Spaces:
Running
Running
Commit
·
86c7e49
1
Parent(s):
463d129
update leaderboard 2024-12-19
Browse files- data_v2/bosc_zh_mc_gen.csv +3 -3
- data_v2/dfcdata_zh_mc_gen.csv +3 -3
- data_v2/gtja_zh_mc_gen.csv +3 -3
- data_v2/huaweicloud_en_mc_gen.csv +4 -0
- data_v2/huaweicloud_zh_mc_gen.csv +4 -3
- data_v2/lenovo_en_mc_gen.csv +2 -2
- data_v2/lenovo_zh_mc_gen.csv +1 -1
- data_v2/network_en_mc_gen.csv +3 -2
- data_v2/network_zh_mc_gen.csv +3 -2
- data_v2/oracle_en_mc_gen.csv +2 -2
- data_v2/oracle_zh_mc_gen.csv +2 -2
- data_v2/pufa_zh_mc_gen.csv +3 -3
- data_v2/rzy_zh_mc_gen.csv +3 -3
- data_v2/zabbix_zh_mc_gen.csv +3 -3
- data_v2/zjyd_en_mc_gen.csv +12 -0
- data_v2/zjyd_zh_mc_gen.csv +3 -2
- data_v2/zte_en_mc_gen.csv +3 -2
- data_v2/zte_zh_mc_gen.csv +3 -2
- leaderboards.py +6 -3
data_v2/bosc_zh_mc_gen.csv
CHANGED
@@ -4,7 +4,7 @@ ChatGLM3-6B,35.0,35.0,50.0,50.0,47.5,47.5,45.0,45.0
|
|
4 |
DevOps-Model-14B-Chat,35.0,27.5,37.5,52.5,50.0,50.0,55.0,62.5
|
5 |
ERNIE-Bot-4.0,57.5,57.5,60.0,60.0,52.5,52.5,57.5,57.5
|
6 |
GPT-3.5-turbo,50.0,47.5,55.0,55.0,40.0,40.0,50.0,55.0
|
7 |
-
|
8 |
InternLM2-Chat-20B,47.5,47.5,,,47.5,47.5,,
|
9 |
InternLM2-Chat-7B,60.0,60.0,57.5,57.5,55.0,55.0,62.5,62.5
|
10 |
LLaMA-2-13B,42.5,42.5,50.0,50.0,50.0,50.0,42.5,42.5
|
@@ -15,8 +15,8 @@ Qwen-14B-Chat,47.5,45.0,50.0,47.5,50.0,47.5,55.0,57.5
|
|
15 |
Qwen-72B-Chat,50.0,50.0,47.5,47.5,45.0,45.0,60.0,60.0
|
16 |
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 |
-
|
19 |
-
|
20 |
Meta-Llama-3-8B-Instruct,52.85714285714286,52.85714285714286,47.14285714285714,47.14285714285714,52.85714285714286,52.85714285714286,30.0,30.0
|
21 |
Qwen1.5-14B-Base,47.5,47.5,50.0,50.0,47.5,47.5,45.0,45.0
|
22 |
Qwen1.5-14B-Chat,45.0,47.5,60.0,72.5,52.5,55.0,60.0,60.0
|
|
|
4 |
DevOps-Model-14B-Chat,35.0,27.5,37.5,52.5,50.0,50.0,55.0,62.5
|
5 |
ERNIE-Bot-4.0,57.5,57.5,60.0,60.0,52.5,52.5,57.5,57.5
|
6 |
GPT-3.5-turbo,50.0,47.5,55.0,55.0,40.0,40.0,50.0,55.0
|
7 |
+
GPT-4,57.5,57.5,57.5,57.5,52.5,52.5,62.5,62.5
|
8 |
InternLM2-Chat-20B,47.5,47.5,,,47.5,47.5,,
|
9 |
InternLM2-Chat-7B,60.0,60.0,57.5,57.5,55.0,55.0,62.5,62.5
|
10 |
LLaMA-2-13B,42.5,42.5,50.0,50.0,50.0,50.0,42.5,42.5
|
|
|
15 |
Qwen-72B-Chat,50.0,50.0,47.5,47.5,45.0,45.0,60.0,60.0
|
16 |
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 |
+
Gemma-2B,37.5,37.5,40.0,40.0,32.5,32.5,40.0,40.0
|
19 |
+
Gemma-7B,32.5,32.5,62.5,62.5,40.0,40.0,50.0,50.0
|
20 |
Meta-Llama-3-8B-Instruct,52.85714285714286,52.85714285714286,47.14285714285714,47.14285714285714,52.85714285714286,52.85714285714286,30.0,30.0
|
21 |
Qwen1.5-14B-Base,47.5,47.5,50.0,50.0,47.5,47.5,45.0,45.0
|
22 |
Qwen1.5-14B-Chat,45.0,47.5,60.0,72.5,52.5,55.0,60.0,60.0
|
data_v2/dfcdata_zh_mc_gen.csv
CHANGED
@@ -4,7 +4,7 @@ ChatGLM3-6B,55.63380282,55.63380282,61.97183099,61.97183099,51.4084507,51.408450
|
|
4 |
DevOps-Model-14B-Chat,33.8,34.51,54.23,56.34,80.99,78.87,51.41,63.38
|
5 |
ERNIE-Bot-4.0,81.0,81.0,82.0,82.0,83.0,83.0,85.0,85.0
|
6 |
GPT-3.5-turbo,77.46,76.06,82.39,81.69,71.13,73.24,80.28,78.87
|
7 |
-
|
8 |
InternLM2-Chat-20B,74.64788732,74.64788732,74.64788732,74.64788732,78.16901408,78.16901408,,
|
9 |
InternLM2-Chat-7B,76.05633803,76.05633803,73.94366197,73.94366197,74.64788732,74.64788732,57.04225352,57.04225352
|
10 |
LLaMA-2-13B,45.77,45.77,70.42,70.42,61.97,61.97,61.27,61.27
|
@@ -14,7 +14,7 @@ Mistral-7B,2.82,2.82,64.79,64.79,16.9,16.9,64.08,64.08
