Junetheriver commited on
Commit
cd43969
·
1 Parent(s): 0257d7c

update leaderboard 2025-02-27

Browse files
data_v2/bosc_zh_mc_gen.csv CHANGED
@@ -17,6 +17,8 @@ Yi-34B-Chat,55.0,55.0,60.0,67.5,50.0,50.0,52.5,55.0
17
  Claude-3-Opus,72.85714285714286,72.85714285714286,,,,,,
18
  Deepseek-R1-Distill-Llama-8B,51.42857142857143,51.42857142857143,48.57142857142857,48.57142857142857,50.0,50.0,41.42857142857143,41.42857142857143
19
  Deepseek-R1-Distill-Qwen-1.5B,42.857142857142854,42.857142857142854,45.71428571428571,45.71428571428571,34.285714285714285,34.285714285714285,34.285714285714285,34.285714285714285
 
 
20
  Deepseek-R1-Distill-Qwen-7B,35.71428571428571,35.71428571428571,41.42857142857143,41.42857142857143,50.0,50.0,22.857142857142858,22.857142857142858
21
  Gemma-2B,37.5,37.5,40.0,40.0,32.5,32.5,40.0,40.0
22
  Gemma-7B,32.5,32.5,62.5,62.5,40.0,40.0,50.0,50.0
 
17
  Claude-3-Opus,72.85714285714286,72.85714285714286,,,,,,
18
  Deepseek-R1-Distill-Llama-8B,51.42857142857143,51.42857142857143,48.57142857142857,48.57142857142857,50.0,50.0,41.42857142857143,41.42857142857143
19
  Deepseek-R1-Distill-Qwen-1.5B,42.857142857142854,42.857142857142854,45.71428571428571,45.71428571428571,34.285714285714285,34.285714285714285,34.285714285714285,34.285714285714285
20
+ Deepseek-R1-Distill-Qwen-14B,50.0,50.0,,,51.42857142857143,51.42857142857143,,
21
+ Deepseek-R1-Distill-Qwen-32B,77.14285714285714,77.14285714285714,,,64.28571428571428,64.28571428571428,,
22
  Deepseek-R1-Distill-Qwen-7B,35.71428571428571,35.71428571428571,41.42857142857143,41.42857142857143,50.0,50.0,22.857142857142858,22.857142857142858
23
  Gemma-2B,37.5,37.5,40.0,40.0,32.5,32.5,40.0,40.0
24
  Gemma-7B,32.5,32.5,62.5,62.5,40.0,40.0,50.0,50.0
data_v2/gtja_zh_mc_gen.csv CHANGED
@@ -17,6 +17,8 @@ Yi-34B-Chat,71.43,74.73,71.43,73.63,69.23,70.33,49.45,47.25
17
  Claude-3-Opus,41.508438818565395,41.508438818565395,,,,,,
18
  Deepseek-R1-Distill-Llama-8B,33.38607594936709,33.38607594936709,42.24683544303797,42.24683544303797,38.449367088607595,38.449367088607595,38.71308016877637,38.71308016877637
19
  Deepseek-R1-Distill-Qwen-1.5B,31.11814345991561,31.11814345991561,24.68354430379747,24.68354430379747,22.890295358649787,22.890295358649787,26.951476793248943,26.951476793248943
 
 
20
  Deepseek-R1-Distill-Qwen-7B,39.71518987341772,39.71518987341772,29.746835443037973,29.746835443037973,27.584388185654007,27.584388185654007,40.348101265822784,40.348101265822784
21
  Gemma-2B,30.76923,30.76923,43.95604,43.95604,32.96703,32.96703,29.67033,29.67033
22
  Gemma-7B,29.67033,29.67033,56.04396,56.04396,34.06593,34.06593,50.54945,50.54945
 
17
  Claude-3-Opus,41.508438818565395,41.508438818565395,,,,,,
18
  Deepseek-R1-Distill-Llama-8B,33.38607594936709,33.38607594936709,42.24683544303797,42.24683544303797,38.449367088607595,38.449367088607595,38.71308016877637,38.71308016877637
19
  Deepseek-R1-Distill-Qwen-1.5B,31.11814345991561,31.11814345991561,24.68354430379747,24.68354430379747,22.890295358649787,22.890295358649787,26.951476793248943,26.951476793248943
20
+ Deepseek-R1-Distill-Qwen-14B,38.34388185654008,38.34388185654008,,,36.075949367088604,36.075949367088604,,
21
+ Deepseek-R1-Distill-Qwen-32B,48.20675105485232,48.20675105485232,,,44.67299578059072,44.67299578059072,,
22
  Deepseek-R1-Distill-Qwen-7B,39.71518987341772,39.71518987341772,29.746835443037973,29.746835443037973,27.584388185654007,27.584388185654007,40.348101265822784,40.348101265822784
23
  Gemma-2B,30.76923,30.76923,43.95604,43.95604,32.96703,32.96703,29.67033,29.67033
24
  Gemma-7B,29.67033,29.67033,56.04396,56.04396,34.06593,34.06593,50.54945,50.54945
data_v2/huaweicloud_en_mc_gen.csv CHANGED
@@ -4,4 +4,6 @@ GPT-4,40.0,40.0,,,55.00000000000001,55.00000000000001,,
4
  JIUTIAN-75B-net,45.0,45.0,60.0,60.0,60.0,60.0,70.0,70.0
5
  Deepseek-R1-Distill-Llama-8B,7.5,7.5,32.5,32.5,22.5,22.5,27.5,27.5
6
  Deepseek-R1-Distill-Qwen-1.5B,10.0,10.0,12.5,12.5,12.5,12.5,22.5,22.5
 
