update leaderboard 2024-08-28

data_v2/bosc_zh_mc_gen.csv

@@ -14,8 +14,9 @@ Mistral-7B,0.0,0.0,37.5,37.5,20.0,20.0,50.0,50.0
 Qwen-14B-Chat,47.5,45.0,50.0,47.5,50.0,47.5,55.0,57.5
 Qwen-72B-Chat,50.0,50.0,47.5,47.5,45.0,45.0,60.0,60.0
 Yi-34B-Chat,55.0,55.0,60.0,67.5,50.0,50.0,52.5,55.0
-gemma_2b,37.5,37.5,40.0,40.0,32.5,32.5,40.0,40.0
-gemma_7b,32.5,32.5,62.5,62.5,40.0,40.0,50.0,50.0
-Qwen1.5-14B-Base,47.5,52.85714285714286,50.0,47.14285714285714,47.5,52.85714285714286,45.0,30.0
-Qwen1.5-14B-Chat,45.0,47.5,60.0,50.0,52.5,47.5,60.0,45.0
+gemma_2b,37.5,72.85714285714286,40.0,40.0,32.5,32.5,40.0,40.0
+gemma_7b,32.5,37.5,62.5,62.5,40.0,40.0,50.0,50.0
+Qwen1.5-14B-Base,47.5,32.5,50.0,47.14285714285714,47.5,52.85714285714286,45.0,30.0
+Qwen1.5-14B-Chat,45.0,52.85714285714286,60.0,50.0,52.5,47.5,60.0,45.0
 Qwen1.5-14B-Chat,,47.5,,72.5,,55.0,,60.0
+Qwen1.5-14B-Chat,,47.5,,,,,,

data_v2/gtja_zh_mc_gen.csv

@@ -14,8 +14,9 @@ Mistral-7B,5.49,5.49,47.25,47.25,14.29,14.29,38.46,38.46
 Qwen-14B-Chat,47.25,47.25,53.85,54.95,54.95,54.95,59.34,61.54
 Qwen-72B-Chat,71.43,71.43,67.03,67.03,70.33,70.33,74.73,74.73
 Yi-34B-Chat,71.43,74.73,71.43,73.63,69.23,70.33,49.45,47.25
-gemma_2b,30.76923,30.76923,43.95604,43.95604,32.96703,32.96703,29.67033,29.67033
-gemma_7b,29.67033,29.67033,56.04396,56.04396,34.06593,34.06593,50.54945,50.54945
-Qwen1.5-14B-Base,53.84615,36.550632911392405,63.73626,38.08016877637131,68.13187,43.24894514767932,42.85714,34.28270042194093
-Qwen1.5-14B-Chat,56.04396,53.84615,67.03297,63.73626,59.34066,68.13187,60.43956,42.85714
-Qwen1.5-14B-Chat,,54.94505,,68.13187,,57.14286,,62.63736
+gemma_2b,30.76923,41.508438818565395,43.95604,43.95604,32.96703,32.96703,29.67033,29.67033
+gemma_7b,29.67033,30.76923,56.04396,56.04396,34.06593,34.06593,50.54945,50.54945
+Qwen1.5-14B-Base,53.84615,29.67033,63.73626,38.08016877637131,68.13187,43.24894514767932,42.85714,34.28270042194093
+Qwen1.5-14B-Chat,56.04396,36.550632911392405,67.03297,63.73626,59.34066,68.13187,60.43956,42.85714
+Qwen1.5-14B-Chat,,53.84615,,68.13187,,57.14286,,62.63736
+Qwen1.5-14B-Chat,,54.94505,,,,,,

data_v2/huaweicloud_zh_mc_gen.csv

@@ -14,8 +14,9 @@ Mistral-7B,0.0,0.0,23.33,23.33,0.0,0.0,16.67,16.67
 Qwen-14B-Chat,13.33,13.33,20.0,26.67,40.0,30.0,26.67,33.33
 Qwen-72B-Chat,36.67,36.67,33.33,33.33,43.33,43.33,33.33,36.67
 Yi-34B-Chat,36.67,40.0,36.67,30.0,50.0,46.67,30.0,43.33
-gemma_2b,26.66667,26.66667,10.0,10.0,26.66667,26.66667,20.0,20.0
-gemma_7b,3.333333,3.333333,23.33333,23.33333,13.33333,13.33333,30.0,30.0
-Qwen1.5-14B-Base,20.0,27.5,33.33333,22.5,20.0,30.0,30.0,30.0
-Qwen1.5-14B-Chat,23.33333,20.0,13.33333,33.33333,26.66667,20.0,20.0,30.0
-Qwen1.5-14B-Chat,,26.66667,,13.33333,,26.66667,,30.0
+gemma_2b,26.66667,55.0,10.0,10.0,26.66667,26.66667,20.0,20.0
+gemma_7b,3.333333,26.66667,23.33333,23.33333,13.33333,13.33333,30.0,30.0
+Qwen1.5-14B-Base,20.0,3.333333,33.33333,22.5,20.0,30.0,30.0,30.0
+Qwen1.5-14B-Chat,23.33333,27.5,13.33333,33.33333,26.66667,20.0,20.0,30.0
+Qwen1.5-14B-Chat,,20.0,,13.33333,,26.66667,,30.0
+Qwen1.5-14B-Chat,,26.66667,,,,,,

