,/,59.02,64.56,/,/,58.35,62.58
 AquilaChat2-34B,36.63,36.63,44.83,44.83,46.65,46.65,NULL,NULL
 Yi-34B-Chat,47.08,48.69,47.08,46.28,58.15,58.35,56.94,58.95
-DevOps-Model-14B-Chat,25.15,26.96,35.41,38.83,33.20,34.81,27.36,27.36
-Qwen-72B-Chat,47.28,47.48,48.09,48.09,49.70,49.70,43.46,43.66
-ERNIE-Bot-4.0,43.80,43.80,47.14,47.14,46.00,46.00,54.00,54.00
-Mistral-7B,17.10,17.10,26.76,26.76,31.19,31.19,27.97,27.97
-Qwen-14B-Chat,24.95,28.37,33.00,36.62,27.97,28.37,27.97,24.14
-LLaMA-2-70B-Chat,19.72,19.72,27.97,27.97,26.56,26.56,32.60,32.60
+DevOps-Model-14B-Chat,25.15,26.96,35.41,38.83,33.2,34.81,27.36,27.36
+Qwen-72B-Chat,47.28,47.48,48.09,48.09,49.7,49.7,43.46,43.66
+ERNIE-Bot-4.0,43.8,43.8,47.14,47.14,46,46,54,54
+Mistral-7B,17.1,17.1,26.76,26.76,31.19,31.19,27.97,27.97
+Qwen-14B-Chat,24.95,28.37,33,36.62,27.97,28.37,27.97,24.14
+LLaMA-2-70B-Chat,19.72,19.72,27.97,27.97,26.56,26.56,32.6,32.6
 ChatGLM3-6B,20.92555332,20.92555332,25.15090543,25.15090543,24.74849095,24.74849095,29.1750503,29.1750503
 InternLM2-Chat-20B,,,59.21052632,59.21052632,,,,
 InternLM2-Chat-7B,27.16297787,27.16297787,28.16901408,28.16901408,29.97987928,29.97987928,30.18108652,30.18108652
-gemma_2b,16.90141,16.90141,19.5171,19.5171 ,16.09658,16.09658,24.74849,24.74849 
-gemma_7b,14.28571,14.28571,30.98592,30.98592 ,2.60223,2.60223,43.85965,43.85965 
-qwen1.5-14b-base,29.17505,29.17505,33.60161,33.60161 ,36.82093,36.82093,27.7666,27.7666 
+gemma_2b,16.90141,16.90141,19.5171,19.5171,16.09658,16.09658,24.74849,24.74849
+gemma_7b,14.28571,14.28571,30.98592,30.98592,2.60223,2.60223,43.85965,43.85965
+qwen1.5-14b-base,29.17505,29.17505,33.60161,33.60161,36.82093,36.82093,27.7666,27.7666
 qwen1.5-14b-chat,32.79678,35.41247,39.43662,43.05835,32.39437,33.60161,36.82093,38.833
-
+Claude-3-Opus,46.47,46.47,,,,,,

