Junetheriver commited on
Commit
6addf0b
·
1 Parent(s): cd43969

update leaderboard 2025-07-01

Browse files
data_v2/huaweicloud_en_mc_gen.csv CHANGED
@@ -2,6 +2,7 @@ name,zero_naive,zero_self_con,zero_cot,zero_cot_self_con,few_naive,few_self_con,
2
  GPT-3.5-turbo,40.0,40.0,,,55.00000000000001,55.00000000000001,,
3
  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-14B,27.5,27.5,,,25.0,25.0,,
 
2
  GPT-3.5-turbo,40.0,40.0,,,55.00000000000001,55.00000000000001,,
3
  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
+ Chmobile2026,55.00000000000001,55.00000000000001,65.0,65.0,55.00000000000001,55.00000000000001,60.0,60.0
6
  Deepseek-R1-Distill-Llama-8B,7.5,7.5,32.5,32.5,22.5,22.5,27.5,27.5
7
  Deepseek-R1-Distill-Qwen-1.5B,10.0,10.0,12.5,12.5,12.5,12.5,22.5,22.5
8
  Deepseek-R1-Distill-Qwen-14B,27.5,27.5,,,25.0,25.0,,
data_v2/huaweicloud_zh_mc_gen.csv CHANGED
@@ -15,6 +15,7 @@ Qwen-14B-Chat,13.33,13.33,20.0,26.67,40.0,30.0,26.67,33.33
15
  Qwen-72B-Chat,36.67,36.67,33.33,33.33,43.33,43.33,33.33,36.67
16
  Yi-34B-Chat,36.67,40.0,36.67,30.0,50.0,46.67,30.0,43.33
17
  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
 
15
  Qwen-72B-Chat,36.67,36.67,33.33,33.33,43.33,43.33,33.33,36.67
16
  Yi-34B-Chat,36.67,40.0,36.67,30.0,50.0,46.67,30.0,43.33
17
  JIUTIAN-75B-net,65.0,65.0,70.0,70.0,50.0,50.0,75.0,75.0
18
+ Chmobile2026,60.0,60.0,55.00000000000001,55.00000000000001,55.00000000000001,55.00000000000001,55.00000000000001,55.00000000000001
19
  Claude-3-Opus,55.0,55.0,,,,,,
20
  Deepseek-R1-Distill-Llama-8B,10.0,10.0,30.0,30.0,35.0,35.0,27.5,27.5
21
  Deepseek-R1-Distill-Qwen-1.5B,25.0,25.0,5.0,5.0,32.5,32.5,20.0,20.0
data_v2/network_en_mc_gen.csv CHANGED
@@ -22,6 +22,7 @@ Qwen-72B-Chat,70.41,70.5,72.38,72.56,70.32,70.32,70.13,70.22
22
  Qwen-7B-Chat,45.9,46.0,47.3,50.1,52.1,51.0,48.3,49.8
23
  Yi-34B-Chat,57.75,59.14,65.11,68.79,68.16,68.37,78.09,80.06
24
  JIUTIAN-75B-net,69.38775510204081,69.38775510204081,76.04726100966703,76.04726100966703,72.71750805585391,72.71750805585391,76.1546723952739,76.1546723952739
 