|
|
14 |
Qwen-14B-Chat,73.94,73.94,73.24,76.76,76.06,74.65,69.01,71.83
|
15 |
Qwen-72B-Chat,86.62,86.62,83.8,83.8,83.8,83.8,83.8,83.8
|
16 |
Yi-34B-Chat,78.87,80.28,85.92,86.62,86.62,86.62,76.06,85.21
|
17 |
-
|
18 |
-
|
19 |
Qwen1.5-14B-Base,73.23944,73.23944,76.05634,76.05634,81.69014,81.69014,57.04225,57.04225
|
20 |
Qwen1.5-14B-Chat,75.35211,76.05634,80.28169,83.09859,83.80282,80.98592,78.87324,80.98592
|
|
|
4 |
DevOps-Model-14B-Chat,33.8,34.51,54.23,56.34,80.99,78.87,51.41,63.38
|
5 |
ERNIE-Bot-4.0,81.0,81.0,82.0,82.0,83.0,83.0,85.0,85.0
|
6 |
GPT-3.5-turbo,77.46,76.06,82.39,81.69,71.13,73.24,80.28,78.87
|
7 |
+
GPT-4,85.21,85.21,86.62,86.62,82.39,82.39,90.14,90.14
|
8 |
InternLM2-Chat-20B,74.64788732,74.64788732,74.64788732,74.64788732,78.16901408,78.16901408,,
|
9 |
InternLM2-Chat-7B,76.05633803,76.05633803,73.94366197,73.94366197,74.64788732,74.64788732,57.04225352,57.04225352
|
10 |
LLaMA-2-13B,45.77,45.77,70.42,70.42,61.97,61.97,61.27,61.27
|
|
|
14 |
Qwen-14B-Chat,73.94,73.94,73.24,76.76,76.06,74.65,69.01,71.83
|
15 |
Qwen-72B-Chat,86.62,86.62,83.8,83.8,83.8,83.8,83.8,83.8
|
16 |
Yi-34B-Chat,78.87,80.28,85.92,86.62,86.62,86.62,76.06,85.21
|
17 |
+
Gemma-2B,28.16901,28.16901,38.02817,38.02817,27.46479,27.46479,41.5493,41.5493
|
18 |
+
Gemma-7B,35.91549,35.91549,59.15493,59.15493,50.70423,50.70423,66.90141,66.90141
|
19 |
Qwen1.5-14B-Base,73.23944,73.23944,76.05634,76.05634,81.69014,81.69014,57.04225,57.04225
|
20 |
Qwen1.5-14B-Chat,75.35211,76.05634,80.28169,83.09859,83.80282,80.98592,78.87324,80.98592
|
data_v2/gtja_zh_mc_gen.csv
CHANGED
@@ -4,7 +4,7 @@ ChatGLM3-6B,43.95604396,43.95604396,53.84615385,53.84615385,43.95604396,43.95604
|
|
4 |
DevOps-Model-14B-Chat,41.76,38.46,45.05,49.45,61.54,59.34,52.75,63.74
|
5 |
ERNIE-Bot-4.0,68.13,68.13,64.84,64.84,65.93,65.93,68.13,68.13
|
6 |
GPT-3.5-turbo,49.45,52.75,59.34,62.64,47.25,52.75,57.14,58.24
|
7 |
-
|
8 |
InternLM2-Chat-20B,56.04395604,56.04395604,,,65.93406593,65.93406593,,
|
9 |
InternLM2-Chat-7B,56.04395604,56.04395604,59.34065934,59.34065934,54.94505495,54.94505495,51.64835165,51.64835165
|
10 |
LLaMA-2-13B,30.77,30.77,47.25,47.25,47.25,47.25,42.86,42.86
|
@@ -15,8 +15,8 @@ Qwen-14B-Chat,47.25,47.25,53.85,54.95,54.95,54.95,59.34,61.54
|
|
15 |
Qwen-72B-Chat,71.43,71.43,67.03,67.03,70.33,70.33,74.73,74.73
|
16 |
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 |
-
|
19 |
-
|
20 |
Meta-Llama-3-8B-Instruct,36.550632911392405,36.550632911392405,38.08016877637131,38.08016877637131,43.24894514767932,43.24894514767932,34.28270042194093,34.28270042194093
|
21 |
Qwen1.5-14B-Base,53.84615,53.84615,63.73626,63.73626,68.13187,68.13187,42.85714,42.85714
|
22 |
Qwen1.5-14B-Chat,56.04396,54.94505,67.03297,68.13187,59.34066,57.14286,60.43956,62.63736
|
|
|
4 |
DevOps-Model-14B-Chat,41.76,38.46,45.05,49.45,61.54,59.34,52.75,63.74
|
5 |
ERNIE-Bot-4.0,68.13,68.13,64.84,64.84,65.93,65.93,68.13,68.13
|
6 |
GPT-3.5-turbo,49.45,52.75,59.34,62.64,47.25,52.75,57.14,58.24
|
7 |
+
GPT-4,68.13,68.13,67.03,67.03,70.33,70.33,71.43,71.43
|
8 |
InternLM2-Chat-20B,56.04395604,56.04395604,,,65.93406593,65.93406593,,
|
9 |
InternLM2-Chat-7B,56.04395604,56.04395604,59.34065934,59.34065934,54.94505495,54.94505495,51.64835165,51.64835165
|
10 |
LLaMA-2-13B,30.77,30.77,47.25,47.25,47.25,47.25,42.86,42.86
|
|
|
15 |
Qwen-72B-Chat,71.43,71.43,67.03,67.03,70.33,70.33,74.73,74.73
|