data/oracle_zh_mc.csv

@@ -3,7 +3,7 @@ Baichuan-13B-Chat,12.88,12.07,25.96,27.57,18.91,19.52,27.97,30.58
 Chinese-Alpaca-2-13B,22.94,22.94,25.75,25.75,25.15,25.15,22.33,22.33
 GPT-3.5-turbo,36.42,35.81,39.24,43.26,39.84,39.44,27.16,27.77
 LLaMA-2-13B,23.94,24.35,29.58,31.99,24.55,26.76,21.13,20.72
-Qwen-7B-Chat,18.51,17.71,27.36,28.37,29.78,29.58,33.60,31.79
+Qwen-7B-Chat,18.51,17.71,27.36,28.37,29.78,29.58,33.6,31.79
 ChatGLM2-6B,23.34,23.34,24.35,24.14,22.94,22.94,26.16,26.16
 Chinese-LLaMA-2-13B,14.69,14.69,19.92,19.92,19.72,19.72,20.93,20.93
 InternLM-7B,25.96,25.96,25.96,25.96,29.18,29.18,28.37,28.37
@@ -11,18 +11,18 @@ LLaMA-2-7B,20.72,20.72,27.16,27.97,21.53,18.51,18.31,17.91
 Baichuan2-13B-Chat,25.7,25.5,20.1,21.3,27.7,26.7,22.7,24.7
 GPT-4,/,/,59.38,65.17,/,/,44.06,48.09
 AquilaChat2-34B,34.66,34.66,47.74,47.74,44.48,44.48,NULL,NULL
-Mistral-7B,1.90,1.90,45.61,45.61,15.00,15.00,35.97,35.97
-Yi-34B-Chat,49.90,49.30,52.72,53.72,56.34,56.34,51.31,54.33
+Mistral-7B,1.9,1.9,45.61,45.61,15,15,35.97,35.97
+Yi-34B-Chat,49.9,49.3,52.72,53.72,56.34,56.34,51.31,54.33
 DevOps-Model-14B-Chat,24.75,22.74,28.37,27.77,36.62,37.02,27.57,26.36
-Qwen-72B-Chat,48.29,48.49,49.50,49.70,49.70,49.70,45.27,44.87
-ERNIE-Bot-4.0,48.56,48.56,50.64,50.64,48.00,48.00,54.00,54.00
-Mistral-7B,0.20,0.20,26.76,26.76,10.26,10.26,32.19,32.19
-Qwen-14B-Chat,27.57,27.57,32.39,36.02,40.04,35.41,30.38,33.40
-LLaMA-2-70B-Chat,15.29,15.29,34.81,34.81,26.76,26.76,33.80,33.80
+Qwen-72B-Chat,48.29,48.49,49.5,49.7,49.7,49.7,45.27,44.87
+ERNIE-Bot-4.0,48.56,48.56,50.64,50.64,48,48,54,54
+Mistral-7B,0.2,0.2,26.76,26.76,10.26,10.26,32.19,32.19
+Qwen-14B-Chat,27.57,27.57,32.39,36.02,40.04,35.41,30.38,33.4
+LLaMA-2-70B-Chat,15.29,15.29,34.81,34.81,26.76,26.76,33.8,33.8
 ChatGLM3-6B,21.32796781,21.32796781,28.97384306,28.97384306,21.73038229,21.73038229,29.57746479,29.57746479
 InternLM2-Chat-7B,28.57142857,28.57142857,31.79074447,31.79074447,30.78470825,30.78470825,31.18712274,31.18712274
-gemma_2b,18.51107,18.51107,24.9497,24.9497 ,21.52918,21.52918,27.7666,27.7666 
-gemma_7b,19.3159,19.3159,53.94737,53.94737 ,18.51107,18.51107,5.204461,5.204461 
-qwen1.5-14b-base,20.92555,20.92555,35.61368,35.61368 ,41.44869,41.44869,30.78471,30.78471 
+gemma_2b,18.51107,18.51107,24.9497,24.9497,21.52918,21.52918,27.7666,27.7666
+gemma_7b,19.3159,19.3159,53.94737,53.94737,18.51107,18.51107,5.204461,5.204461
+qwen1.5-14b-base,20.92555,20.92555,35.61368,35.61368,41.44869,41.44869,30.78471,30.78471
 qwen1.5-14b-chat,24.14487,23.34004,40.64386,41.04628,38.22938,38.02817,39.43662,40.04024
-
+Claude-3-Opus,48.09,48.09,,,,,,

