DONG19 commited on
Commit
0413a09
1 Parent(s): c307e47
leaderboard_table_20240525.csv DELETED
@@ -1,98 +0,0 @@
1
- model,Dataset,Timeout,ET,NET,Max_NET,NET>5,MU,NMU,Max_NMU,NMU>5,TMU,NTMU,Max_TMU,TMU>5,pass1
2
- Artigenz-Coder-DS-6.7B,EffiBench,10,0.65,4.86,97.02,6.0,71.74,1.85,317.51,0.8,207.87,25.6,27332.76,6.3,38.2
3
- claude-3-haiku_1,EffiBench,10,0.48,3.69,100.28,3.6,38.33,1.07,40.12,0.5,32.52,4.85,3524.68,3.8,44.3
4
- claude-3-sonnet,EffiBench,10,0.7,5.19,100.31,5.7,73.52,1.97,539.82,0.4,248.98,33.08,48799.93,5.7,45.5
5
- CodeFuse-DeepSeek-33B,EffiBench,10,0.48,3.74,96.19,3.3,80.44,2.3,259.7,1.0,305.94,48.22,28532.0,3.3,30.1
6
- codegemma-7b-it,EffiBench,10,1.32,10.04,100.45,12.8,406.94,11.92,910.63,2.7,1772.13,327.14,59405.83,13.4,18.7
7
- codegemma-7b,EffiBench,10,0.77,6.36,93.87,6.6,39.37,1.22,43.21,0.7,62.26,14.93,1286.75,6.6,13.7
8
- CodeLlama-7b-hf,EffiBench,10,5.25,46.68,96.38,52.4,336.22,12.41,248.66,9.5,1617.73,800.47,17563.1,52.4,2.2
9
- CodeLlama-7b-Instruct-hf,EffiBench,10,3.33,21.97,98.15,33.3,63.96,1.37,48.16,1.4,191.57,14.99,3564.4,33.3,7.0
10
- CodeLlama-7b-Python-hf,EffiBench,10,2.4,17.68,97.84,22.6,114.89,2.86,207.42,6.0,449.52,56.99,13685.67,25.0,8.6
11
- CodeLlama-13b-hf,EffiBench,10,5.8,36.46,95.26,57.7,127.59,2.44,67.15,7.7,531.94,31.1,4600.56,57.7,2.6
12
- CodeLlama-13b-Instruct-hf,EffiBench,10,1.49,11.17,98.89,14.7,117.34,2.87,304.16,1.1,608.26,68.3,30376.45,14.7,9.7
13
- CodeLlama-13b-Python-hf,EffiBench,10,1.77,12.33,94.58,15.7,90.72,2.22,134.59,2.6,277.59,31.52,8324.75,15.7,11.5
14
- CodeLlama-34b-hf,EffiBench,10,2.07,16.45,98.57,19.0,61.34,1.81,44.34,3.8,201.6,35.33,3160.63,19.0,10.5
15
- CodeLlama-34b-Instruct-hf,EffiBench,10,1.96,14.26,97.48,18.5,99.05,2.46,148.0,3.7,458.56,55.67,13278.69,19.3,13.5
16
- CodeLlama-34b-Python-hf,EffiBench,10,1.61,11.76,97.37,20.5,41.49,1.0,1.39,0.0,88.52,9.55,162.73,16.4,12.2
17
- CodeLlama-70b-hf,EffiBench,10,1.75,13.4,97.57,45.1,39.96,1.07,11.87,1.0,61.82,9.15,745.81,26.5,10.2
18
- CodeLlama-70b-Instruct-hf,EffiBench,10,1.28,10.49,94.94,56.4,109.05,3.56,259.78,1.3,361.24,106.76,16667.78,34.6,7.8
19
- deepseek-coder-1.3b-instruct,EffiBench,10,1.09,8.57,94.8,35.4,38.38,1.13,9.69,2.1,43.81,10.14,687.67,25.0,4.8
20
- deepseek-coder-6.7b-base,EffiBench,10,1.35,10.11,97.9,46.6,40.14,1.04,14.57,0.6,50.94,6.13,1107.79,29.2,17.9
21
- deepseek-coder-6.7b-instruct,EffiBench,10,1.24,7.83,92.04,62.5,77.28,1.45,9.53,1.4,181.46,12.18,183.82,47.2,7.2
22