 
7
  Deepseek-R1-Distill-Qwen-7B,10.0,10.0,17.5,17.5,22.5,22.5,22.5,22.5
 
4
  JIUTIAN-75B-net,45.0,45.0,60.0,60.0,60.0,60.0,70.0,70.0
5
  Deepseek-R1-Distill-Llama-8B,7.5,7.5,32.5,32.5,22.5,22.5,27.5,27.5
6
  Deepseek-R1-Distill-Qwen-1.5B,10.0,10.0,12.5,12.5,12.5,12.5,22.5,22.5
7
+ Deepseek-R1-Distill-Qwen-14B,27.5,27.5,,,25.0,25.0,,
8
+ Deepseek-R1-Distill-Qwen-32B,42.5,42.5,,,30.0,30.0,,
9
  Deepseek-R1-Distill-Qwen-7B,10.0,10.0,17.5,17.5,22.5,22.5,22.5,22.5
data_v2/huaweicloud_zh_mc_gen.csv CHANGED
@@ -18,6 +18,8 @@ JIUTIAN-75B-net,65.0,65.0,70.0,70.0,50.0,50.0,75.0,75.0
18
  Claude-3-Opus,55.0,55.0,,,,,,
19
  Deepseek-R1-Distill-Llama-8B,10.0,10.0,30.0,30.0,35.0,35.0,27.5,27.5
20
  Deepseek-R1-Distill-Qwen-1.5B,25.0,25.0,5.0,5.0,32.5,32.5,20.0,20.0
 
 
21
  Deepseek-R1-Distill-Qwen-7B,10.0,10.0,22.5,22.5,35.0,35.0,32.5,32.5
22
  Gemma-2B,26.66667,26.66667,10.0,10.0,26.66667,26.66667,20.0,20.0
23
  Gemma-7B,3.333333,3.333333,23.33333,23.33333,13.33333,13.33333,30.0,30.0
 
18
  Claude-3-Opus,55.0,55.0,,,,,,
19
  Deepseek-R1-Distill-Llama-8B,10.0,10.0,30.0,30.0,35.0,35.0,27.5,27.5
20
  Deepseek-R1-Distill-Qwen-1.5B,25.0,25.0,5.0,5.0,32.5,32.5,20.0,20.0
21
+ Deepseek-R1-Distill-Qwen-14B,50.0,50.0,,,60.0,60.0,,
22
+ Deepseek-R1-Distill-Qwen-32B,60.0,60.0,,,62.5,62.5,,
23
  Deepseek-R1-Distill-Qwen-7B,10.0,10.0,22.5,22.5,35.0,35.0,32.5,32.5
24
  Gemma-2B,26.66667,26.66667,10.0,10.0,26.66667,26.66667,20.0,20.0
25
  Gemma-7B,3.333333,3.333333,23.33333,23.33333,13.33333,13.33333,30.0,30.0
data_v2/inspur_en_mc_gen.csv CHANGED
@@ -5,6 +5,8 @@ Baichuan2-7B-Chat,44.89795918367347,44.89795918367347,66.66666666666666,66.66666
5
  Claude-3-Opus,87.75510204081633,87.75510204081633,89.1156462585034,89.1156462585034,91.15646258503402,91.15646258503402,88.43537414965986,88.43537414965986
6
  Deepseek-R1-Distill-Llama-8B,36.054421768707485,36.054421768707485,70.74829931972789,70.74829931972789,34.01360544217687,34.01360544217687,59.863945578231295,59.863945578231295
7
  Deepseek-R1-Distill-Qwen-1.5B,41.49659863945578,41.49659863945578,50.34013605442177,50.34013605442177,42.17687074829932,42.17687074829932,56.4625850340136,56.4625850340136
 
 
8
  Deepseek-R1-Distill-Qwen-7B,42.17687074829932,42.17687074829932,56.4625850340136,56.4625850340136,44.89795918367347,44.89795918367347,74.14965986394559,74.14965986394559
9
  Qwen2-0.5B-Instruct,,,53.06122448979592,53.06122448979592,,,52.38095238095239,52.38095238095239
10
  Qwen2-1.5B-Instruct,,,67.3469387755102,67.3469387755102,65.98639455782312,65.98639455782312,,
 
5
  Claude-3-Opus,87.75510204081633,87.75510204081633,89.1156462585034,89.1156462585034,91.15646258503402,91.15646258503402,88.43537414965986,88.43537414965986
6
  Deepseek-R1-Distill-Llama-8B,36.054421768707485,36.054421768707485,70.74829931972789,70.74829931972789,34.01360544217687,34.01360544217687,59.863945578231295,59.863945578231295
7
  Deepseek-R1-Distill-Qwen-1.5B,41.49659863945578,41.49659863945578,50.34013605442177,50.34013605442177,42.17687074829932,42.17687074829932,56.4625850340136,56.4625850340136
8
+ Deepseek-R1-Distill-Qwen-14B,68.02721088435374,68.02721088435374,,,61.904761904761905,61.904761904761905,,
9
+ Deepseek-R1-Distill-Qwen-32B,85.03401360544217,85.03401360544217,,,58.50340136054422,58.50340136054422,,
10
  Deepseek-R1-Distill-Qwen-7B,42.17687074829932,42.17687074829932,56.4625850340136,56.4625850340136,44.89795918367347,44.89795918367347,74.14965986394559,74.14965986394559
11
  Qwen2-0.5B-Instruct,,,53.06122448979592,53.06122448979592,,,52.38095238095239,52.38095238095239
12
  Qwen2-1.5B-Instruct,,,67.3469387755102,67.3469387755102,65.98639455782312,65.98639455782312,,
data_v2/inspur_zh_mc_gen.csv CHANGED
@@ -5,6 +5,8 @@ Baichuan2-7B-Chat,62.585034013605444,62.585034013605444,,,42.857142857142854,42.
5
  Claude-3-Opus,83.6734693877551,83.6734693877551,85.03401360544217,85.03401360544217,87.75510204081633,87.75510204081633,91.83673469387756,91.83673469387756
6
  Deepseek-R1-Distill-Llama-8B,55.78231292517006,55.78231292517006,76.19047619047619,76.19047619047619,72.10884353741497,72.10884353741497,78.2312925170068,78.2312925170068
7
  Deepseek-R1-Distill-Qwen-1.5B,59.863945578231295,59.863945578231295,58.50340136054422,58.50340136054422,41.49659863945578,41.49659863945578,71.42857142857143,71.42857142857143
 