data/pufa_zh_mc.csv

@@ -1,21 +1,21 @@
 name,few_native,few_self_con,few_cot,few_cot_self_con,zero_native,zero_self_con,zero_cot,zero_cot_self_con
-GPT4,84.00,84.00,90.67,90.67,88.00,88.00,86.67,86.67
-Yi-34B-Chat,90.67,92.00,78.67,89.33,84.00,84.00,88.00,88.00
+GPT4,84,84,90.67,90.67,88,88,86.67,86.67
+Yi-34B-Chat,90.67,92,78.67,89.33,84,84,88,88
 DevOps-Model-14B-Chat,82.67,81.33,53.33,70.67,29.33,29.33,62.67,61.33
-LLaMA-2-7B,48.00,48.00,52.00,52.00,25.33,25.33,40.00,40.00
-Qwen-72B-Chat,88.00,88.00,82.67,82.67,90.67,90.67,85.33,85.33
-GPT-3.5-turbo,76.00,78.67,84.00,82.67,77.33,77.33,84.00,81.33
+LLaMA-2-7B,48,48,52,52,25.33,25.33,40,40
+Qwen-72B-Chat,88,88,82.67,82.67,90.67,90.67,85.33,85.33
+GPT-3.5-turbo,76,78.67,84,82.67,77.33,77.33,84,81.33
 ERNIE-Bot-4.0,82.67,82.67,86.67,86.67,86.67,86.67,86.67,86.67
-Mistral-7B,22.67,22.67,54.67,54.67,4.00,4.00,58.67,58.67
-LLaMA-2-13B,61.33,61.33,53.33,53.33,44.00,44.00,68.00,68.00
+Mistral-7B,22.67,22.67,54.67,54.67,4,4,58.67,58.67
+LLaMA-2-13B,61.33,61.33,53.33,53.33,44,44,68,68
 Baichuan2-13B-Chat,62.67,61.33,62.67,62.67,65.33,66.67,66.67,66.67
-Qwen-14B-Chat,73.33,73.33,72.00,80.00,73.33,73.33,69.33,72.00
+Qwen-14B-Chat,73.33,73.33,72,80,73.33,73.33,69.33,72
 LLaMA-2-70B-Chat,49.33,49.33,66.67,66.67,6.67,6.67,65.33,65.33
 ChatGLM3-6B,56,56,58.66666667,58.66666667,60,60,61.33333333,61.33333333
 InternLM2-Chat-20B,80,80,,,76,76,80,80
 InternLM2-Chat-7B,72,72,53.33333333,53.33333333,78.66666667,78.66666667,72,72
-gemma_2b,36,36,30.66667,30.66667,36,36,41.33333,41.33333 
-gemma_7b,46.66667,46.66667,56,56,34.66667,34.66667,56,56 
-qwen1.5-14b-base,92,92,42.66667,42.66667,78.66667,78.66667,72,72 
+gemma_2b,36,36,30.66667,30.66667,36,36,41.33333,41.33333
+gemma_7b,46.66667,46.66667,56,56,34.66667,34.66667,56,56
+qwen1.5-14b-base,92,92,42.66667,42.66667,78.66667,78.66667,72,72
 qwen1.5-14b-chat,78.66667,80,86.66667,85.33333,86.66667,89.33333,85.33333,85.33333
-
+Claude-3-Opus,,,,,86.67,86.67,,

data/rzy_zh_mc.csv

@@ -1,21 +1,21 @@
 name,few_native,few_self_con,few_cot,few_cot_self_con,zero_native,zero_self_con,zero_cot,zero_cot_self_con
 GPT4,65.28,65.28,68.19,68.19,65.56,65.56,68.05,68.05
 Yi-34B-Chat,60.17,60.03,57.68,57.54,64.45,64.59,67.77,67.36
-DevOps-Model-14B-Chat,65.28,64.18,55.19,61.83,53.67,56.85,54.50,59.20
-LLaMA-2-7B,46.20,46.20,53.39,53.39,34.85,34.85,44.95,44.95
+DevOps-Model-14B-Chat,65.28,64.18,55.19,61.83,53.67,56.85,54.5,59.2
+LLaMA-2-7B,46.2,46.2,53.39,53.39,34.85,34.85,44.95,44.95
 Qwen-72B-Chat,65.98,65.98,70.12,70.12,66.67,66.67,65.28,65.28
-GPT-3.5-turbo,65.28,66.25,68.05,68.74,65.28,65.42,66.39,67.50
-ERNIE-Bot-4.0,73.00,73.00,77.00,77.00,76.00,76.00,79.00,79.00
-Mistral-7B,29.88,29.88,59.75,59.75,18.53,18.53,60.30,60.30
+GPT-3.5-turbo,65.28,66.25,68.05,68.74,65.28,65.42,66.39,67.5
+ERNIE-Bot-4.0,73,73,77,77,76,76,79,79
+Mistral-7B,29.88,29.88,59.75,59.75,18.53,18.53,60.3,60.3
 LLaMA-2-13B,57.12,57.12,53.39,53.39,51.18,51.18,59.06,59.06
-Baichuan2-13B-Chat,59.06,59.34,64.45,64.32,60.17,60.17,62.79,67.50
+Baichuan2-13B-Chat,59.06,59.34,64.45,64.32,60.17,60.17,62.79,67.5
 Qwen-14B-Chat,65.28,63.49,62.93,65.98,61.96,61.55,61.55,64.45
 LLaMA-2-70B-Chat,48.82,48.82,59.75,59.75,5.26,5.26,62.52,62.52
 ChatGLM3-6B,55.32503458,55.32503458,59.33609959,59.33609959,54.21853389,54.21853389,62.10235131,62.10235131
 InternLM2-Chat-20B,,,,,63.90041494,63.90041494,64.03872752,64.03872752
 InternLM2-Chat-7B,65.00691563,65.00691563,54.21853389,54.21853389,61.2724758,61.2724758,63.62378976,63.62378976
-gemma_2b,33.60996,33.60996,37.75934,37.75934 ,36.37621,36.37621,45.22822,45.22822 
-gemma_7b,42.04703,42.04703,56.70816,56.70816 ,39.41909,39.41909,54.77178,54.77178 
-qwen1.5-14b-base,65.42185,65.42185,50.89903,50.89903 ,51.17566,51.17566,62.6556,62.6556 
+gemma_2b,33.60996,33.60996,37.75934,37.75934,36.37621,36.37621,45.22822,45.22822
+gemma_7b,42.04703,42.04703,56.70816,56.70816,39.41909,39.41909,54.77178,54.77178
+qwen1.5-14b-base,65.42185,65.42185,50.89903,50.89903,51.17566,51.17566,62.6556,62.6556
 qwen1.5-14b-chat,63.34716,63.7621,65.42185,65.9751,62.93223,64.03873,64.59198,64.31535
-
+Claude-3-Opus,,,,,76.76,76.76,,