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
 
22
  Qwen-7B-Chat,45.9,46.0,47.3,50.1,52.1,51.0,48.3,49.8
23
  Yi-34B-Chat,57.75,59.14,65.11,68.79,68.16,68.37,78.09,80.06
24
  JIUTIAN-75B-net,69.38775510204081,69.38775510204081,76.04726100966703,76.04726100966703,72.71750805585391,72.71750805585391,76.1546723952739,76.1546723952739
25
+ Chmobile2026,74.22126745435015,74.22126745435015,69.92481203007519,69.92481203007519,63.05048335123523,63.05048335123523,74.65091299677766,74.65091299677766
26
  Claude-3-Opus,69.03417341637355,69.03417341637355,,,,,,
27
  Deepseek-R1-Distill-Llama-8B,19.65121264227399,19.65121264227399,44.240352567500906,44.240352567500906,25.932243238384128,25.932243238384128,37.26068697187482,37.26068697187482
28
  Deepseek-R1-Distill-Qwen-1.5B,15.894119111389756,15.894119111389756,20.67346477782439,20.67346477782439,18.523623589937444,18.523623589937444,25.022012419153338,25.022012419153338
data_v2/network_zh_mc_gen.csv CHANGED
@@ -25,6 +25,7 @@ Qwen-72B-Chat,65.77,65.86,68.13,68.3,69.4,69.4,69.99,70.08
25
  Qwen-7B-Chat,29.6,29.9,50.6,53.5,50.4,46.9,46.9,47.7
26
  Yi-34B-Chat,61.61,62.56,68.11,69.75,65.73,65.37,69.88,71.21
27
  JIUTIAN-75B-net,66.38023630504833,66.38023630504833,74.75832438238453,74.75832438238453,67.88399570354457,67.88399570354457,74.43609022556392,74.43609022556392
 
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
 
25
  Qwen-7B-Chat,29.6,29.9,50.6,53.5,50.4,46.9,46.9,47.7
26
  Yi-34B-Chat,61.61,62.56,68.11,69.75,65.73,65.37,69.88,71.21
27
  JIUTIAN-75B-net,66.38023630504833,66.38023630504833,74.75832438238453,74.75832438238453,67.88399570354457,67.88399570354457,74.43609022556392,74.43609022556392
28
+ Chmobile2026,68.52846401718583,68.52846401718583,82.59935553168636,82.59935553168636,66.9172932330827,66.9172932330827,81.203007518797,81.203007518797
29
  Claude-3-Opus,62.329525111479995,62.329525111479995,,,,,,
30
  Deepseek-R1-Distill-Llama-8B,27.380138658334147,27.380138658334147,41.48846141327344,41.48846141327344,32.6123750935781,32.6123750935781,33.60348924258699,33.60348924258699
31
  Deepseek-R1-Distill-Qwen-1.5B,24.732285258601046,24.732285258601046,24.071542492595125,24.071542492595125,20.06151742993848,20.06151742993848,25.47277284119389,25.47277284119389
data_v2/oracle_en_mc_gen.csv CHANGED
@@ -21,6 +21,7 @@ Qwen-14B-Chat,24.95,28.37,33.0,36.62,27.97,28.37,27.97,24.14
21
  Qwen-72B-Chat,47.28,47.48,48.09,48.09,49.7,49.7,43.46,43.66
22
  Qwen-7B-Chat,18.91,19.11,22.13,23.94,26.76,25.55,34.81,33.4
23
  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
 
21
  Qwen-72B-Chat,47.28,47.48,48.09,48.09,49.7,49.7,43.46,43.66
22
  Qwen-7B-Chat,18.91,19.11,22.13,23.94,26.76,25.55,34.81,33.4
23
  Yi-34B-Chat,47.08,48.69,47.08,46.28,58.15,58.35,56.94,58.95
24
+ Chmobile2026,71.49122807017544,71.49122807017544,61.40350877192983,61.40350877192983,19.298245614035086,19.298245614035086,64.47368421052632,64.47368421052632
25
  Claude-3-Opus,48.31816996021653,48.31816996021653,,,,,,
26
  Deepseek-R1-Distill-Llama-8B,13.362518750407617,13.362518750407617,31.26345137937781,31.26345137937781,23.33528989760647,23.33528989760647,32.98441270462401,32.98441270462401
27
  Deepseek-R1-Distill-Qwen-1.5B,15.083480075653819,15.083480075653819,18.153655514250307,18.153655514250307,16.92346572751582,16.92346572751582,24.784777929955,24.784777929955
data_v2/oracle_zh_mc_gen.csv CHANGED
@@ -20,6 +20,7 @@ Qwen-14B-Chat,27.57,27.57,32.39,36.02,40.04,35.41,30.38,33.4
20
  Qwen-72B-Chat,48.29,48.49,49.5,49.7,49.7,49.7,45.27,44.87
21
  Qwen-7B-Chat,18.51,17.71,27.36,28.37,29.78,29.58,33.6,31.79
22
  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
 