16 |
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 |
+
Gemma-2B,30.76923,30.76923,43.95604,43.95604,32.96703,32.96703,29.67033,29.67033
|
19 |
+
Gemma-7B,29.67033,29.67033,56.04396,56.04396,34.06593,34.06593,50.54945,50.54945
|
20 |
Meta-Llama-3-8B-Instruct,36.550632911392405,36.550632911392405,38.08016877637131,38.08016877637131,43.24894514767932,43.24894514767932,34.28270042194093,34.28270042194093
|
21 |
Qwen1.5-14B-Base,53.84615,53.84615,63.73626,63.73626,68.13187,68.13187,42.85714,42.85714
|
22 |
Qwen1.5-14B-Chat,56.04396,54.94505,67.03297,68.13187,59.34066,57.14286,60.43956,62.63736
|
data_v2/huaweicloud_en_mc_gen.csv
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
name,zero_naive,zero_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
|
data_v2/huaweicloud_zh_mc_gen.csv
CHANGED
@@ -4,7 +4,7 @@ ChatGLM3-6B,13.33333333,13.33333333,16.66666667,16.66666667,6.666666667,6.666666
|
|
4 |
DevOps-Model-14B-Chat,16.67,16.67,33.33,13.33,40.0,40.0,20.0,23.33
|
5 |
ERNIE-Bot-4.0,16.67,16.67,20.0,20.0,36.67,36.67,23.33,23.33
|
6 |
GPT-3.5-turbo,13.33,13.33,20.0,26.67,20.0,20.0,16.67,23.33
|
7 |
-
|
8 |
InternLM2-Chat-20B,13.33333333,13.33333333,20.0,20.0,16.66666667,16.66666667,,
|
9 |
InternLM2-Chat-7B,43.33333333,43.33333333,23.33333333,23.33333333,30.0,30.0,40.0,40.0
|
10 |
LLaMA-2-13B,10.0,10.0,20.0,20.0,26.67,26.67,13.33,13.33
|
@@ -14,9 +14,10 @@ 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 |
Claude-3-Opus,55.0,55.0,,,,,,
|
18 |
-
|
19 |
-
|
20 |
Meta-Llama-3-8B-Instruct,27.5,27.5,22.5,22.5,30.0,30.0,30.0,30.0
|
21 |
Qwen1.5-14B-Base,20.0,20.0,33.33333,33.33333,20.0,20.0,30.0,30.0
|
22 |
Qwen1.5-14B-Chat,23.33333,26.66667,13.33333,13.33333,26.66667,26.66667,20.0,30.0
|
|
|
4 |
DevOps-Model-14B-Chat,16.67,16.67,33.33,13.33,40.0,40.0,20.0,23.33
|
5 |
ERNIE-Bot-4.0,16.67,16.67,20.0,20.0,36.67,36.67,23.33,23.33
|
6 |
GPT-3.5-turbo,13.33,13.33,20.0,26.67,20.0,20.0,16.67,23.33
|
7 |
+
GPT-4,20.0,20.0,20.0,20.0,43.33,43.33,46.67,46.67
|
8 |
InternLM2-Chat-20B,13.33333333,13.33333333,20.0,20.0,16.66666667,16.66666667,,
|
9 |
InternLM2-Chat-7B,43.33333333,43.33333333,23.33333333,23.33333333,30.0,30.0,40.0,40.0
|
10 |
LLaMA-2-13B,10.0,10.0,20.0,20.0,26.67,26.67,13.33,13.33
|
|
|
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,,,50.0,50.0,,
|
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
|
21 |
Meta-Llama-3-8B-Instruct,27.5,27.5,22.5,22.5,30.0,30.0,30.0,30.0
|
22 |
Qwen1.5-14B-Base,20.0,20.0,33.33333,33.33333,20.0,20.0,30.0,30.0
|
23 |
Qwen1.5-14B-Chat,23.33333,26.66667,13.33333,13.33333,26.66667,26.66667,20.0,30.0
|
data_v2/lenovo_en_mc_gen.csv
CHANGED
@@ -2,7 +2,7 @@ name,zero_naive,zero_self_con,zero_cot,zero_cot_self_con,few_naive,few_self_con,
|
|
2 |
ChatGLM3-6B,60.0,60.0,60.0,60.0,55.0,55.0,60.0,60.0
|
3 |
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 |
-
|
6 |
-
|
7 |
Qwen1.5-14B-Base,67.5,67.5,70.0,70.0,72.5,72.5,50.0,50.0
|
8 |
Qwen1.5-14B-Chat,67.5,67.5,70.0,70.0,72.5,65.0,77.5,77.5
|
|
|
2 |
ChatGLM3-6B,60.0,60.0,60.0,60.0,55.0,55.0,60.0,60.0
|
3 |
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 |
+
Gemma-2B,22.5,22.5,47.5,47.5,30.0,30.0,37.5,37.5
|
6 |
+
Gemma-7B,32.5,32.5,65.0,65.0,35.0,35.0,65.0,65.0
|
7 |
Qwen1.5-14B-Base,67.5,67.5,70.0,70.0,72.5,72.5,50.0,50.0
|
8 |
Qwen1.5-14B-Chat,67.5,67.5,70.0,70.0,72.5,65.0,77.5,77.5
|
data_v2/lenovo_zh_mc_gen.csv
CHANGED