 
8
  Deepseek-R1-Distill-Qwen-7B,62.585034013605444,62.585034013605444,64.62585034013605,64.62585034013605,57.82312925170068,57.82312925170068,67.3469387755102,67.3469387755102
9
  Qwen2-0.5B-Instruct,56.4625850340136,56.4625850340136,,,,,57.14285714285714,57.14285714285714
10
  Qwen2-1.5B-Instruct,,,68.02721088435374,68.02721088435374,,,,
 
5
  Claude-3-Opus,83.6734693877551,83.6734693877551,85.03401360544217,85.03401360544217,87.75510204081633,87.75510204081633,91.83673469387756,91.83673469387756
6
  Deepseek-R1-Distill-Llama-8B,55.78231292517006,55.78231292517006,76.19047619047619,76.19047619047619,72.10884353741497,72.10884353741497,78.2312925170068,78.2312925170068
7
  Deepseek-R1-Distill-Qwen-1.5B,59.863945578231295,59.863945578231295,58.50340136054422,58.50340136054422,41.49659863945578,41.49659863945578,71.42857142857143,71.42857142857143
8
+ Deepseek-R1-Distill-Qwen-14B,68.70748299319727,68.70748299319727,,,72.78911564625851,72.78911564625851,,
9
+ Deepseek-R1-Distill-Qwen-32B,87.07482993197279,87.07482993197279,,,85.71428571428571,85.71428571428571,,
10
  Deepseek-R1-Distill-Qwen-7B,62.585034013605444,62.585034013605444,64.62585034013605,64.62585034013605,57.82312925170068,57.82312925170068,67.3469387755102,67.3469387755102
11
  Qwen2-0.5B-Instruct,56.4625850340136,56.4625850340136,,,,,57.14285714285714,57.14285714285714
12
  Qwen2-1.5B-Instruct,,,68.02721088435374,68.02721088435374,,,,
data_v2/lenovo_en_mc_gen.csv CHANGED
@@ -4,6 +4,8 @@ InternLM2-Chat-20B,62.5,62.5,,,75.0,75.0,,
4
  InternLM2-Chat-7B,65.0,65.0,67.5,67.5,75.0,75.0,57.5,57.5
5
  Deepseek-R1-Distill-Llama-8B,30.0,30.0,60.0,60.0,12.857142857142856,12.857142857142856,47.14285714285714,47.14285714285714
6
  Deepseek-R1-Distill-Qwen-1.5B,28.571428571428573,28.571428571428573,42.85714285714286,42.85714285714286,31.428571428571427,31.428571428571427,35.71428571428571,35.71428571428571
 
 
7
  Deepseek-R1-Distill-Qwen-7B,25.71428571428571,25.71428571428571,37.142857142857146,37.142857142857146,37.14285714285714,37.14285714285714,58.57142857142858,58.57142857142858
8
  Gemma-2B,22.5,22.5,47.5,47.5,30.0,30.0,37.5,37.5
9
  Gemma-7B,32.5,32.5,65.0,65.0,35.0,35.0,65.0,65.0
 
4
  InternLM2-Chat-7B,65.0,65.0,67.5,67.5,75.0,75.0,57.5,57.5
5
  Deepseek-R1-Distill-Llama-8B,30.0,30.0,60.0,60.0,12.857142857142856,12.857142857142856,47.14285714285714,47.14285714285714
6
  Deepseek-R1-Distill-Qwen-1.5B,28.571428571428573,28.571428571428573,42.85714285714286,42.85714285714286,31.428571428571427,31.428571428571427,35.71428571428571,35.71428571428571
7
+ Deepseek-R1-Distill-Qwen-14B,47.14285714285714,47.14285714285714,,,32.85714285714286,32.85714285714286,,
8
+ Deepseek-R1-Distill-Qwen-32B,64.28571428571428,64.28571428571428,,,54.285714285714285,54.285714285714285,,
9
  Deepseek-R1-Distill-Qwen-7B,25.71428571428571,25.71428571428571,37.142857142857146,37.142857142857146,37.14285714285714,37.14285714285714,58.57142857142858,58.57142857142858
10
  Gemma-2B,22.5,22.5,47.5,47.5,30.0,30.0,37.5,37.5
11
  Gemma-7B,32.5,32.5,65.0,65.0,35.0,35.0,65.0,65.0
data_v2/lenovo_zh_mc_gen.csv CHANGED
@@ -15,5 +15,7 @@ Yi-34B-Chat,75.0,75.0,87.5,82.5,62.5,57.5,52.5,52.5
15
  Claude-3-Opus,71.42857142857143,71.42857142857143,,,,,,
16
  Deepseek-R1-Distill-Llama-8B,47.142857142857146,47.142857142857146,60.0,60.0,60.0,60.0,40.0,40.0
17
  Deepseek-R1-Distill-Qwen-1.5B,24.285714285714285,24.285714285714285,34.285714285714285,34.285714285714285,55.71428571428571,55.71428571428571,52.857142857142854,52.857142857142854
 