20
  Qwen-72B-Chat,48.29,48.49,49.5,49.7,49.7,49.7,45.27,44.87
21
  Qwen-7B-Chat,18.51,17.71,27.36,28.37,29.78,29.58,33.6,31.79
22
  Yi-34B-Chat,49.9,49.3,52.72,53.72,56.34,56.34,51.31,54.33
23
+ Chmobile2026,73.24561403508771,73.24561403508771,78.0701754385965,78.0701754385965,10.087719298245613,10.087719298245613,76.75438596491229,76.75438596491229
24
  Claude-3-Opus,50.00570664579664,50.00570664579664,,,,,,
25
  Deepseek-R1-Distill-Llama-8B,25.90001956564273,25.90001956564273,34.199928259309985,34.199928259309985,29.46096654275093,29.46096654275093,31.583023543990087,31.583023543990087
26
  Deepseek-R1-Distill-Qwen-1.5B,25.54294658579534,25.54294658579534,21.57682775712516,21.57682775712516,20.87083414856845,20.87083414856845,25.67664514445966,25.67664514445966
data_v2/zjyd_en_mc_gen.csv CHANGED
@@ -10,6 +10,7 @@ Qwen1.5-1.8B-Chat,,69.64286,67.85714,77.67857,,66.07142857,68.75,75.0
10
  Qwen1.5-14B-Base,,76.92308,,,,78.63247863,83.03571429,83.03571429
11
  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-14B,69.44444444444444,69.44444444444444,,,19.90740740740741,19.90740740740741,,
 
10
  Qwen1.5-14B-Base,,76.92308,,,,78.63247863,83.03571429,83.03571429
11
  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
+ Chmobile2026,80.55555555555556,80.55555555555556,85.18518518518519,85.18518518518519,75.0,75.0,90.74074074074075,90.74074074074075
14
  Deepseek-R1-Distill-Llama-8B,37.03703703703704,37.03703703703704,41.2037037037037,41.2037037037037,22.685185185185187,22.685185185185187,31.01851851851852,31.01851851851852
15
  Deepseek-R1-Distill-Qwen-1.5B,37.03703703703704,37.03703703703704,27.77777777777778,27.77777777777778,15.74074074074074,15.74074074074074,30.09259259259259,30.09259259259259
16
  Deepseek-R1-Distill-Qwen-14B,69.44444444444444,69.44444444444444,,,19.90740740740741,19.90740740740741,,
data_v2/zjyd_zh_mc_gen.csv CHANGED
@@ -22,6 +22,7 @@ Qwen-72B-Chat,64.79,64.79,65.79,65.72,70.19,70.19,68.31,68.38
22
  Qwen-7B-Chat,36.28,36.5,33.18,33.51,41.58,40.59,31.48,31.46
23
  Yi-34B-Chat,64.91,64.58,62.77,65.51,70.85,70.92,48.77,47.97
24
  JIUTIAN-75B-net,80.55555555555556,80.55555555555556,88.88888888888889,88.88888888888889,85.18518518518519,85.18518518518519,88.88888888888889,88.88888888888889
 