@@ -4,7 +4,7 @@ ChatGLM3-6B,60.0,60.0,60.0,60.0,55.0,55.0,60.0,60.0
|
|
4 |
DevOps-Model-14B-Chat,60.0,67.5,65.0,57.5,67.5,70.0,62.5,70.0
|
5 |
ERNIE-Bot-4.0,75.0,75.0,77.5,77.5,75.0,75.0,82.5,82.5
|
6 |
GPT-3.5-turbo,60.0,62.5,65.0,70.0,57.5,57.5,62.5,62.5
|
7 |
-
|
8 |
LLaMA-2-13B,45.0,45.0,62.5,62.5,60.0,60.0,55.0,55.0
|
9 |
LLaMA-2-70B-Chat,22.5,22.5,75.0,75.0,20.0,20.0,57.5,57.5
|
10 |
LLaMA-2-7B,32.5,32.5,45.0,45.0,60.0,60.0,55.0,55.0
|
|
|
4 |
DevOps-Model-14B-Chat,60.0,67.5,65.0,57.5,67.5,70.0,62.5,70.0
|
5 |
ERNIE-Bot-4.0,75.0,75.0,77.5,77.5,75.0,75.0,82.5,82.5
|
6 |
GPT-3.5-turbo,60.0,62.5,65.0,70.0,57.5,57.5,62.5,62.5
|
7 |
+
GPT-4,77.5,77.5,82.5,82.5,77.5,77.5,82.5,82.5
|
8 |
LLaMA-2-13B,45.0,45.0,62.5,62.5,60.0,60.0,55.0,55.0
|
9 |
LLaMA-2-70B-Chat,22.5,22.5,75.0,75.0,20.0,20.0,57.5,57.5
|
10 |
LLaMA-2-7B,32.5,32.5,45.0,45.0,60.0,60.0,55.0,55.0
|
data_v2/network_en_mc_gen.csv
CHANGED
@@ -21,9 +21,10 @@ 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 |
Claude-3-Opus,69.03417341637355,69.03417341637355,,,,,,
|
25 |
-
|
26 |
-
|
27 |
Meta-Llama-3-8B-Instruct,38.279481659390655,38.279481659390655,76.69172932330827,76.69172932330827,23.734458771084668,23.734458771084668,33.241749376506874,33.241749376506874
|
28 |
Qwen1.5-14B-Base,34.87973,34.87973,60.82474,60.82474,65.54983,65.54983,47.07904,47.07904
|
29 |
Qwen1.5-14B-Chat,54.89691,56.4433,64.08935,67.09622,52.23368,53.52234,59.53608,64.17526
|
|
|
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,,,72.71750805585391,72.71750805585391,,
|
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
|
28 |
Meta-Llama-3-8B-Instruct,38.279481659390655,38.279481659390655,76.69172932330827,76.69172932330827,23.734458771084668,23.734458771084668,33.241749376506874,33.241749376506874
|
29 |
Qwen1.5-14B-Base,34.87973,34.87973,60.82474,60.82474,65.54983,65.54983,47.07904,47.07904
|
30 |
Qwen1.5-14B-Chat,54.89691,56.4433,64.08935,67.09622,52.23368,53.52234,59.53608,64.17526
|
data_v2/network_zh_mc_gen.csv
CHANGED
@@ -24,9 +24,10 @@ 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 |
Claude-3-Opus,62.329525111479995,62.329525111479995,,,,,,
|
28 |
-
|
29 |
-
|
30 |
Meta-Llama-3-8B-Instruct,35.904696806952444,35.904696806952444,38.94801939914722,38.94801939914722,41.717931191615406,41.717931191615406,31.059792337987826,31.059792337987826
|
31 |
Qwen1.5-14B-Base,45.18072,45.18072,59.1222,59.1222,61.10155,61.10155,52.4957,52.4957
|
32 |
Qwen1.5-14B-Chat,54.04475,53.87263,62.56454,63.85542,58.77797,58.0895,63.42513,65.57659
|
|
|
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,,,67.88399570354457,67.88399570354457,,
|
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
|
31 |
Meta-Llama-3-8B-Instruct,35.904696806952444,35.904696806952444,38.94801939914722,38.94801939914722,41.717931191615406,41.717931191615406,31.059792337987826,31.059792337987826
|
32 |
Qwen1.5-14B-Base,45.18072,45.18072,59.1222,59.1222,61.10155,61.10155,52.4957,52.4957
|
33 |
Qwen1.5-14B-Chat,54.04475,53.87263,62.56454,63.85542,58.77797,58.0895,63.42513,65.57659
|
data_v2/oracle_en_mc_gen.csv
CHANGED
@@ -22,8 +22,8 @@ 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 |
-
|
26 |
-
|
27 |
Meta-Llama-3-8B-Instruct,28.468825409248026,28.468825409248026,40.47805387073632,40.47805387073632,23.33528989760647,23.33528989760647,34.6197743429205,34.6197743429205
|
28 |