 
18
  Deepseek-R1-Distill-Qwen-7B,40.0,40.0,30.0,30.0,42.85714285714286,42.85714285714286,57.142857142857146,57.142857142857146
19
  Meta-Llama-3-8B-Instruct,47.14285714285714,47.14285714285714,44.285714285714285,44.285714285714285,45.714285714285715,45.714285714285715,32.857142857142854,32.857142857142854
 
15
  Claude-3-Opus,71.42857142857143,71.42857142857143,,,,,,
16
  Deepseek-R1-Distill-Llama-8B,47.142857142857146,47.142857142857146,60.0,60.0,60.0,60.0,40.0,40.0
17
  Deepseek-R1-Distill-Qwen-1.5B,24.285714285714285,24.285714285714285,34.285714285714285,34.285714285714285,55.71428571428571,55.71428571428571,52.857142857142854,52.857142857142854
18
+ Deepseek-R1-Distill-Qwen-14B,68.57142857142858,68.57142857142858,,,68.57142857142858,68.57142857142858,,
19
+ Deepseek-R1-Distill-Qwen-32B,61.42857142857143,61.42857142857143,,,60.0,60.0,,
20
  Deepseek-R1-Distill-Qwen-7B,40.0,40.0,30.0,30.0,42.85714285714286,42.85714285714286,57.142857142857146,57.142857142857146
21
  Meta-Llama-3-8B-Instruct,47.14285714285714,47.14285714285714,44.285714285714285,44.285714285714285,45.714285714285715,45.714285714285715,32.857142857142854,32.857142857142854
data_v2/network_en_mc_gen.csv CHANGED
@@ -25,6 +25,8 @@ JIUTIAN-75B-net,69.38775510204081,69.38775510204081,76.04726100966703,76.0472610
25
  Claude-3-Opus,69.03417341637355,69.03417341637355,,,,,,
26
  Deepseek-R1-Distill-Llama-8B,19.65121264227399,19.65121264227399,44.240352567500906,44.240352567500906,25.932243238384128,25.932243238384128,37.26068697187482,37.26068697187482
27
  Deepseek-R1-Distill-Qwen-1.5B,15.894119111389756,15.894119111389756,20.67346477782439,20.67346477782439,18.523623589937444,18.523623589937444,25.022012419153338,25.022012419153338
 
 
28
  Deepseek-R1-Distill-Qwen-7B,17.8256800800284,17.8256800800284,35.38237070296834,35.38237070296834,25.341711114081956,25.341711114081956,34.738132885862726,34.738132885862726
29
  Gemma-2B,26.46048,26.46048,33.41924,33.41924,26.6323,26.6323,37.54296,37.54296
30
  Gemma-7B,25.08591,25.08591,50.85911,50.85911,30.24055,30.24055,51.55747,51.55747
 
25
  Claude-3-Opus,69.03417341637355,69.03417341637355,,,,,,
26
  Deepseek-R1-Distill-Llama-8B,19.65121264227399,19.65121264227399,44.240352567500906,44.240352567500906,25.932243238384128,25.932243238384128,37.26068697187482,37.26068697187482
27
  Deepseek-R1-Distill-Qwen-1.5B,15.894119111389756,15.894119111389756,20.67346477782439,20.67346477782439,18.523623589937444,18.523623589937444,25.022012419153338,25.022012419153338
28
+ Deepseek-R1-Distill-Qwen-14B,37.09841741078631,37.09841741078631,,,31.725773661621865,31.725773661621865,,
29
+ Deepseek-R1-Distill-Qwen-32B,61.682486412229224,61.682486412229224,,,37.41811610571493,37.41811610571493,,
30
  Deepseek-R1-Distill-Qwen-7B,17.8256800800284,17.8256800800284,35.38237070296834,35.38237070296834,25.341711114081956,25.341711114081956,34.738132885862726,34.738132885862726
31
  Gemma-2B,26.46048,26.46048,33.41924,33.41924,26.6323,26.6323,37.54296,37.54296
32
  Gemma-7B,25.08591,25.08591,50.85911,50.85911,30.24055,30.24055,51.55747,51.55747
data_v2/network_zh_mc_gen.csv CHANGED
@@ -28,6 +28,8 @@ JIUTIAN-75B-net,66.38023630504833,66.38023630504833,74.75832438238453,74.7583243
28
  Claude-3-Opus,62.329525111479995,62.329525111479995,,,,,,
29
  Deepseek-R1-Distill-Llama-8B,27.380138658334147,27.380138658334147,41.48846141327344,41.48846141327344,32.6123750935781,32.6123750935781,33.60348924258699,33.60348924258699
30
  Deepseek-R1-Distill-Qwen-1.5B,24.732285258601046,24.732285258601046,24.071542492595125,24.071542492595125,20.06151742993848,20.06151742993848,25.47277284119389,25.47277284119389
 
 
31
  Deepseek-R1-Distill-Qwen-7B,30.83520489535527,30.83520489535527,31.99882823942974,31.99882823942974,26.802395599388078,26.802395599388078,33.14454968590307,33.14454968590307
32
  Gemma-2B,29.69019,29.69019,39.15663,39.15663,29.77625,29.77625,38.64028,38.64028
33
  Gemma-7B,31.58348,31.58348,47.59036,47.59036,34.68158,34.68158,48.88124,48.88124
 