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
 
22
  Qwen-7B-Chat,36.28,36.5,33.18,33.51,41.58,40.59,31.48,31.46
23
  Yi-34B-Chat,64.91,64.58,62.77,65.51,70.85,70.92,48.77,47.97
24
  JIUTIAN-75B-net,80.55555555555556,80.55555555555556,88.88888888888889,88.88888888888889,85.18518518518519,85.18518518518519,88.88888888888889,88.88888888888889
25
+ Chmobile2026,86.11111111111111,86.11111111111111,95.37037037037037,95.37037037037037,81.48148148148148,81.48148148148148,94.44444444444444,94.44444444444444
26
  Claude-3-Opus,68.05555555555556,68.05555555555556,,,,,,
27
  Deepseek-R1-Distill-Llama-8B,32.407407407407405,32.407407407407405,43.05555555555556,43.05555555555556,37.96296296296296,37.96296296296296,48.61111111111111,48.61111111111111
28
  Deepseek-R1-Distill-Qwen-1.5B,30.555555555555557,30.555555555555557,47.22222222222222,47.22222222222222,38.425925925925924,38.425925925925924,35.648148148148145,35.648148148148145
data_v2/zte_en_mc_gen.csv CHANGED
@@ -20,6 +20,7 @@ Qwen-72B-Chat,53.19,53.19,55.25,55.52,58.13,58.13,58.72,58.99
20
  Qwen-7B-Chat,33.37,33.74,32.97,34.1,32.98,32.7,36.6,36.65
21
  Yi-34B-Chat,38.24,37.04,48.24,52.1,61.33,61.19,53.53,53.39
22
  JIUTIAN-75B-net,56.99999999999999,56.99999999999999,61.4,61.4,56.99999999999999,56.99999999999999,55.400000000000006,55.400000000000006
 
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
 
20
  Qwen-7B-Chat,33.37,33.74,32.97,34.1,32.98,32.7,36.6,36.65
21
  Yi-34B-Chat,38.24,37.04,48.24,52.1,61.33,61.19,53.53,53.39
22
  JIUTIAN-75B-net,56.99999999999999,56.99999999999999,61.4,61.4,56.99999999999999,56.99999999999999,55.400000000000006,55.400000000000006
23
+ Chmobile2026,63.6,63.6,61.8,61.8,61.4,61.4,63.0,63.0
24
  Claude-3-Opus,49.599999999999994,49.599999999999994,,,,,,
25
  Deepseek-R1-Distill-Llama-8B,17.6,17.6,31.799999999999997,31.799999999999997,24.099999999999998,24.099999999999998,33.8,33.8
26
  Deepseek-R1-Distill-Qwen-1.5B,19.0,19.0,20.9,20.9,22.700000000000003,22.700000000000003,29.6,29.6
data_v2/zte_zh_mc_gen.csv CHANGED
@@ -22,6 +22,7 @@ Qwen-72B-Chat,64.79,64.79,65.79,65.72,70.19,70.19,68.31,68.38
22
  Qwen-7B-Chat,36.28,36.5,33.18,33.51,41.58,40.59,31.48,31.46
23
  Yi-34B-Chat,64.91,64.58,62.77,65.51,70.85,70.92,48.77,47.97
24
  JIUTIAN-75B-net,64.2,64.2,66.60000000000001,66.60000000000001,64.0,64.0,67.80000000000001,67.80000000000001
 
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
 
22
  Qwen-7B-Chat,36.28,36.5,33.18,33.51,41.58,40.59,31.48,31.46
23
  Yi-34B-Chat,64.91,64.58,62.77,65.51,70.85,70.92,48.77,47.97
24
  JIUTIAN-75B-net,64.2,64.2,66.60000000000001,66.60000000000001,64.0,64.0,67.80000000000001,67.80000000000001
25
+ Chmobile2026,67.80000000000001,67.80000000000001,76.6,76.6,67.60000000000001,67.60000000000001,75.8,75.8
26
  Claude-3-Opus,51.4,51.4,,,,,,
27
  Deepseek-R1-Distill-Llama-8B,25.0,25.0,32.1,32.1,30.5,30.5,34.6,34.6
28
  Deepseek-R1-Distill-Qwen-1.5B,28.299999999999997,28.299999999999997,24.6,24.6,23.1,23.1,31.300000000000004,31.300000000000004