- deepseek-coder-33b-base,EffiBench,10,1.36,11.02,95.37,63.1,98.3,2.99,259.02,3.2,302.75,55.15,16479.52,53.2,25.2
23
- gpt-3.5-turbo-0301,EffiBench,10,1.18,8.92,93.26,64.2,77.19,2.08,336.7,0.9,238.96,32.52,24636.2,56.3,44.0
24
- gpt-3.5-turbo-0613,EffiBench,10,1.19,9.08,93.69,68.5,41.64,1.15,111.14,0.2,74.45,10.61,8009.72,63.7,48.2
25
- gpt-3.5-turbo-1106,EffiBench,10,1.08,8.3,83.23,72.1,36.04,1.01,7.76,0.2,45.23,6.64,255.16,67.1,50.2
26
- gpt-4,EffiBench,10,1.18,8.89,91.94,73.5,68.52,1.84,246.91,1.3,193.6,23.12,15521.36,69.3,52.5
27
- gpt-4-turbo-preview,EffiBench,10,1.12,8.53,94.13,77.2,35.07,1.0,7.78,0.2,46.75,6.58,141.19,73.9,66.6
28
- Magicoder-S-DS-6.7B,EffiBench,10,1.07,8.19,90.3,79.3,38.23,1.03,15.74,0.5,47.72,6.64,953.97,76.6,36.8
29
- Mistral-7B-codealpaca-lora,EffiBench,10,3.19,27.73,94.55,77.8,27.35,1.03,2.22,0.0,72.67,36.67,142.55,72.2,3.6
30
- octocoder,EffiBench,10,3.62,30.38,92.39,83.3,31.49,1.0,1.01,0.0,82.33,32.71,139.5,50.0,0.6
31
- OpenCodeInterpreter-DS-1.3B,EffiBench,10,1.84,11.01,90.12,73.3,59.27,1.03,3.13,0.0,175.01,6.84,318.38,68.3,6.2
32
- OpenCodeInterpreter-DS-6.7B,EffiBench,10,1.4,10.22,95.3,82.5,39.89,1.0,1.38,0.0,60.03,7.11,140.4,78.1,13.7
33
- OpenCodeInterpreter-DS-33B,EffiBench,10,1.41,10.23,91.03,77.8,39.06,1.0,2.3,0.0,59.67,5.93,136.37,73.8,24.9
34
- Phind-CodeLlama-34B-Python-v1,EffiBench,10,2.21,14.62,91.62,77.5,76.64,1.58,153.3,1.3,271.78,19.87,10583.35,74.8,15.1
35
- Phind-CodeLlama-34B-v1,EffiBench,10,2.25,16.26,94.3,83.3,158.79,3.78,215.99,5.8,588.07,61.3,16601.89,81.2,13.8
36
- Phind-CodeLlama-34B-v2,EffiBench,10,1.85,12.26,90.88,85.0,97.79,1.99,148.92,2.9,350.9,24.91,9532.94,82.1,20.9
37
- speechless-starcoder2-15b,EffiBench,10,2.09,19.65,82.35,83.3,26.27,1.0,1.01,0.0,45.12,25.67,127.38,83.3,0.6
38
- starcoder,EffiBench,10,3.3,23.31,94.42,85.4,39.96,1.08,5.5,2.1,104.5,14.65,138.13,85.4,4.8
39
- starcoder2-3b,EffiBench,10,2.82,13.29,85.73,94.1,83.53,1.12,7.03,5.9,288.56,5.3,379.23,88.2,1.7
40
- starcoder2-7b,EffiBench,10,2.31,21.74,86.4,100.0,29.46,1.2,4.79,0.0,66.1,38.95,276.52,100.0,1.9
41
- starcoder2-15b,EffiBench,10,3.43,17.46,86.44,100.0,93.19,1.09,3.71,0.0,282.84,10.2,392.53,100.0,0.9
42
- starcoderbase,EffiBench,10,3.93,23.75,96.02,90.3,196.64,4.57,152.91,12.9,764.66,78.21,8540.21,87.1,3.2
43
- WizardCoder-15B-V1.0,EffiBench,10,3.11,22.17,92.78,87.2,168.1,3.74,139.88,7.7,821.23,86.88,9659.92,87.2,4.0
44
- WizardCoder-Python-13B-V1.0-GPTQ,EffiBench,10,2.83,15.33,93.53,95.0,93.92,1.75,66.6,2.5,334.38,23.03,4540.18,90.0,4.0