28
  Claude-3-Opus,62.329525111479995,62.329525111479995,,,,,,
29
  Deepseek-R1-Distill-Llama-8B,27.380138658334147,27.380138658334147,41.48846141327344,41.48846141327344,32.6123750935781,32.6123750935781,33.60348924258699,33.60348924258699
30
  Deepseek-R1-Distill-Qwen-1.5B,24.732285258601046,24.732285258601046,24.071542492595125,24.071542492595125,20.06151742993848,20.06151742993848,25.47277284119389,25.47277284119389
31
+ Deepseek-R1-Distill-Qwen-14B,45.859779318425936,45.859779318425936,,,47.220323536113014,47.220323536113014,,
32
+ Deepseek-R1-Distill-Qwen-32B,58.3829704130456,58.3829704130456,,,57.567620349575236,57.567620349575236,,
33
  Deepseek-R1-Distill-Qwen-7B,30.83520489535527,30.83520489535527,31.99882823942974,31.99882823942974,26.802395599388078,26.802395599388078,33.14454968590307,33.14454968590307
34
  Gemma-2B,29.69019,29.69019,39.15663,39.15663,29.77625,29.77625,38.64028,38.64028
35
  Gemma-7B,31.58348,31.58348,47.59036,47.59036,34.68158,34.68158,48.88124,48.88124
data_v2/oracle_en_mc_gen.csv CHANGED
@@ -24,6 +24,8 @@ Yi-34B-Chat,47.08,48.69,47.08,46.28,58.15,58.35,56.94,58.95
24
  Claude-3-Opus,48.31816996021653,48.31816996021653,,,,,,
25
  Deepseek-R1-Distill-Llama-8B,13.362518750407617,13.362518750407617,31.26345137937781,31.26345137937781,23.33528989760647,23.33528989760647,32.98441270462401,32.98441270462401
26
  Deepseek-R1-Distill-Qwen-1.5B,15.083480075653819,15.083480075653819,18.153655514250307,18.153655514250307,16.92346572751582,16.92346572751582,24.784777929955,24.784777929955
 
 
27
  Deepseek-R1-Distill-Qwen-7B,15.674525533163767,15.674525533163767,29.412867671036324,29.412867671036324,19.859942607447987,19.859942607447987,27.435107284940976,27.435107284940976
28
  Gemma-2B,16.90141,16.90141,19.5171,19.5171,16.09658,16.09658,24.74849,24.74849
29
  Gemma-7B,14.28571,14.28571,30.98592,30.98592,2.60223,2.60223,43.85965,43.85965
 
24
  Claude-3-Opus,48.31816996021653,48.31816996021653,,,,,,
25
  Deepseek-R1-Distill-Llama-8B,13.362518750407617,13.362518750407617,31.26345137937781,31.26345137937781,23.33528989760647,23.33528989760647,32.98441270462401,32.98441270462401
26
  Deepseek-R1-Distill-Qwen-1.5B,15.083480075653819,15.083480075653819,18.153655514250307,18.153655514250307,16.92346572751582,16.92346572751582,24.784777929955,24.784777929955
27
+ Deepseek-R1-Distill-Qwen-14B,31.89199765212287,31.89199765212287,,,36.61628513663341,36.61628513663341,,
28
+ Deepseek-R1-Distill-Qwen-32B,50.49240200873932,50.49240200873932,,,40.329681080023484,40.329681080023484,,
29
  Deepseek-R1-Distill-Qwen-7B,15.674525533163767,15.674525533163767,29.412867671036324,29.412867671036324,19.859942607447987,19.859942607447987,27.435107284940976,27.435107284940976
30
  Gemma-2B,16.90141,16.90141,19.5171,19.5171,16.09658,16.09658,24.74849,24.74849
31
  Gemma-7B,14.28571,14.28571,30.98592,30.98592,2.60223,2.60223,43.85965,43.85965
data_v2/oracle_zh_mc_gen.csv CHANGED
@@ -23,6 +23,8 @@ Yi-34B-Chat,49.9,49.3,52.72,53.72,56.34,56.34,51.31,54.33
23
  Claude-3-Opus,50.00570664579664,50.00570664579664,,,,,,
24
  Deepseek-R1-Distill-Llama-8B,25.90001956564273,25.90001956564273,34.199928259309985,34.199928259309985,29.46096654275093,29.46096654275093,31.583023543990087,31.583023543990087
25
  Deepseek-R1-Distill-Qwen-1.5B,25.54294658579534,25.54294658579534,21.57682775712516,21.57682775712516,20.87083414856845,20.87083414856845,25.67664514445966,25.67664514445966
 
 
26
  Deepseek-R1-Distill-Qwen-7B,26.35736646448836,26.35736646448836,27.31608295832518,27.31608295832518,29.617491684601838,29.617491684601838,31.11100241309594,31.11100241309594
27
  Gemma-2B,18.51107,18.51107,24.9497,24.9497,21.52918,21.52918,27.7666,27.7666
28
  Gemma-7B,19.3159,19.3159,53.94737,53.94737,18.51107,18.51107,5.204461,5.204461
 