data_v2/lenovo_zh_mc_gen.csv

@@ -12,4 +12,5 @@ Mistral-7B,47.5,47.5,62.5,62.5,35.0,35.0,60.0,60.0
 Qwen-14B-Chat,70.0,67.5,70.0,67.5,70.0,65.0,65.0,67.5
 Qwen-72B-Chat,72.5,72.5,75.0,75.0,75.0,75.0,75.0,75.0
 Yi-34B-Chat,75.0,75.0,87.5,82.5,62.5,57.5,52.5,52.5
-Meta-Llama-3-8B-Instruct,47.14285714285714,47.14285714285714,44.285714285714285,44.285714285714285,45.714285714285715,45.714285714285715,32.857142857142854,32.857142857142854
+Meta-Llama-3-8B-Instruct,71.42857142857143,71.42857142857143,44.285714285714285,44.285714285714285,45.714285714285715,45.714285714285715,32.857142857142854,32.857142857142854
+Meta-Llama-3-8B-Instruct,47.14285714285714,47.14285714285714,,,,,,

data_v2/network_en_mc_gen.csv

@@ -21,8 +21,9 @@ Qwen-14B-Chat,43.78,47.81,56.58,59.4,62.09,59.7,49.06,55.88
 Qwen-72B-Chat,70.41,70.5,72.38,72.56,70.32,70.32,70.13,70.22
 Qwen-7B-Chat,45.9,46.0,47.3,50.1,52.1,51.0,48.3,49.8
 Yi-34B-Chat,57.75,59.14,65.11,68.79,68.16,68.37,78.09,80.06
-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,34.87973,38.279481659390655,60.82474,76.69172932330827,65.54983,23.734458771084668,47.07904,33.241749376506874
-Qwen1.5-14B-Chat,54.89691,34.87973,64.08935,60.82474,52.23368,65.54983,59.53608,47.07904
-Qwen1.5-14B-Chat,,56.4433,,67.09622,,53.52234,,64.17526
+gemma_2b,26.46048,69.03417341637355,33.41924,33.41924,26.6323,26.6323,37.54296,37.54296
+gemma_7b,25.08591,26.46048,50.85911,50.85911,30.24055,30.24055,51.55747,51.55747
+Qwen1.5-14B-Base,34.87973,25.08591,60.82474,76.69172932330827,65.54983,23.734458771084668,47.07904,33.241749376506874
+Qwen1.5-14B-Chat,54.89691,38.279481659390655,64.08935,60.82474,52.23368,65.54983,59.53608,47.07904
+Qwen1.5-14B-Chat,,34.87973,,67.09622,,53.52234,,64.17526
+Qwen1.5-14B-Chat,,56.4433,,,,,,

data_v2/network_zh_mc_gen.csv

@@ -24,8 +24,9 @@ Qwen-14B-Chat,48.35,48.81,55.35,57.4,58.53,56.12,52.12,54.99
 Qwen-72B-Chat,65.77,65.86,68.13,68.3,69.4,69.4,69.99,70.08
 Qwen-7B-Chat,29.6,29.9,50.6,53.5,50.4,46.9,46.9,47.7
 Yi-34B-Chat,61.61,62.56,68.11,69.75,65.73,65.37,69.88,71.21
-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,45.18072,35.904696806952444,59.1222,38.94801939914722,61.10155,41.717931191615406,52.4957,31.059792337987826
-Qwen1.5-14B-Chat,54.04475,45.18072,62.56454,59.1222,58.77797,61.10155,63.42513,52.4957
-Qwen1.5-14B-Chat,,53.87263,,63.85542,,58.0895,,65.57659
+gemma_2b,29.69019,62.329525111479995,39.15663,39.15663,29.77625,29.77625,38.64028,38.64028
+gemma_7b,31.58348,29.69019,47.59036,47.59036,34.68158,34.68158,48.88124,48.88124
+Qwen1.5-14B-Base,45.18072,31.58348,59.1222,38.94801939914722,61.10155,41.717931191615406,52.4957,31.059792337987826
+Qwen1.5-14B-Chat,54.04475,35.904696806952444,62.56454,59.1222,58.77797,61.10155,63.42513,52.4957
+Qwen1.5-14B-Chat,,45.18072,,63.85542,,58.0895,,65.57659
+Qwen1.5-14B-Chat,,53.87263,,,,,,

