Junetheriver commited on
Commit
147416c
1 Parent(s): 32e04fa

update leaderboard 2024-05-20

Browse files
Files changed (1) hide show
  1. data_v2/zte_zh_mc_gen.csv +28 -26
data_v2/zte_zh_mc_gen.csv CHANGED
@@ -1,27 +1,29 @@
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
- Baichuan-13B-Chat,11.04,31.1,37.4,37.4,14.35,51.10000000000001,36.900000000000006,36.900000000000006
3
- Chatglm2-6B,23.09,31.1,34.3,34.3,30.46,36.0,37.1,37.1
4
- Chatglm3-6B,32.6,,,,28.3,,,
5
- Chinese-Alpaca-2-13B,22.69,,,,40.52,,,
6
- Chinese-Llama-2-13B,17.98,,,,31.66,,,
7
- Devops-Model-14B-Chat,41.04,,,,56.85,,,
8
- Ernie-Bot-4.0,45.99,,,,46.0,,,
9
- Glm3-Turbo,43.0,,,,,,,
10
- Glm4,50.0,,,,,,,
11
- Gpt-3.5-Turbo,37.06,,,,39.42,,,
12
- Gpt-4,,,,,,,,
13
- Internlm-7B,27.81,,,,24.18,,,
14
- Internlm2-Chat-20B,44.6,,,,62.2,,,
15
- Internlm2-Chat-7B,38.8,,,,46.0,,,
16
- Llama-2-13B,25.43,,,,36.56,,,
17
- Llama-2-70B-Chat,24.38,,,,44.65,,,
18
- Llama-2-7B,24.09,,,,29.94,,,
19
- Mistral-7B,1.27,,,,30.72,,,
20
- Qwen-14B-Chat,41.71,,,,53.52,,,
21
- Qwen-72B-Chat,64.79,,,,70.19,,,
22
- Qwen-7B-Chat,36.28,,,,41.58,,,
23
- Yi-34B-Chat,64.91,,,,70.85,,,
24
- gemma_2b,25.6,,,,19.1,,,
25
- gemma_7b,27.3,,,,17.3,,,
26
- Qwen1.5-14B-Base,49.1,,,,62.5,,,
27
- Qwen1.5-14B-Chat,38.6,,,,54.6,,,
 
 
 
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
+ Baichuan-13B-Chat,11.04,11.13,26.92,28.61,14.35,13.22,31.69,33.97
3
+ Chatglm2-6B,23.09,23.12,24.22,24.08,30.46,30.46,35.97,35.9
4
+ Chatglm3-6B,32.6,32.6,35.4,35.4,28.3,28.3,40.9,40.9
5
+ Chinese-Alpaca-2-13B,22.69,22.69,24.59,24.59,40.52,40.52,40.73,40.73
6
+ Chinese-Llama-2-13B,17.98,17.98,17.83,17.83,31.66,31.66,36.24,36.24
7
+ Devops-Model-14B-Chat,41.04,42.7,48.71,53.57,56.85,57.25,51.3,54.29
8
+ Ernie-Bot-4.0,45.99,45.99,48.98,48.98,46.0,46.0,54.0,54.0
9
+ Glm3-Turbo,43.0,43.0,,,,,,
10
+ Glm4,50.0,50.0,,,,,,
11
+ Gpt-3.5-Turbo,37.06,36.83,37.56,39.25,39.42,39.77,41.96,42.15
12
+ Gpt-4,,,57.35,62.11,,,61.2,65.68
13
+ Internlm-7B,27.81,27.81,19.95,19.95,24.18,24.18,35.35,35.35
14
+ Internlm2-Chat-20B,44.6,44.6,47.0,47.0,62.2,62.2,38.3,38.3
15
+ Internlm2-Chat-7B,38.8,38.8,44.6,44.6,46.0,46.0,35.8,35.8
16
+ Llama-2-13B,25.43,27.16,29.17,29.99,36.56,36.15,37.7,39.02
17
+ Llama-2-70B-Chat,24.38,24.38,43.63,43.63,44.65,44.65,48.84,48.84
18
+ Llama-2-7B,24.09,23.47,28.69,29.26,29.94,30.03,31.35,31.93
19
+ Mistral-7B,1.27,1.27,42.05,42.05,30.72,30.72,46.44,46.44
20
+ 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
+ gemma_2b,25.6,25.6,28.3,28.3,19.1,19.1,35.5,35.5
25
+ gemma_7b,27.3,27.3,35.4,35.4,17.3,17.3,44.5,44.5
26
+ Qwen1.5-14B-Base,49.1,31.1,49.9,37.4,62.5,51.10000000000001,41.3,36.900000000000006
27
+ Qwen1.5-14B-Chat,38.6,31.1,48.8,34.3,54.6,36.0,52.1,37.1
28
+ Qwen1.5-14B-Base,,49.1,,49.9,,62.5,,41.3
29
+ Qwen1.5-14B-Chat,,38.9,,50.5,,55.2,,52.7