Junetheriver commited on
Commit
97881c0
·
1 Parent(s): 1922969

update leaderboard 2025-01-09

Browse files
data_v2/huaweicloud_en_mc_gen.csv CHANGED
@@ -1,4 +1,4 @@
1
  name,zero_naive,zero_self_con,zero_cot,zero_cot_self_con,few_naive,few_self_con,few_cot,few_cot_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,45.0,45.0,55.00000000000001,55.00000000000001,60.0,60.0,50.0,50.0
 
1
  name,zero_naive,zero_self_con,zero_cot,zero_cot_self_con,few_naive,few_self_con,few_cot,few_cot_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
data_v2/huaweicloud_zh_mc_gen.csv CHANGED
@@ -14,7 +14,7 @@ Mistral-7B,0.0,0.0,23.33,23.33,0.0,0.0,16.67,16.67
14
  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,65.0,65.0,80.0,80.0,50.0,50.0,75.0,75.0
18
  Claude-3-Opus,55.0,55.0,,,,,,
19
  Gemma-2B,26.66667,26.66667,10.0,10.0,26.66667,26.66667,20.0,20.0
20
  Gemma-7B,3.333333,3.333333,23.33333,23.33333,13.33333,13.33333,30.0,30.0
 
14
  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
  Gemma-2B,26.66667,26.66667,10.0,10.0,26.66667,26.66667,20.0,20.0
20
  Gemma-7B,3.333333,3.333333,23.33333,23.33333,13.33333,13.33333,30.0,30.0
data_v2/network_en_mc_gen.csv CHANGED
@@ -21,7 +21,7 @@ Qwen-14B-Chat,43.78,47.81,56.58,59.4,62.09,59.7,49.06,55.88
21
  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,69.38775510204081,69.38775510204081,71.75080558539206,71.75080558539206,72.71750805585391,72.71750805585391,70.99892588614392,70.99892588614392
25
  Claude-3-Opus,69.03417341637355,69.03417341637355,,,,,,
26
  Gemma-2B,26.46048,26.46048,33.41924,33.41924,26.6323,26.6323,37.54296,37.54296
27
  Gemma-7B,25.08591,25.08591,50.85911,50.85911,30.24055,30.24055,51.55747,51.55747
 
21
  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
  Gemma-2B,26.46048,26.46048,33.41924,33.41924,26.6323,26.6323,37.54296,37.54296
27
  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
@@ -24,7 +24,7 @@ Qwen-14B-Chat,48.35,48.81,55.35,57.4,58.53,56.12,52.12,54.99
24
  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,66.38023630504833,66.38023630504833,72.18045112781954,72.18045112781954,67.88399570354457,67.88399570354457,71.32116004296455,71.32116004296455
28
  Claude-3-Opus,62.329525111479995,62.329525111479995,,,,,,
29
  Gemma-2B,29.69019,29.69019,39.15663,39.15663,29.77625,29.77625,38.64028,38.64028
30
  Gemma-7B,31.58348,31.58348,47.59036,47.59036,34.68158,34.68158,48.88124,48.88124
 
24
  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
  Gemma-2B,29.69019,29.69019,39.15663,39.15663,29.77625,29.77625,38.64028,38.64028
30
  Gemma-7B,31.58348,31.58348,47.59036,47.59036,34.68158,34.68158,48.88124,48.88124
data_v2/zjyd_en_mc_gen.csv CHANGED
@@ -9,4 +9,4 @@ Qwen1.5-1.8B-Base,,71.42857,71.42857,71.42857,,70.53571429,80.35714286,80.357142
9
  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,82.4074074074074,82.4074074074074,86.11111111111111,86.11111111111111,84.25925925925925,84.25925925925925,85.18518518518519,85.18518518518519
 
9
  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
data_v2/zjyd_zh_mc_gen.csv CHANGED
@@ -21,7 +21,7 @@ Qwen-14B-Chat,41.71,41.44,45.58,47.98,53.52,49.92,54.72,58.85
21
  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,80.55555555555556,80.55555555555556,90.74074074074075,90.74074074074075,85.18518518518519,85.18518518518519,89.81481481481481,89.81481481481481
25
  Claude-3-Opus,68.05555555555556,68.05555555555556,,,,,,
26
  Gemma-2B,25.6,25.6,28.3,28.3,19.1,19.1,35.5,35.5
27
  Gemma-7B,27.3,27.3,35.4,35.4,17.3,17.3,44.5,44.5
 
21
  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
  Gemma-2B,25.6,25.6,28.3,28.3,19.1,19.1,35.5,35.5
27
  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
@@ -19,7 +19,7 @@ Qwen-14B-Chat,33.71,36.25,41.24,42.51,51.19,50.39,57.18,59.18
19
  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,56.99999999999999,56.99999999999999,57.199999999999996,57.199999999999996,56.99999999999999,56.99999999999999,57.8,57.8
23
  Claude-3-Opus,49.599999999999994,49.599999999999994,,,,,,
24
  Gemma-2B,20.1,20.1,24.2,24.2,31.2,31.2,35.5,35.5
25
  Gemma-7B,23.1,23.1,34.4,34.4,21.4,21.4,33.1,33.1
 
19
  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
  Gemma-2B,20.1,20.1,24.2,24.2,31.2,31.2,35.5,35.5
25
  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
@@ -21,7 +21,7 @@ Qwen-14B-Chat,41.71,41.44,45.58,47.98,53.52,49.92,54.72,58.85
21
  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,64.2,64.2,67.2,67.2,64.0,64.0,66.0,66.0
25
  Claude-3-Opus,51.4,51.4,,,,,,
26
  Gemma-2B,25.6,25.6,28.3,28.3,19.1,19.1,35.5,35.5
27
  Gemma-7B,27.3,27.3,35.4,35.4,17.3,17.3,44.5,44.5
 
21
  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
  Gemma-2B,25.6,25.6,28.3,28.3,19.1,19.1,35.5,35.5
27
  Gemma-7B,27.3,27.3,35.4,35.4,17.3,17.3,44.5,44.5