Qwen1.5-14B-Base,29.17505,29.17505,33.60161,33.60161,36.82093,36.82093,27.7666,27.7666
|
29 |
Qwen1.5-14B-Chat,32.79678,35.41247,39.43662,43.05835,32.39437,33.60161,36.82093,38.833
|
|
|
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 |
+
Gemma-2B,16.90141,16.90141,19.5171,19.5171,16.09658,16.09658,24.74849,24.74849
|
26 |
+
Gemma-7B,14.28571,14.28571,30.98592,30.98592,2.60223,2.60223,43.85965,43.85965
|
27 |
Meta-Llama-3-8B-Instruct,28.468825409248026,28.468825409248026,40.47805387073632,40.47805387073632,23.33528989760647,23.33528989760647,34.6197743429205,34.6197743429205
|
28 |
Qwen1.5-14B-Base,29.17505,29.17505,33.60161,33.60161,36.82093,36.82093,27.7666,27.7666
|
29 |
Qwen1.5-14B-Chat,32.79678,35.41247,39.43662,43.05835,32.39437,33.60161,36.82093,38.833
|
data_v2/oracle_zh_mc_gen.csv
CHANGED
@@ -21,8 +21,8 @@ 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 |
-
|
25 |
-
|
26 |
Hisense,42.6270136307311,43.645733955881,43.228657144720536,45.1016345740917,37.94267266679711,38.257319271049425,45.94991195460771,46.49883899708
|
27 |
Meta-Llama-3-8B-Instruct,33.91785690993282,33.91785690993282,27.773429857170807,27.773429857170807,41.359323028761494,41.359323028761494,32.62733972477663,32.62733972477663
|
28 |
Qwen1.5-14B-Base,20.92555,20.92555,35.61368,35.61368,41.44869,41.44869,30.78471,30.78471
|
|
|
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 |
+
Gemma-2B,18.51107,18.51107,24.9497,24.9497,21.52918,21.52918,27.7666,27.7666
|
25 |
+
Gemma-7B,19.3159,19.3159,53.94737,53.94737,18.51107,18.51107,5.204461,5.204461
|
26 |
Hisense,42.6270136307311,43.645733955881,43.228657144720536,45.1016345740917,37.94267266679711,38.257319271049425,45.94991195460771,46.49883899708
|
27 |
Meta-Llama-3-8B-Instruct,33.91785690993282,33.91785690993282,27.773429857170807,27.773429857170807,41.359323028761494,41.359323028761494,32.62733972477663,32.62733972477663
|
28 |
Qwen1.5-14B-Base,20.92555,20.92555,35.61368,35.61368,41.44869,41.44869,30.78471,30.78471
|
data_v2/pufa_zh_mc_gen.csv
CHANGED
@@ -4,7 +4,7 @@ ChatGLM3-6B,60.0,60.0,61.33333333,61.33333333,56.0,56.0,58.66666667,58.66666667
|
|
4 |
DevOps-Model-14B-Chat,29.33,29.33,62.67,61.33,82.67,81.33,53.33,70.67
|
5 |
ERNIE-Bot-4.0,86.67,86.67,86.67,86.67,82.67,82.67,86.67,86.67
|
6 |
GPT-3.5-turbo,77.33,77.33,84.0,81.33,76.0,78.67,84.0,82.67
|
7 |
-
|
8 |
InternLM2-Chat-20B,76.0,76.0,80.0,80.0,80.0,80.0,,
|
9 |
InternLM2-Chat-7B,78.66666667,78.66666667,72.0,72.0,72.0,72.0,53.33333333,53.33333333
|
10 |
LLaMA-2-13B,44.0,44.0,68.0,68.0,61.33,61.33,53.33,53.33
|
@@ -15,8 +15,8 @@ Qwen-14B-Chat,73.33,73.33,69.33,72.0,73.33,73.33,72.0,80.0
|
|
15 |
Qwen-72B-Chat,90.67,90.67,85.33,85.33,88.0,88.0,82.67,82.67
|
16 |
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 |
-
|
19 |
-
|
20 |
Hisense,92.56756756756756,93.36486486468645,93.91891891891892,94.2410479339064,93.91891891891892,94.5147428741915,93.91891891891892,94.08436728447799
|
21 |
Meta-Llama-3-8B-Instruct,85.8108108108108,85.8108108108108,31.756756756756754,31.756756756756754,83.1081081081081,83.1081081081081,27.7027027027027,27.7027027027027
|
22 |
Qwen1.5-14B-Base,78.66667,78.66667,72.0,72.0,92.0,92.0,42.66667,42.66667
|
|
|
4 |
DevOps-Model-14B-Chat,29.33,29.33,62.67,61.33,82.67,81.33,53.33,70.67
|
5 |
ERNIE-Bot-4.0,86.67,86.67,86.67,86.67,82.67,82.67,86.67,86.67
|
6 |
GPT-3.5-turbo,77.33,77.33,84.0,81.33,76.0,78.67,84.0,82.67
|
7 |
+