45
- XwinCoder-13B,EffiBench,10,2.81,23.55,93.76,91.4,53.97,1.66,83.49,1.9,177.3,37.61,4347.14,88.6,10.8
46
- XwinCoder-34B,EffiBench,10,2.23,16.54,96.23,89.3,42.92,1.16,26.85,1.9,103.16,11.58,1352.04,88.8,21.5
47
- Yi-34B-200K,EffiBench,10,2.84,25.52,93.66,91.5,73.99,2.79,74.99,4.3,288.27,149.95,5222.09,91.5,4.7
48
- Yi-34B-Chat,EffiBench,10,2.37,12.72,90.75,90.9,67.5,1.0,1.02,0.0,202.05,5.59,135.56,87.9,3.3
49
- Yi-34B,EffiBench,10,4.21,24.62,93.25,95.3,135.57,2.18,133.09,2.3,540.82,23.26,8138.38,93.0,4.3
50
- Artigenz-Coder-DS-6.7B,HumanEval,10,2.66,11.38,54.23,91.5,64.1,1.1,3.5,0.0,123.54,15.89,240.56,100.0,96.3
51
- CodeFuse-DeepSeek-33B,HumanEval,10,2.49,10.64,52.69,93.8,64.03,1.1,3.51,0.0,112.73,14.54,228.11,100.0,95.1
52
- CodeLlama-7b-Instruct-hf,HumanEval,10,2.22,9.39,43.51,95.2,65.04,1.14,3.51,0.0,99.06,12.45,187.92,95.2,48.8
53
- CodeLlama-13b-Instruct-hf,HumanEval,10,2.48,10.32,15.87,91.7,63.61,1.06,1.14,0.0,111.7,13.91,20.63,91.7,68.9
54
- CodeLlama-34b-hf,HumanEval,10,2.57,11.27,61.03,92.5,63.94,1.11,3.51,0.0,113.78,15.19,229.79,100.0,82.3
55
- CodeLlama-34b-Instruct-hf,HumanEval,10,2.4,10.62,52.72,97.4,64.48,1.12,3.5,0.0,109.61,14.8,218.12,100.0,76.8
56
- CodeLlama-70b-Instruct-hf,HumanEval,10,1.46,6.48,9.57,90.9,63.52,1.07,1.09,0.0,61.2,8.54,12.03,90.9,18.3
57
- deepseek-coder-1.3b-instruct,HumanEval,10,1.55,6.81,8.65,90.0,64.33,1.06,1.09,0.0,65.9,8.98,12.83,90.0,22.6
58
- deepseek-coder-6.7b-instruct,HumanEval,10,1.8,7.71,31.36,100.0,64.32,1.21,3.39,0.0,79.09,10.71,129.23,100.0,21.3
59
- Magicoder-S-DS-6.7B,HumanEval,10,2.66,11.24,61.6,91.7,63.94,1.09,3.49,0.0,119.65,15.25,234.52,100.0,95.7
60
- Mistral-7B-codealpaca-lora,HumanEval,10,2.4,10.38,52.99,93.0,64.05,1.11,3.5,0.0,113.59,14.82,233.85,93.0,89.0
61
- OpenCodeInterpreter-DS-1.3B,HumanEval,10,1.9,8.2,36.57,95.9,63.67,1.1,3.39,0.0,85.06,11.06,153.99,100.0,40.2
62
- OpenCodeInterpreter-DS-6.7B,HumanEval,10,2.18,9.71,48.95,96.2,62.91,1.11,3.51,0.0,95.65,13.29,210.58,96.2,63.4
63
- OpenCodeInterpreter-DS-33B,HumanEval,10,2.57,11.07,57.58,91.5,64.05,1.1,3.51,0.0,114.67,14.89,248.48,100.0,89.0
64
- Phind-CodeLlama-34B-v2,HumanEval,10,2.34,10.08,47.35,95.2,63.63,1.11,3.53,0.0,102.55,13.48,212.01,100.0,81.7
65
- speechless-starcoder2-15b,HumanEval,10,1.35,5.93,7.07,83.3,62.26,1.06,1.08,0.0,57.92,7.88,9.53,83.3,10.4
66
- starcoder2-3b,HumanEval,10,1.72,6.59,10.08,88.9,64.02,1.06,1.09,0.0,76.79,8.79,13.0,88.9,23.2
67