data/zabbix_zh_mc.csv

@@ -1,21 +1,21 @@
 name,few_native,few_self_con,few_cot,few_cot_self_con,zero_native,zero_self_con,zero_cot,zero_cot_self_con
-GPT4,60.00,60.00,59.00,59.00,51.00,51.00,53.00,53.00
-Yi-34B-Chat,42.00,42.00,42.00,42.00,40.00,40.00,40.00,40.00
-DevOps-Model-14B-Chat,46.00,44.00,44.00,46.00,27.00,28.00,36.00,33.00
-LLaMA-2-7B,22.00,22.00,28.00,28.00,18.00,18.00,35.00,35.00
-Qwen-72B-Chat,45.00,45.00,61.00,61.00,46.00,46.00,44.00,44.00
-GPT-3.5-turbo,40.00,40.00,48.00,48.00,36.00,36.00,42.00,42.00
-ERNIE-Bot-4.0,47.00,47.00,51.00,51.00,44.00,44.00,48.00,48.00
-Mistral-7B,11.00,11.00,44.00,44.00,6.00,6.00,42.00,42.00
-LLaMA-2-13B,40.00,40.00,43.00,43.00,28.00,28.00,45.00,45.00
-Baichuan2-13B-Chat,29.00,27.00,40.00,43.00,31.00,29.00,47.00,47.00
-Qwen-14B-Chat,44.00,40.00,47.00,43.00,36.00,36.00,39.00,41.00
-LLaMA-2-70B-Chat,29.00,29.00,46.00,46.00,1.00,1.00,47.00,47.00
+GPT4,60,60,59,59,51,51,53,53
+Yi-34B-Chat,42,42,42,42,40,40,40,40
+DevOps-Model-14B-Chat,46,44,44,46,27,28,36,33
+LLaMA-2-7B,22,22,28,28,18,18,35,35
+Qwen-72B-Chat,45,45,61,61,46,46,44,44
+GPT-3.5-turbo,40,40,48,48,36,36,42,42
+ERNIE-Bot-4.0,47,47,51,51,44,44,48,48
+Mistral-7B,11,11,44,44,6,6,42,42
+LLaMA-2-13B,40,40,43,43,28,28,45,45
+Baichuan2-13B-Chat,29,27,40,43,31,29,47,47
+Qwen-14B-Chat,44,40,47,43,36,36,39,41
+LLaMA-2-70B-Chat,29,29,46,46,1,1,47,47
 ChatGLM3-6B,29,29,34,34,29,29,36,36
 InternLM2-Chat-20B,44,44,,,41,41,,
 InternLM2-Chat-7B,45,45,35,35,43,43,39,39
 gemma_2b,24,24,30,30,25,25,32,32
-gemma_7b,28,28,40,40 ,22,22,44,44
+gemma_7b,28,28,40,40,22,22,44,44
 qwen1.5-14b-base,48,48,36,36,38,38,39,39
 qwen1.5-14b-chat,42,39,48,49,34,34,45,43
-
+Claude-3-Opus,,,,,65,65,,