GPT-4,88.0,88.0,86.67,86.67,84.0,84.0,90.67,90.67
|
8 |
InternLM2-Chat-20B,76.0,76.0,80.0,80.0,80.0,80.0,,
|
9 |
InternLM2-Chat-7B,78.66666667,78.66666667,72.0,72.0,72.0,72.0,53.33333333,53.33333333
|
10 |
LLaMA-2-13B,44.0,44.0,68.0,68.0,61.33,61.33,53.33,53.33
|
|
|
15 |
Qwen-72B-Chat,90.67,90.67,85.33,85.33,88.0,88.0,82.67,82.67
|
16 |
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 |
+
Gemma-2B,36.0,36.0,41.33333,41.33333,36.0,36.0,30.66667,30.66667
|
19 |
+
Gemma-7B,34.66667,34.66667,56.0,56.0,46.66667,46.66667,56.0,56.0
|
20 |
Hisense,92.56756756756756,93.36486486468645,93.91891891891892,94.2410479339064,93.91891891891892,94.5147428741915,93.91891891891892,94.08436728447799
|
21 |
Meta-Llama-3-8B-Instruct,85.8108108108108,85.8108108108108,31.756756756756754,31.756756756756754,83.1081081081081,83.1081081081081,27.7027027027027,27.7027027027027
|
22 |
Qwen1.5-14B-Base,78.66667,78.66667,72.0,72.0,92.0,92.0,42.66667,42.66667
|
data_v2/rzy_zh_mc_gen.csv
CHANGED
@@ -4,7 +4,7 @@ ChatGLM3-6B,54.21853389,54.21853389,62.10235131,62.10235131,55.32503458,55.32503
|
|
4 |
DevOps-Model-14B-Chat,53.67,56.85,54.5,59.2,65.28,64.18,55.19,61.83
|
5 |
ERNIE-Bot-4.0,76.0,76.0,79.0,79.0,73.0,73.0,77.0,77.0
|
6 |
GPT-3.5-turbo,65.28,65.42,66.39,67.5,65.28,66.25,68.05,68.74
|
7 |
-
|
8 |
InternLM2-Chat-20B,63.90041494,63.90041494,64.03872752,64.03872752,,,,
|
9 |
InternLM2-Chat-7B,61.2724758,61.2724758,63.62378976,63.62378976,65.00691563,65.00691563,54.21853389,54.21853389
|
10 |
LLaMA-2-13B,51.18,51.18,59.06,59.06,57.12,57.12,53.39,53.39
|
@@ -15,8 +15,8 @@ Qwen-14B-Chat,61.96,61.55,61.55,64.45,65.28,63.49,62.93,65.98
|
|
15 |
Qwen-72B-Chat,66.67,66.67,65.28,65.28,65.98,65.98,70.12,70.12
|
16 |
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 |
-
|
19 |
-
|
20 |
Meta-Llama-3-8B-Instruct,36.55172413793103,36.55172413793103,28.27586206896552,28.27586206896552,38.62068965517241,38.62068965517241,34.48275862068966,34.48275862068966
|
21 |
Qwen1.5-14B-Base,51.17566,51.17566,62.6556,62.6556,65.42185,65.42185,50.89903,50.89903
|
22 |
Qwen1.5-14B-Chat,62.93223,64.03873,64.59198,64.31535,63.34716,63.7621,65.42185,65.9751
|
|
|
4 |
DevOps-Model-14B-Chat,53.67,56.85,54.5,59.2,65.28,64.18,55.19,61.83
|
5 |
ERNIE-Bot-4.0,76.0,76.0,79.0,79.0,73.0,73.0,77.0,77.0
|
6 |
GPT-3.5-turbo,65.28,65.42,66.39,67.5,65.28,66.25,68.05,68.74
|
7 |
+
GPT-4,65.56,65.56,68.05,68.05,65.28,65.28,68.19,68.19
|
8 |
InternLM2-Chat-20B,63.90041494,63.90041494,64.03872752,64.03872752,,,,
|
9 |
InternLM2-Chat-7B,61.2724758,61.2724758,63.62378976,63.62378976,65.00691563,65.00691563,54.21853389,54.21853389
|
10 |
LLaMA-2-13B,51.18,51.18,59.06,59.06,57.12,57.12,53.39,53.39
|
|
|
15 |
Qwen-72B-Chat,66.67,66.67,65.28,65.28,65.98,65.98,70.12,70.12
|
16 |
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 |
+
Gemma-2B,36.37621,36.37621,45.22822,45.22822,33.60996,33.60996,37.75934,37.75934
|
19 |
+
Gemma-7B,39.41909,39.41909,54.77178,54.77178,42.04703,42.04703,56.70816,56.70816
|
20 |
Meta-Llama-3-8B-Instruct,36.55172413793103,36.55172413793103,28.27586206896552,28.27586206896552,38.62068965517241,38.62068965517241,34.48275862068966,34.48275862068966
|
21 |
Qwen1.5-14B-Base,51.17566,51.17566,62.6556,62.6556,65.42185,65.42185,50.89903,50.89903
|
22 |
Qwen1.5-14B-Chat,62.93223,64.03873,64.59198,64.31535,63.34716,63.7621,65.42185,65.9751
|
data_v2/zabbix_zh_mc_gen.csv
CHANGED