- starcoder2-7b,HumanEval,10,1.55,6.04,8.99,75.0,66.69,1.06,1.08,0.0,67.85,7.5,10.61,100.0,9.8
68
- starcoder2-15b,HumanEval,10,1.88,6.99,6.99,100.0,70.76,1.08,1.08,0.0,88.23,8.8,8.8,100.0,4.9
69
- WizardCoder-Python-7B-V1.0-GPTQ,HumanEval,10,2.56,11.09,18.94,100.0,63.75,1.08,1.73,0.0,114.61,15.23,22.51,100.0,64.0
70
- WizardCoder-Python-13B-V1.0-GPTQ,HumanEval,10,1.78,7.34,10.8,93.3,62.65,1.09,1.73,0.0,77.92,9.88,14.21,93.3,31.7
71
- WizardCoder-Python-34B-V1.0-GPTQ,HumanEval,10,2.47,10.57,17.08,96.7,63.71,1.08,1.73,0.0,109.55,14.37,21.73,96.7,68.3
72
- XwinCoder-7B,HumanEval,10,2.7,11.63,56.15,92.0,64.03,1.1,3.5,0.0,122.6,15.95,227.69,98.0,100.0
73
- XwinCoder-13B,HumanEval,10,2.56,11.02,54.75,91.7,64.04,1.1,3.51,0.0,114.46,14.9,250.79,95.8,93.3
74
- XwinCoder-34B,HumanEval,10,2.61,11.23,59.91,92.0,63.91,1.1,3.51,0.0,116.84,15.2,233.53,100.0,95.7
75
- Artigenz-Coder-DS-6.7B,MBPP,10,2.7,9.02,43.11,98.7,67.65,1.0,1.1,0.0,132.95,3.51,70.75,98.7,63.2
76
- CodeFuse-DeepSeek-33B,MBPP,10,2.96,9.74,48.61,98.2,62.39,1.07,1.1,0.0,129.82,10.57,87.21,98.2,59.0
77
- CodeLlama-7b-Instruct-hf,MBPP,10,1.97,8.94,38.89,100.0,61.76,1.06,1.1,0.0,81.83,11.07,53.15,100.0,13.8
78
- CodeLlama-13b-Instruct-hf,MBPP,10,2.12,8.38,43.06,95.6,61.22,1.05,1.15,0.0,90.76,9.8,75.23,95.6,24.1
79
- CodeLlama-34b-hf,MBPP,10,2.55,8.39,46.86,97.4,61.68,1.06,1.41,0.0,109.46,8.94,80.83,97.4,30.2
80
- CodeLlama-34b-Instruct-hf,MBPP,10,2.76,7.81,40.61,97.0,62.16,1.06,2.61,0.0,118.78,7.91,96.77,96.3,35.4
81
- CodeLlama-70b-Instruct-hf,MBPP,10,1.54,7.08,9.8,94.6,62.74,1.06,1.09,0.0,62.97,8.62,13.32,97.3,9.8
82
- deepseek-coder-1.3b-instruct,MBPP,10,2.28,6.25,48.07,93.8,131.54,2.25,38.52,3.1,397.41,25.13,1240.85,96.9,8.5
83
- deepseek-coder-6.7b-instruct,MBPP,10,1.92,9.2,49.89,100.0,62.47,1.07,1.1,0.0,86.58,12.59,93.37,100.0,4.8
84
- Magicoder-S-DS-6.7B,MBPP,10,2.68,9.13,44.19,97.4,62.48,1.06,1.09,0.0,114.14,9.22,72.37,97.4,60.1
85
- Mistral-7B-codealpaca-lora,MBPP,10,1.99,8.36,14.71,98.9,62.33,1.07,1.1,0.0,83.74,10.0,20.28,98.9,23.5
86
- OpenCodeInterpreter-DS-1.3B,MBPP,10,2.16,7.3,39.51,96.6,62.74,1.07,1.98,0.0,93.47,8.0,52.95,96.6,23.3
87
- OpenCodeInterpreter-DS-6.7B,MBPP,10,2.27,9.46,31.76,98.6,62.37,1.07,1.09,0.0,93.45,11.03,52.63,98.6,37.8
88
- OpenCodeInterpreter-DS-33B,MBPP,10,2.71,8.88,48.27,98.5,62.66,1.06,1.41,0.0,117.53,8.91,85.46,98.5,52.6
89
- Phind-CodeLlama-34B-v2,MBPP,10,2.64,8.66,42.58,98.5,62.4,1.06,1.1,0.0,113.38,8.67,71.13,98.5,52.6
90