23
  Claude-3-Opus,50.00570664579664,50.00570664579664,,,,,,
24
  Deepseek-R1-Distill-Llama-8B,25.90001956564273,25.90001956564273,34.199928259309985,34.199928259309985,29.46096654275093,29.46096654275093,31.583023543990087,31.583023543990087
25
  Deepseek-R1-Distill-Qwen-1.5B,25.54294658579534,25.54294658579534,21.57682775712516,21.57682775712516,20.87083414856845,20.87083414856845,25.67664514445966,25.67664514445966
26
+ Deepseek-R1-Distill-Qwen-14B,43.671329811517644,43.671329811517644,,,43.575132068088436,43.575132068088436,,
27
+ Deepseek-R1-Distill-Qwen-32B,51.3027457118633,51.3027457118633,,,53.48105393595513,53.48105393595513,,
28
  Deepseek-R1-Distill-Qwen-7B,26.35736646448836,26.35736646448836,27.31608295832518,27.31608295832518,29.617491684601838,29.617491684601838,31.11100241309594,31.11100241309594
29
  Gemma-2B,18.51107,18.51107,24.9497,24.9497,21.52918,21.52918,27.7666,27.7666
30
  Gemma-7B,19.3159,19.3159,53.94737,53.94737,18.51107,18.51107,5.204461,5.204461
data_v2/pufa_zh_mc_gen.csv CHANGED
@@ -17,6 +17,8 @@ Yi-34B-Chat,84.0,84.0,88.0,88.0,90.67,92.0,78.67,89.33
17
  Claude-3-Opus,93.24324324324324,93.24324324324324,,,,,,
18
  Deepseek-R1-Distill-Llama-8B,24.324324324324326,24.324324324324326,35.13513513513514,35.13513513513514,79.05405405405405,79.05405405405405,26.351351351351347,26.351351351351347
19
  Deepseek-R1-Distill-Qwen-1.5B,25.0,25.0,22.972972972972975,22.972972972972975,13.513513513513514,13.513513513513514,25.0,25.0
 
 
20
  Deepseek-R1-Distill-Qwen-7B,77.70270270270271,77.70270270270271,81.75675675675676,81.75675675675676,26.351351351351347,26.351351351351347,34.45945945945946,34.45945945945946
21
  Gemma-2B,36.0,36.0,41.33333,41.33333,36.0,36.0,30.66667,30.66667
22
  Gemma-7B,34.66667,34.66667,56.0,56.0,46.66667,46.66667,56.0,56.0
 
17
  Claude-3-Opus,93.24324324324324,93.24324324324324,,,,,,
18
  Deepseek-R1-Distill-Llama-8B,24.324324324324326,24.324324324324326,35.13513513513514,35.13513513513514,79.05405405405405,79.05405405405405,26.351351351351347,26.351351351351347
19
  Deepseek-R1-Distill-Qwen-1.5B,25.0,25.0,22.972972972972975,22.972972972972975,13.513513513513514,13.513513513513514,25.0,25.0
20
+ Deepseek-R1-Distill-Qwen-14B,92.56756756756756,92.56756756756756,,,87.16216216216216,87.16216216216216,,
21
+ Deepseek-R1-Distill-Qwen-32B,95.94594594594595,95.94594594594595,,,95.27027027027026,95.27027027027026,,
22
  Deepseek-R1-Distill-Qwen-7B,77.70270270270271,77.70270270270271,81.75675675675676,81.75675675675676,26.351351351351347,26.351351351351347,34.45945945945946,34.45945945945946
23
  Gemma-2B,36.0,36.0,41.33333,41.33333,36.0,36.0,30.66667,30.66667
24
  Gemma-7B,34.66667,34.66667,56.0,56.0,46.66667,46.66667,56.0,56.0
data_v2/rzy_zh_mc_gen.csv CHANGED
@@ -17,6 +17,8 @@ Yi-34B-Chat,64.45,64.59,67.77,67.36,60.17,60.03,57.68,57.54
17
  Claude-3-Opus,67.64288271089369,67.64288271089369,,,,,,
18
  Deepseek-R1-Distill-Llama-8B,40.965278606371555,40.965278606371555,51.60422383963728,51.60422383963728,44.682615439685,44.682615439685,40.891898341486694,40.891898341486694
19
  Deepseek-R1-Distill-Qwen-1.5B,37.342799188640974,37.342799188640974,35.109175516048204,35.109175516048204,32.75086505190311,32.75086505190311,37.609473809807895,37.609473809807895
 
 
20
  Deepseek-R1-Distill-Qwen-7B,53.8294952869586,53.8294952869586,46.16036272521179,46.16036272521179,47.17217515809569,47.17217515809569,47.62379191027324,47.62379191027324
21
  Gemma-2B,36.37621,36.37621,45.22822,45.22822,33.60996,33.60996,37.75934,37.75934
22
  Gemma-7B,39.41909,39.41909,54.77178,54.77178,42.04703,42.04703,56.70816,56.70816
 
17
  Claude-3-Opus,67.64288271089369,67.64288271089369,,,,,,
18
  Deepseek-R1-Distill-Llama-8B,40.965278606371555,40.965278606371555,51.60422383963728,51.60422383963728,44.682615439685,44.682615439685,40.891898341486694,40.891898341486694
19
  Deepseek-R1-Distill-Qwen-1.5B,37.342799188640974,37.342799188640974,35.109175516048204,35.109175516048204,32.75086505190311,32.75086505190311,37.609473809807895,37.609473809807895
20
+ Deepseek-R1-Distill-Qwen-14B,60.99749433241857,60.99749433241857,,,58.225748717336835,58.225748717336835,,
21
+ Deepseek-R1-Distill-Qwen-32B,69.02696575587639,69.02696575587639,,,67.8988187567116,67.8988187567116,,
22
  Deepseek-R1-Distill-Qwen-7B,53.8294952869586,53.8294952869586,46.16036272521179,46.16036272521179,47.17217515809569,47.17217515809569,47.62379191027324,47.62379191027324
23
  Gemma-2B,36.37621,36.37621,45.22822,45.22822,33.60996,33.60996,37.75934,37.75934
24
  Gemma-7B,39.41909,39.41909,54.77178,54.77178,42.04703,42.04703,56.70816,56.70816
data_v2/zabbix_zh_mc_gen.csv CHANGED
@@ -17,6 +17,8 @@ Yi-34B-Chat,40.0,40.0,40.0,40.0,42.0,42.0,42.0,42.0
17
  Claude-3-Opus,61.71875,61.71875,,,,,,
18
  Deepseek-R1-Distill-Llama-8B,34.89583333333333,34.89583333333333,36.02430555555556,36.02430555555556,25.260416666666664,25.260416666666664,36.63194444444444,36.63194444444444
19
  Deepseek-R1-Distill-Qwen-1.5B,23.4375,23.4375,25.78125,25.78125,16.40625,16.40625,32.11805555555556,32.11805555555556
 