data/zjyd_zh_mc.csv

@@ -2,17 +2,17 @@ name,zero_native,zero_self_con,zero_cot,zero_cot_self_con,few_native,few_self_co
 Baichuan-13B-Chat,11.04,11.13,26.92,28.61,14.35,13.22,31.69,33.97
 Chinese-Alpaca-2-13B,22.69,22.69,24.59,24.59,40.52,40.52,40.73,40.73
 GPT-3.5-turbo,37.06,36.83,37.56,39.25,39.42,39.77,41.96,42.15
-LLaMA-2-13B,25.43,27.16,29.17,29.99,36.56,36.15,37.70,39.02
-Qwen-7B-Chat,36.28,36.50,33.18,33.51,41.58,40.59,31.48,31.46
-ChatGLM2-6B,23.09,23.12,24.22,24.08,30.46,30.46,35.97,35.90
+LLaMA-2-13B,25.43,27.16,29.17,29.99,36.56,36.15,37.7,39.02
+Qwen-7B-Chat,36.28,36.5,33.18,33.51,41.58,40.59,31.48,31.46
+ChatGLM2-6B,23.09,23.12,24.22,24.08,30.46,30.46,35.97,35.9
 Chinese-LLaMA-2-13B,17.98,17.98,17.83,17.83,31.66,31.66,36.24,36.24
 InternLM-7B,27.81,27.81,19.95,19.95,24.18,24.18,35.35,35.35
 LLaMA-2-7B,24.09,23.47,28.69,29.26,29.94,30.03,31.35,31.93
-GPT-4,/,/,57.35,62.11,/,/,61.20,65.68
+GPT-4,/,/,57.35,62.11,/,/,61.2,65.68
 Yi-34B-Chat,64.91,64.58,62.77,65.51,70.85,70.92,48.77,47.97
-DevOps-Model-14B-Chat,41.04,42.70,48.71,53.57,56.85,57.25,51.30,54.29
+DevOps-Model-14B-Chat,41.04,42.7,48.71,53.57,56.85,57.25,51.3,54.29
 Qwen-72B-Chat,64.79,64.79,65.79,65.72,70.19,70.19,68.31,68.38
-ERNIE-Bot-4.0,45.99,45.99,48.98,48.98,46.00,46.00,54.00,54.00
+ERNIE-Bot-4.0,45.99,45.99,48.98,48.98,46,46,54,54
 Mistral-7B,1.27,1.27,42.05,42.05,30.72,30.72,46.44,46.44
 Qwen-14B-Chat,41.71,41.44,45.58,47.98,53.52,49.92,54.72,58.85
 LLaMA-2-70B-Chat,24.38,24.38,43.63,43.63,44.65,44.65,48.84,48.84
@@ -21,8 +21,8 @@ InternLM2-Chat-20B,44.6,44.6,47,47,62.2,62.2,38.3,38.3
 InternLM2-Chat-7B,38.8,38.8,44.6,44.6,46,46,35.8,35.8
 GLM3-turbo,43,43,,,,,,
 GLM4,50,50,,,,,,
-gemma_2b,25.6,25.6,28.3,28.3 ,19.1,19.1,35.5,35.5 
-gemma_7b,27.3,27.3,35.4,35.4 ,17.3,17.3,44.5,44.5 
-qwen1.5-14b-base,49.1,49.1,49.9,49.9 ,62.5,62.5,41.3,41.3 
+gemma_2b,25.6,25.6,28.3,28.3,19.1,19.1,35.5,35.5
+gemma_7b,27.3,27.3,35.4,35.4,17.3,17.3,44.5,44.5
+qwen1.5-14b-base,49.1,49.1,49.9,49.9,62.5,62.5,41.3,41.3
 qwen1.5-14b-chat,38.6,38.9,48.8,50.5,54.6,55.2,52.1,52.7
-
+Claude-3-Opus,84.82,84.82,,,,,,