data_v2/oracle_en_mc_gen.csv

@@ -21,8 +21,9 @@ Qwen-14B-Chat,24.95,28.37,33.0,36.62,27.97,28.37,27.97,24.14
 Qwen-72B-Chat,47.28,47.48,48.09,48.09,49.7,49.7,43.46,43.66
 Qwen-7B-Chat,18.91,19.11,22.13,23.94,26.76,25.55,34.81,33.4
 Yi-34B-Chat,47.08,48.69,47.08,46.28,58.15,58.35,56.94,58.95
-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,29.17505,28.468825409248026,33.60161,40.47805387073632,36.82093,23.33528989760647,27.7666,34.6197743429205
-Qwen1.5-14B-Chat,32.79678,29.17505,39.43662,33.60161,32.39437,36.82093,36.82093,27.7666
-Qwen1.5-14B-Chat,,35.41247,,43.05835,,33.60161,,38.833
+gemma_2b,16.90141,48.31816996021653,19.5171,19.5171,16.09658,16.09658,24.74849,24.74849
+gemma_7b,14.28571,16.90141,30.98592,30.98592,2.60223,2.60223,43.85965,43.85965
+Qwen1.5-14B-Base,29.17505,14.28571,33.60161,40.47805387073632,36.82093,23.33528989760647,27.7666,34.6197743429205
+Qwen1.5-14B-Chat,32.79678,28.468825409248026,39.43662,33.60161,32.39437,36.82093,36.82093,27.7666
+Qwen1.5-14B-Chat,,29.17505,,43.05835,,33.60161,,38.833
+Qwen1.5-14B-Chat,,35.41247,,,,,,

data_v2/oracle_zh_mc_gen.csv

@@ -20,8 +20,9 @@ Qwen-14B-Chat,27.57,27.57,32.39,36.02,40.04,35.41,30.38,33.4
 Qwen-72B-Chat,48.29,48.49,49.5,49.7,49.7,49.7,45.27,44.87
 Qwen-7B-Chat,18.51,17.71,27.36,28.37,29.78,29.58,33.6,31.79
 Yi-34B-Chat,49.9,49.3,52.72,53.72,56.34,56.34,51.31,54.33
-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,20.92555,33.91785690993282,35.61368,27.773429857170807,41.44869,41.359323028761494,30.78471,32.62733972477663
-Qwen1.5-14B-Chat,24.14487,20.92555,40.64386,35.61368,38.22938,41.44869,39.43662,30.78471
-Qwen1.5-14B-Chat,,23.34004,,41.04628,,38.02817,,40.04024
+gemma_2b,18.51107,50.00570664579664,24.9497,24.9497,21.52918,21.52918,27.7666,27.7666
+gemma_7b,19.3159,18.51107,53.94737,53.94737,18.51107,18.51107,5.204461,5.204461
+Qwen1.5-14B-Base,20.92555,19.3159,35.61368,27.773429857170807,41.44869,41.359323028761494,30.78471,32.62733972477663
+Qwen1.5-14B-Chat,24.14487,33.91785690993282,40.64386,35.61368,38.22938,41.44869,39.43662,30.78471
+Qwen1.5-14B-Chat,,20.92555,,41.04628,,38.02817,,40.04024
+Qwen1.5-14B-Chat,,23.34004,,,,,,