 
20
  Deepseek-R1-Distill-Qwen-7B,25.43402777777778,25.43402777777778,28.993055555555557,28.993055555555557,23.697916666666664,23.697916666666664,32.89930555555556,32.89930555555556
21
  Gemma-2B,25.0,25.0,32.0,32.0,24.0,24.0,30.0,30.0
22
  Gemma-7B,22.0,22.0,44.0,44.0,28.0,28.0,40.0,40.0
 
17
  Claude-3-Opus,61.71875,61.71875,,,,,,
18
  Deepseek-R1-Distill-Llama-8B,34.89583333333333,34.89583333333333,36.02430555555556,36.02430555555556,25.260416666666664,25.260416666666664,36.63194444444444,36.63194444444444
19
  Deepseek-R1-Distill-Qwen-1.5B,23.4375,23.4375,25.78125,25.78125,16.40625,16.40625,32.11805555555556,32.11805555555556
20
+ Deepseek-R1-Distill-Qwen-14B,51.822916666666664,51.822916666666664,,,49.479166666666664,49.479166666666664,,
21
+ Deepseek-R1-Distill-Qwen-32B,58.94097222222222,58.94097222222222,,,58.94097222222222,58.94097222222222,,
22
  Deepseek-R1-Distill-Qwen-7B,25.43402777777778,25.43402777777778,28.993055555555557,28.993055555555557,23.697916666666664,23.697916666666664,32.89930555555556,32.89930555555556
23
  Gemma-2B,25.0,25.0,32.0,32.0,24.0,24.0,30.0,30.0
24
  Gemma-7B,22.0,22.0,44.0,44.0,28.0,28.0,40.0,40.0
data_v2/zjyd_en_mc_gen.csv CHANGED
@@ -12,4 +12,6 @@ Qwen1.5-14B-Chat,,23.21429,,,,78.57142857,80.35714286,83.92857143
12
  JIUTIAN-75B-net,82.4074074074074,82.4074074074074,87.96296296296296,87.96296296296296,84.25925925925925,84.25925925925925,87.96296296296296,87.96296296296296
13
  Deepseek-R1-Distill-Llama-8B,37.03703703703704,37.03703703703704,41.2037037037037,41.2037037037037,22.685185185185187,22.685185185185187,31.01851851851852,31.01851851851852
14
  Deepseek-R1-Distill-Qwen-1.5B,37.03703703703704,37.03703703703704,27.77777777777778,27.77777777777778,15.74074074074074,15.74074074074074,30.09259259259259,30.09259259259259
 
 
15
  Deepseek-R1-Distill-Qwen-7B,22.685185185185187,22.685185185185187,37.5,37.5,21.296296296296298,21.296296296296298,31.944444444444443,31.944444444444443
 
12
  JIUTIAN-75B-net,82.4074074074074,82.4074074074074,87.96296296296296,87.96296296296296,84.25925925925925,84.25925925925925,87.96296296296296,87.96296296296296
13
  Deepseek-R1-Distill-Llama-8B,37.03703703703704,37.03703703703704,41.2037037037037,41.2037037037037,22.685185185185187,22.685185185185187,31.01851851851852,31.01851851851852
14
  Deepseek-R1-Distill-Qwen-1.5B,37.03703703703704,37.03703703703704,27.77777777777778,27.77777777777778,15.74074074074074,15.74074074074074,30.09259259259259,30.09259259259259
15
+ Deepseek-R1-Distill-Qwen-14B,69.44444444444444,69.44444444444444,,,19.90740740740741,19.90740740740741,,
16
+ Deepseek-R1-Distill-Qwen-32B,66.2037037037037,66.2037037037037,,,21.75925925925926,21.75925925925926,,
17
  Deepseek-R1-Distill-Qwen-7B,22.685185185185187,22.685185185185187,37.5,37.5,21.296296296296298,21.296296296296298,31.944444444444443,31.944444444444443
data_v2/zjyd_zh_mc_gen.csv CHANGED
@@ -25,6 +25,8 @@ JIUTIAN-75B-net,80.55555555555556,80.55555555555556,88.88888888888889,88.8888888
25
  Claude-3-Opus,68.05555555555556,68.05555555555556,,,,,,
26
  Deepseek-R1-Distill-Llama-8B,32.407407407407405,32.407407407407405,43.05555555555556,43.05555555555556,37.96296296296296,37.96296296296296,48.61111111111111,48.61111111111111
27
  Deepseek-R1-Distill-Qwen-1.5B,30.555555555555557,30.555555555555557,47.22222222222222,47.22222222222222,38.425925925925924,38.425925925925924,35.648148148148145,35.648148148148145
 
 
28
  Deepseek-R1-Distill-Qwen-7B,49.53703703703704,49.53703703703704,35.648148148148145,35.648148148148145,33.7962962962963,33.7962962962963,61.11111111111111,61.11111111111111
29
  Gemma-2B,25.6,25.6,28.3,28.3,19.1,19.1,35.5,35.5
30
  Gemma-7B,27.3,27.3,35.4,35.4,17.3,17.3,44.5,44.5
 