data/zte_en_mc.csv

@@ -1,26 +1,26 @@
 name,zero_native,zero_self_con,zero_cot,zero_cot_self_con,few_native,few_self_con,few_cot,few_cot_self_con
-Baichuan-13B-Chat,11.60,14.31,14.68,18.46,14.56,15.68,16.21,16.82
+Baichuan-13B-Chat,11.6,14.31,14.68,18.46,14.56,15.68,16.21,16.82
 Chinese-Alpaca-2-13B,20.86,20.86,23.08,23.08,29.75,29.75,32.83,32.83
-GPT-3.5-turbo,35.04,34.82,38.46,43.50,39.29,39.19,41.01,42.58
-LLaMA-2-13B,15.62,18.32,29.88,34.45,23.16,29.14,37.59,44.30
-Qwen-7B-Chat,33.37,33.74,32.97,34.10,32.98,32.70,36.60,36.65
+GPT-3.5-turbo,35.04,34.82,38.46,43.5,39.29,39.19,41.01,42.58
+LLaMA-2-13B,15.62,18.32,29.88,34.45,23.16,29.14,37.59,44.3
+Qwen-7B-Chat,33.37,33.74,32.97,34.1,32.98,32.7,36.6,36.65
 ChatGLM2-6B,15.94,16.06,19.83,19.91,26.27,26.22,28.25,28.37
 Chinese-LLaMA-2-13B,10.02,10.02,19.51,19.51,34.51,34.51,33.34,33.34
 InternLM-7B,20.48,20.48,23.85,23.85,23.69,23.69,26.06,26.06
-LLaMA-2-7B,19.42,21.62,25.46,27.11,21.45,24.85,33.60,34.83
-GPT-4,/,/,56.90,65.49,/,/,59.39,63.54
-Yi-34B-Chat,38.24,37.04,48.24,52.10,61.33,61.19,53.53,53.39
-DevOps-Model-14B-Chat,31.04,30.51,42.84,47.37,52.25,49.38,45.90,47.23
+LLaMA-2-7B,19.42,21.62,25.46,27.11,21.45,24.85,33.6,34.83
+GPT-4,/,/,56.9,65.49,/,/,59.39,63.54
+Yi-34B-Chat,38.24,37.04,48.24,52.1,61.33,61.19,53.53,53.39
+DevOps-Model-14B-Chat,31.04,30.51,42.84,47.37,52.25,49.38,45.9,47.23
 Qwen-72B-Chat,53.19,53.19,55.25,55.52,58.13,58.13,58.72,58.99
-ERNIE-Bot-4.0,43.66,43.66,51.99,51.99,44.00,44.00,50.00,50.00
+ERNIE-Bot-4.0,43.66,43.66,51.99,51.99,44,44,50,50
 Mistral-7B,26.91,26.91,30.65,30.65,40.52,40.52,46.84,46.84
 Qwen-14B-Chat,33.71,36.25,41.24,42.51,51.19,50.39,57.18,59.18
-LLaMA-2-70B-Chat,23.64,23.64,39.31,39.31,38.98,39.12,47.90,47.90
+LLaMA-2-70B-Chat,23.64,23.64,39.31,39.31,38.98,39.12,47.9,47.9
 ChatGLM3-6B,30.4,30.4,30.7,30.7,26.9,26.9,37.2,37.2
 InternLM2-Chat-20B,39.1,39.1,37.7,37.7,47.7,47.7,33.5,33.5
 InternLM2-Chat-7B,36.8,36.8,31.7,31.7,46.3,46.3,36.9,36.9
-gemma_2b,20.1,20.1,24.2,24.2 ,31.2,31.2,35.5,35.5 
-gemma_7b,23.1,23.1,34.4,34.4 ,21.4,21.4,33.1,33.1 
-qwen1.5-14b-base,34,34,42.8,42.8 ,57.9,57.9,40.2,40.2 
+gemma_2b,20.1,20.1,24.2,24.2,31.2,31.2,35.5,35.5
+gemma_7b,23.1,23.1,34.4,34.4,21.4,21.4,33.1,33.1
+qwen1.5-14b-base,34,34,42.8,42.8,57.9,57.9,40.2,40.2
 qwen1.5-14b-chat,34.5,35.6,41.7,41.1,33.2,34.7,46.2,47.4
-
+Claude-3-Opus,62.4,62.4,,,,,,

data/zte_zh_mc.csv

@@ -25,4 +25,4 @@ gemma_2b,25.6,25.6,28.3,28.3,19.1,19.1,35.5,35.5
 InternLM-7B,27.81,27.81,19.95,19.95,24.18,24.18,35.35,35.35
 Baichuan-13B-Chat,11.04,11.13,26.92,28.61,14.35,13.22,31.69,33.97
 LLaMA-2-7B,24.09,23.47,28.69,29.26,29.94,30.03,31.35,31.93
-
+Claude-3-Opus,59.2,59.2,,,,,,