data_v2/pufa_zh_mc_gen.csv

@@ -14,8 +14,9 @@ Mistral-7B,4.0,4.0,58.67,58.67,22.67,22.67,54.67,54.67
 Qwen-14B-Chat,73.33,73.33,69.33,72.0,73.33,73.33,72.0,80.0
 Qwen-72B-Chat,90.67,90.67,85.33,85.33,88.0,88.0,82.67,82.67
 Yi-34B-Chat,84.0,84.0,88.0,88.0,90.67,92.0,78.67,89.33
-gemma_2b,36.0,36.0,41.33333,41.33333,36.0,36.0,30.66667,30.66667
-gemma_7b,34.66667,34.66667,56.0,56.0,46.66667,46.66667,56.0,56.0
-Qwen1.5-14B-Base,78.66667,85.8108108108108,72.0,31.756756756756754,92.0,83.1081081081081,42.66667,27.7027027027027
-Qwen1.5-14B-Chat,86.66667,78.66667,85.33333,72.0,78.66667,92.0,86.66667,42.66667
-Qwen1.5-14B-Chat,,89.33333,,85.33333,,80.0,,85.33333
+gemma_2b,36.0,93.24324324324324,41.33333,41.33333,36.0,36.0,30.66667,30.66667
+gemma_7b,34.66667,36.0,56.0,56.0,46.66667,46.66667,56.0,56.0
+Qwen1.5-14B-Base,78.66667,34.66667,72.0,31.756756756756754,92.0,83.1081081081081,42.66667,27.7027027027027
+Qwen1.5-14B-Chat,86.66667,85.8108108108108,85.33333,72.0,78.66667,92.0,86.66667,42.66667
+Qwen1.5-14B-Chat,,78.66667,,85.33333,,80.0,,85.33333
+Qwen1.5-14B-Chat,,89.33333,,,,,,

data_v2/rzy_zh_mc_gen.csv

@@ -14,8 +14,9 @@ Mistral-7B,18.53,18.53,60.3,60.3,29.88,29.88,59.75,59.75
 Qwen-14B-Chat,61.96,61.55,61.55,64.45,65.28,63.49,62.93,65.98
 Qwen-72B-Chat,66.67,66.67,65.28,65.28,65.98,65.98,70.12,70.12
 Yi-34B-Chat,64.45,64.59,67.77,67.36,60.17,60.03,57.68,57.54
-gemma_2b,36.37621,36.37621,45.22822,45.22822,33.60996,33.60996,37.75934,37.75934
-gemma_7b,39.41909,39.41909,54.77178,54.77178,42.04703,42.04703,56.70816,56.70816
-Qwen1.5-14B-Base,51.17566,36.55172413793103,62.6556,28.27586206896552,65.42185,38.62068965517241,50.89903,34.48275862068966
-Qwen1.5-14B-Chat,62.93223,51.17566,64.59198,62.6556,63.34716,65.42185,65.42185,50.89903
-Qwen1.5-14B-Chat,,64.03873,,64.31535,,63.7621,,65.9751
+gemma_2b,36.37621,67.64288271089369,45.22822,45.22822,33.60996,33.60996,37.75934,37.75934
+gemma_7b,39.41909,36.37621,54.77178,54.77178,42.04703,42.04703,56.70816,56.70816
+Qwen1.5-14B-Base,51.17566,39.41909,62.6556,28.27586206896552,65.42185,38.62068965517241,50.89903,34.48275862068966
+Qwen1.5-14B-Chat,62.93223,36.55172413793103,64.59198,62.6556,63.34716,65.42185,65.42185,50.89903
+Qwen1.5-14B-Chat,,51.17566,,64.31535,,63.7621,,65.9751
+Qwen1.5-14B-Chat,,64.03873,,,,,,

data_v2/zabbix_zh_mc_gen.csv

@@ -14,8 +14,9 @@ Mistral-7B,6.0,6.0,42.0,42.0,11.0,11.0,44.0,44.0
 Qwen-14B-Chat,36.0,36.0,39.0,41.0,44.0,40.0,47.0,43.0
 Qwen-72B-Chat,46.0,46.0,44.0,44.0,45.0,45.0,61.0,61.0
 Yi-34B-Chat,40.0,40.0,40.0,40.0,42.0,42.0,42.0,42.0
-gemma_2b,25.0,25.0,32.0,32.0,24.0,24.0,30.0,30.0
-gemma_7b,22.0,22.0,44.0,44.0,28.0,28.0,40.0,40.0
-Qwen1.5-14B-Base,38.0,39.670138888888886,39.0,37.58680555555556,48.0,30.381944444444443,36.0,33.072916666666664
-Qwen1.5-14B-Chat,34.0,38.0,45.0,39.0,42.0,48.0,48.0,36.0
-Qwen1.5-14B-Chat,,34.0,,43.0,,39.0,,49.0
+gemma_2b,25.0,61.71875,32.0,32.0,24.0,24.0,30.0,30.0
+gemma_7b,22.0,25.0,44.0,44.0,28.0,28.0,40.0,40.0
+Qwen1.5-14B-Base,38.0,22.0,39.0,37.58680555555556,48.0,30.381944444444443,36.0,33.072916666666664
+Qwen1.5-14B-Chat,34.0,39.670138888888886,45.0,39.0,42.0,48.0,48.0,36.0
+Qwen1.5-14B-Chat,,38.0,,43.0,,39.0,,49.0
+Qwen1.5-14B-Chat,,34.0,,,,,,