25
  Claude-3-Opus,68.05555555555556,68.05555555555556,,,,,,
26
  Deepseek-R1-Distill-Llama-8B,32.407407407407405,32.407407407407405,43.05555555555556,43.05555555555556,37.96296296296296,37.96296296296296,48.61111111111111,48.61111111111111
27
  Deepseek-R1-Distill-Qwen-1.5B,30.555555555555557,30.555555555555557,47.22222222222222,47.22222222222222,38.425925925925924,38.425925925925924,35.648148148148145,35.648148148148145
28
+ Deepseek-R1-Distill-Qwen-14B,64.81481481481481,64.81481481481481,,,50.0,50.0,,
29
+ Deepseek-R1-Distill-Qwen-32B,81.94444444444444,81.94444444444444,,,67.5925925925926,67.5925925925926,,
30
  Deepseek-R1-Distill-Qwen-7B,49.53703703703704,49.53703703703704,35.648148148148145,35.648148148148145,33.7962962962963,33.7962962962963,61.11111111111111,61.11111111111111
31
  Gemma-2B,25.6,25.6,28.3,28.3,19.1,19.1,35.5,35.5
32
  Gemma-7B,27.3,27.3,35.4,35.4,17.3,17.3,44.5,44.5
data_v2/zte_en_mc_gen.csv CHANGED
@@ -23,6 +23,8 @@ JIUTIAN-75B-net,56.99999999999999,56.99999999999999,61.4,61.4,56.99999999999999,
23
  Claude-3-Opus,49.599999999999994,49.599999999999994,,,,,,
24
  Deepseek-R1-Distill-Llama-8B,17.6,17.6,31.799999999999997,31.799999999999997,24.099999999999998,24.099999999999998,33.8,33.8
25
  Deepseek-R1-Distill-Qwen-1.5B,19.0,19.0,20.9,20.9,22.700000000000003,22.700000000000003,29.6,29.6
 
 
26
  Deepseek-R1-Distill-Qwen-7B,21.0,21.0,27.0,27.0,26.700000000000003,26.700000000000003,32.4,32.4
27
  Gemma-2B,20.1,20.1,24.2,24.2,31.2,31.2,35.5,35.5
28
  Gemma-7B,23.1,23.1,34.4,34.4,21.4,21.4,33.1,33.1
 
23
  Claude-3-Opus,49.599999999999994,49.599999999999994,,,,,,
24
  Deepseek-R1-Distill-Llama-8B,17.6,17.6,31.799999999999997,31.799999999999997,24.099999999999998,24.099999999999998,33.8,33.8
25
  Deepseek-R1-Distill-Qwen-1.5B,19.0,19.0,20.9,20.9,22.700000000000003,22.700000000000003,29.6,29.6
26
+ Deepseek-R1-Distill-Qwen-14B,35.7,35.7,,,29.6,29.6,,
27
+ Deepseek-R1-Distill-Qwen-32B,57.8,57.8,,,30.9,30.9,,
28
  Deepseek-R1-Distill-Qwen-7B,21.0,21.0,27.0,27.0,26.700000000000003,26.700000000000003,32.4,32.4
29
  Gemma-2B,20.1,20.1,24.2,24.2,31.2,31.2,35.5,35.5
30
  Gemma-7B,23.1,23.1,34.4,34.4,21.4,21.4,33.1,33.1
data_v2/zte_zh_mc_gen.csv CHANGED
@@ -25,6 +25,8 @@ JIUTIAN-75B-net,64.2,64.2,66.60000000000001,66.60000000000001,64.0,64.0,67.80000
25
  Claude-3-Opus,51.4,51.4,,,,,,
26
  Deepseek-R1-Distill-Llama-8B,25.0,25.0,32.1,32.1,30.5,30.5,34.6,34.6
27
  Deepseek-R1-Distill-Qwen-1.5B,28.299999999999997,28.299999999999997,24.6,24.6,23.1,23.1,31.300000000000004,31.300000000000004
 
 
28
  Deepseek-R1-Distill-Qwen-7B,30.900000000000002,30.900000000000002,29.400000000000002,29.400000000000002,32.6,32.6,35.599999999999994,35.599999999999994
29
  Gemma-2B,25.6,25.6,28.3,28.3,19.1,19.1,35.5,35.5
30
  Gemma-7B,27.3,27.3,35.4,35.4,17.3,17.3,44.5,44.5
 
25
  Claude-3-Opus,51.4,51.4,,,,,,
26
  Deepseek-R1-Distill-Llama-8B,25.0,25.0,32.1,32.1,30.5,30.5,34.6,34.6
27
  Deepseek-R1-Distill-Qwen-1.5B,28.299999999999997,28.299999999999997,24.6,24.6,23.1,23.1,31.300000000000004,31.300000000000004
28
+ Deepseek-R1-Distill-Qwen-14B,46.5,46.5,,,52.3,52.3,,
29
+ Deepseek-R1-Distill-Qwen-32B,65.5,65.5,,,67.39999999999999,67.39999999999999,,
30
  Deepseek-R1-Distill-Qwen-7B,30.900000000000002,30.900000000000002,29.400000000000002,29.400000000000002,32.6,32.6,35.599999999999994,35.599999999999994
31
  Gemma-2B,25.6,25.6,28.3,28.3,19.1,19.1,35.5,35.5
32
  Gemma-7B,27.3,27.3,35.4,35.4,17.3,17.3,44.5,44.5