@@ -4,7 +4,7 @@ ChatGLM3-6B,29.0,29.0,36.0,36.0,29.0,29.0,34.0,34.0
|
|
4 |
DevOps-Model-14B-Chat,27.0,28.0,36.0,33.0,46.0,44.0,44.0,46.0
|
5 |
ERNIE-Bot-4.0,44.0,44.0,48.0,48.0,47.0,47.0,51.0,51.0
|
6 |
GPT-3.5-turbo,36.0,36.0,42.0,42.0,40.0,40.0,48.0,48.0
|
7 |
-
|
8 |
InternLM2-Chat-20B,41.0,41.0,,,44.0,44.0,,
|
9 |
InternLM2-Chat-7B,43.0,43.0,39.0,39.0,45.0,45.0,35.0,35.0
|
10 |
LLaMA-2-13B,28.0,28.0,45.0,45.0,40.0,40.0,43.0,43.0
|
@@ -15,8 +15,8 @@ Qwen-14B-Chat,36.0,36.0,39.0,41.0,44.0,40.0,47.0,43.0
|
|
15 |
Qwen-72B-Chat,46.0,46.0,44.0,44.0,45.0,45.0,61.0,61.0
|
16 |
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 |
-
|
19 |
-
|
20 |
Meta-Llama-3-8B-Instruct,39.670138888888886,39.670138888888886,37.58680555555556,37.58680555555556,30.381944444444443,30.381944444444443,33.072916666666664,33.072916666666664
|
21 |
Qwen1.5-14B-Base,38.0,38.0,39.0,39.0,48.0,48.0,36.0,36.0
|
22 |
Qwen1.5-14B-Chat,34.0,34.0,45.0,43.0,42.0,39.0,48.0,49.0
|
|
|
4 |
DevOps-Model-14B-Chat,27.0,28.0,36.0,33.0,46.0,44.0,44.0,46.0
|
5 |
ERNIE-Bot-4.0,44.0,44.0,48.0,48.0,47.0,47.0,51.0,51.0
|
6 |
GPT-3.5-turbo,36.0,36.0,42.0,42.0,40.0,40.0,48.0,48.0
|
7 |
+
GPT-4,51.0,51.0,53.0,53.0,60.0,60.0,59.0,59.0
|
8 |
InternLM2-Chat-20B,41.0,41.0,,,44.0,44.0,,
|
9 |
InternLM2-Chat-7B,43.0,43.0,39.0,39.0,45.0,45.0,35.0,35.0
|
10 |
LLaMA-2-13B,28.0,28.0,45.0,45.0,40.0,40.0,43.0,43.0
|
|
|
15 |
Qwen-72B-Chat,46.0,46.0,44.0,44.0,45.0,45.0,61.0,61.0
|
16 |
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 |
+
Gemma-2B,25.0,25.0,32.0,32.0,24.0,24.0,30.0,30.0
|
19 |
+
Gemma-7B,22.0,22.0,44.0,44.0,28.0,28.0,40.0,40.0
|
20 |
Meta-Llama-3-8B-Instruct,39.670138888888886,39.670138888888886,37.58680555555556,37.58680555555556,30.381944444444443,30.381944444444443,33.072916666666664,33.072916666666664
|
21 |
Qwen1.5-14B-Base,38.0,38.0,39.0,39.0,48.0,48.0,36.0,36.0
|
22 |
Qwen1.5-14B-Chat,34.0,34.0,45.0,43.0,42.0,39.0,48.0,49.0
|
data_v2/zjyd_en_mc_gen.csv
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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,87.03703703703704,84.11680851851852,88.39286,89.28571,86.11111111111111,83.65384615555556,86.60714286,88.39285714
|
3 |
+
GPT-4,87.03703703703704,87.03703703703704,,,87.03703703703704,87.03703703703704,,
|
4 |
+
Gemma-2B,,26.49573,62.5,62.5,,58.97435897,75.0,75.0
|
5 |
+
Gemma-7B,,77.77778,75.89286,75.89286,,76.06837607,86.60714286,86.60714286
|
6 |
+
Qwen1.5-0.5B-Base,,65.17857,75.0,75.0,,56.25,57.14285714,57.14285714
|
7 |
+
Qwen1.5-0.5B-Chat,,0.0,54.46429,53.57143,,19.64285714,16.96428571,17.85714286
|
8 |
+
Qwen1.5-1.8B-Base,,71.42857,71.42857,71.42857,,70.53571429,80.35714286,80.35714286
|
9 |
+
Qwen1.5-1.8B-Chat,,69.64286,67.85714,77.67857,,66.07142857,68.75,75.0
|
10 |
+
Qwen1.5-14B-Base,,76.92308,88.39286,88.39286,,78.63247863,83.03571429,83.03571429
|
11 |
+
Qwen1.5-14B-Chat,,23.21429,91.07143,92.85714,,78.57142857,80.35714286,83.92857143
|
12 |
+
JIUTIAN-75B-net,82.4074074074074,82.4074074074074,,,84.25925925925925,84.25925925925925,,
|
data_v2/zjyd_zh_mc_gen.csv
CHANGED
@@ -21,9 +21,10 @@ 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 |
Claude-3-Opus,68.05555555555556,68.05555555555556,,,,,,
|
25 |
-
|
26 |
-
|
27 |
Meta-Llama-3-8B-Instruct,63.425925925925924,63.425925925925924,0.0,0.0,66.2037037037037,66.2037037037037,25.0,25.0
|
28 |
Qwen1.5-14B-Base,49.1,49.1,49.9,49.9,62.5,62.5,41.3,41.3
|
29 |