data_v2/zjyd_zh_mc_gen.csv

@@ -21,8 +21,9 @@ Qwen-14B-Chat,41.71,41.44,45.58,47.98,53.52,49.92,54.72,58.85
 Qwen-72B-Chat,64.79,64.79,65.79,65.72,70.19,70.19,68.31,68.38
 Qwen-7B-Chat,36.28,36.5,33.18,33.51,41.58,40.59,31.48,31.46
 Yi-34B-Chat,64.91,64.58,62.77,65.51,70.85,70.92,48.77,47.97
-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,49.1,63.425925925925924,49.9,0.0,62.5,66.2037037037037,41.3,25.0
-Qwen1.5-14B-Chat,38.6,49.1,48.8,49.9,54.6,62.5,52.1,41.3
-Qwen1.5-14B-Chat,,38.9,,50.5,,55.2,,52.7
+gemma_2b,25.6,68.05555555555556,28.3,28.3,19.1,19.1,35.5,35.5
+gemma_7b,27.3,25.6,35.4,35.4,17.3,17.3,44.5,44.5
+Qwen1.5-14B-Base,49.1,27.3,49.9,0.0,62.5,66.2037037037037,41.3,25.0
+Qwen1.5-14B-Chat,38.6,63.425925925925924,48.8,49.9,54.6,62.5,52.1,41.3
+Qwen1.5-14B-Chat,,49.1,,50.5,,55.2,,52.7
+Qwen1.5-14B-Chat,,38.9,,,,,,

data_v2/zte_en_mc_gen.csv

@@ -19,9 +19,10 @@ Qwen-14B-Chat,33.71,36.25,41.24,42.51,51.19,50.39,57.18,59.18
 Qwen-72B-Chat,53.19,53.19,55.25,55.52,58.13,58.13,58.72,58.99
 Qwen-7B-Chat,33.37,33.74,32.97,34.1,32.98,32.7,36.6,36.65
 Yi-34B-Chat,38.24,37.04,48.24,52.1,61.33,61.19,53.53,53.39
-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,34.0,38.9,42.8,63.4,57.9,37.6,40.2,59.0
-Qwen1.5-14B-Chat,34.5,24.7,41.7,35.4,33.2,19.7,46.2,32.9
-Qwen1.5-14B-Base,,34.0,,42.8,,57.9,,40.2
-Qwen1.5-14B-Chat,,35.6,,41.1,,34.7,,47.4
+gemma_2b,20.1,49.599999999999994,24.2,24.2,31.2,31.2,35.5,35.5
+gemma_7b,23.1,20.1,34.4,34.4,21.4,21.4,33.1,33.1
+Qwen1.5-14B-Base,34.0,23.1,42.8,63.4,57.9,37.6,40.2,59.0
+Qwen1.5-14B-Chat,34.5,38.9,41.7,35.4,33.2,19.7,46.2,32.9
+Qwen1.5-14B-Base,24.7,24.7,,42.8,,57.9,,40.2
+Qwen1.5-14B-Chat,,34.0,,41.1,,34.7,,47.4
+Qwen1.5-14B-Chat,,35.6,,,,,,

data_v2/zte_zh_mc_gen.csv

@@ -21,9 +21,10 @@ Qwen-14B-Chat,41.71,41.44,45.58,47.98,53.52,49.92,54.72,58.85
 Qwen-72B-Chat,64.79,64.79,65.79,65.72,70.19,70.19,68.31,68.38
 Qwen-7B-Chat,36.28,36.5,33.18,33.51,41.58,40.59,31.48,31.46
 Yi-34B-Chat,64.91,64.58,62.77,65.51,70.85,70.92,48.77,47.97
-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,49.1,31.1,49.9,37.4,62.5,51.10000000000001,41.3,36.900000000000006
+gemma_2b,25.6,51.4,28.3,28.3,19.1,19.1,35.5,35.5
+gemma_7b,27.3,25.6,35.4,35.4,17.3,17.3,44.5,44.5
+Qwen1.5-14B-Base,49.1,27.3,49.9,37.4,62.5,51.10000000000001,41.3,36.900000000000006
 Qwen1.5-14B-Chat,38.6,31.1,48.8,34.3,54.6,36.0,52.1,37.1
-Qwen1.5-14B-Base,,49.1,,49.9,,62.5,,41.3
-Qwen1.5-14B-Chat,,38.9,,50.5,,55.2,,52.7
+Qwen1.5-14B-Base,31.1,31.1,,49.9,,62.5,,41.3
+Qwen1.5-14B-Chat,,49.1,,50.5,,55.2,,52.7
+Qwen1.5-14B-Chat,,38.9,,,,,,