Qwen1.5-14B-Chat,38.6,38.9,48.8,50.5,54.6,55.2,52.1,52.7
|
|
|
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,,,85.18518518518519,85.18518518518519,,
|
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
|
28 |
Meta-Llama-3-8B-Instruct,63.425925925925924,63.425925925925924,0.0,0.0,66.2037037037037,66.2037037037037,25.0,25.0
|
29 |
Qwen1.5-14B-Base,49.1,49.1,49.9,49.9,62.5,62.5,41.3,41.3
|
30 |
Qwen1.5-14B-Chat,38.6,38.9,48.8,50.5,54.6,55.2,52.1,52.7
|
data_v2/zte_en_mc_gen.csv
CHANGED
@@ -19,9 +19,10 @@ 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 |
Claude-3-Opus,49.599999999999994,49.599999999999994,,,,,,
|
23 |
-
|
24 |
-
|
25 |
Meta-Llama-3-70B-Instruct,38.9,38.9,63.4,63.4,37.6,37.6,59.0,59.0
|
26 |
Meta-Llama-3-8B-Instruct,24.7,24.7,35.4,35.4,19.7,19.7,32.9,32.9
|
27 |
Qwen1.5-14B-Base,34.0,34.0,42.8,42.8,57.9,57.9,40.2,40.2
|
|
|
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,,,56.99999999999999,56.99999999999999,,
|
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
|
26 |
Meta-Llama-3-70B-Instruct,38.9,38.9,63.4,63.4,37.6,37.6,59.0,59.0
|
27 |
Meta-Llama-3-8B-Instruct,24.7,24.7,35.4,35.4,19.7,19.7,32.9,32.9
|
28 |
Qwen1.5-14B-Base,34.0,34.0,42.8,42.8,57.9,57.9,40.2,40.2
|
data_v2/zte_zh_mc_gen.csv
CHANGED
@@ -21,9 +21,10 @@ 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 |
Claude-3-Opus,51.4,51.4,,,,,,
|
25 |
-
|
26 |
-
|
27 |
Meta-Llama-3-70B-Instruct,31.1,31.1,37.4,37.4,51.10000000000001,51.10000000000001,36.900000000000006,36.900000000000006
|
28 |
Meta-Llama-3-8B-Instruct,31.1,31.1,34.3,34.3,36.0,36.0,37.1,37.1
|
29 |
Qwen1.5-14B-Base,49.1,49.1,49.9,49.9,62.5,62.5,41.3,41.3
|
|
|
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,,,64.0,64.0,,
|
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
|
28 |
Meta-Llama-3-70B-Instruct,31.1,31.1,37.4,37.4,51.10000000000001,51.10000000000001,36.900000000000006,36.900000000000006
|
29 |
Meta-Llama-3-8B-Instruct,31.1,31.1,34.3,34.3,36.0,36.0,37.1,37.1
|
30 |
Qwen1.5-14B-Base,49.1,49.1,49.9,49.9,62.5,62.5,41.3,41.3
|
leaderboards.py
CHANGED
@@ -4,7 +4,8 @@ eng_leaderboards = [
|
|
4 |
('oracle', ['mc']),
|
5 |
('network', ['mc', 'qa']),
|
6 |
('owl', ['qa']),
|
7 |
-
|
|
|
8 |
('inspur', ['mc']),
|
9 |
]
|
10 |
|
@@ -47,7 +48,8 @@ datasets_abbr = [
|
|
47 |
datasets_zh = [
|
48 |
'5G通信运维(华为核心网)',
|
49 |
'证券信息系统运维(国泰君安)',
|
50 |
-
|
|
|
51 |
'有线网络运维(清华Netman)',
|
52 |
'金融IT运维(浦发银行)',
|
53 |
'运维监控能力测评(Zabbix中国宏时数据)',
|
@@ -65,7 +67,8 @@ datasets_zh = [
|
|
65 |
datasets_en = [
|
66 |
"5G Telecommunications",
|
67 |
"Securities Information System",
|
68 |
-
"China Mobile Zhejiang",
|
|
|
69 |
"Wired Network Operations",
|
70 |
"Financial IT",
|
71 |
"Operations Monitoring Capability",
|
|
|
4 |
('oracle', ['mc']),
|
5 |
('network', ['mc', 'qa']),
|
6 |
('owl', ['qa']),
|
7 |
+
('zjyd', ['mc']),
|
8 |
+
('huaweicloud', ['mc']),
|
9 |
('inspur', ['mc']),
|
10 |
]
|
11 |
|
|
|
48 |
datasets_zh = [
|
49 |
'5G通信运维(华为核心网)',
|
50 |
'证券信息系统运维(国泰君安)',
|
51 |
+
# '中国移动浙江公司',
|
52 |
+
'移动通信网络',
|
53 |
'有线网络运维(清华Netman)',
|
54 |
'金融IT运维(浦发银行)',
|
55 |
'运维监控能力测评(Zabbix中国宏时数据)',
|
|
|
67 |
datasets_en = [
|
68 |
"5G Telecommunications",
|
69 |
"Securities Information System",
|
70 |
+
# "China Mobile Zhejiang",
|
71 |
+
"Mobile Communication Network",
|
72 |
"Wired Network Operations",
|
73 |
"Financial IT",
|
74 |
"Operations Monitoring Capability",
|