- starcoder2-3b,MBPP,10,1.31,6.28,9.77,66.7,57.97,0.99,1.15,0.0,51.05,7.52,13.58,72.2,4.8
91
- starcoder2-7b,MBPP,10,2.34,11.72,45.21,50.0,49.07,0.84,1.07,0.0,98.86,15.22,63.59,50.0,1.6
92
- starcoder2-15b,MBPP,10,1.59,8.7,8.7,100.0,62.45,1.08,1.08,0.0,60.54,10.25,10.25,100.0,0.3
93
- WizardCoder-Python-7B-V1.0-GPTQ,MBPP,10,1.76,8.29,13.73,100.0,62.26,1.06,1.07,0.0,70.39,10.05,16.64,100.0,3.4
94
- WizardCoder-Python-13B-V1.0-GPTQ,MBPP,10,2.21,4.43,49.49,93.4,62.05,1.06,1.1,0.0,98.26,4.15,91.41,93.4,16.1
95
- WizardCoder-Python-34B-V1.0-GPTQ,MBPP,10,2.68,6.79,36.35,88.5,61.04,1.04,1.08,0.0,122.51,7.01,64.28,88.5,6.9
96
- XwinCoder-7B,MBPP,10,2.56,12.82,13.49,100.0,62.39,1.06,1.07,0.0,109.08,16.68,17.88,100.0,0.8
97
- XwinCoder-13B,MBPP,10,2.88,11.31,45.38,98.1,62.35,1.07,1.08,0.0,125.2,13.29,83.29,98.1,41.5
98
- XwinCoder-34B,MBPP,10,2.73,10.38,46.05,98.6,62.29,1.07,1.1,0.0,116.42,11.76,78.19,99.1,58.2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
leaderboard_table_20240527.csv ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model,Dataset,Timeout,ET,NET,Max_NET,NET>5,ThroughtPut,NThroughtPut,Max_ThroughtPut,ThroughtPut>5,MU,NMU,Max_NMU,NMU>5,TMU,NTMU,Max_TMU,TMU>5,pass1
2
+ Artigenz-Coder-DS-6.7B,EffiBench,10,0.39,2.89,27.78,1.6,2187.71,0.9,0.92,0.0,62.13,1.59,2.48,0.0,19.72,2.35,70.28,90.9,36.4
3
+ claude-3-haiku_1,EffiBench,10,0.39,3.0,28.75,0.7,1969.94,0.88,0.93,0.0,59.15,1.64,2.05,0.0,17.99,2.66,72.87,90.0,42.9
4
+ claude-3-sonnet,EffiBench,10,0.4,3.05,17.43,0.9,1954.22,0.86,0.93,0.0,60.22,1.62,2.06,0.0,23.29,3.13,50.78,90.5,43.2
5
+ CodeFuse-DeepSeek-33B,EffiBench,10,0.36,2.77,6.1,0.3,1792.2,0.88,0.94,0.0,58.3,1.65,2.06,0.0,16.45,2.54,15.19,87.6,29.2
6
+ codegemma-7b-it,EffiBench,10,0.36,2.85,14.19,1.2,1775.12,0.81,0.93,0.0,58.46,1.68,2.06,0.0,16.12,2.87,40.54,89.8,16.6
7
+ codegemma-7b,EffiBench,10,0.34,2.82,8.09,0.8,2179.43,0.9,0.93,0.0,55.68,1.71,2.06,0.0,13.78,3.19,20.96,92.2,12.8
8
+ CodeLlama-7b-Instruct-hf,EffiBench,10,0.46,2.89,17.26,4.2,1881.5,0.71,0.94,0.0,77.87,1.43,3.59,0.0,32.14,1.87,56.61,87.5,4.8
9
+ CodeLlama-7b-Python-hf,EffiBench,10,0.34,2.64,4.05,0.0,2479.33,0.92,0.92,0.0,58.02,1.63,2.42,0.0,14.42,2.4,9.94,84.4,6.5
10
+ CodeLlama-13b-hf,EffiBench,10,0.4,1.95,3.21,0.0,2863.0,1.07,1.07,0.0,104.42,1.25,2.05,0.0,43.83,1.19,6.53,81.8,1.1
11
+ CodeLlama-13b-Instruct-hf,EffiBench,10,0.35,2.55,4.46,0.0,2448.5,0.91,0.92,0.0,65.96,1.54,2.48,0.0,18.74,1.89,10.22,91.6,8.4
12
+ CodeLlama-13b-Python-hf,EffiBench,10,0.37,2.69,9.54,1.0,2082.17,0.88,0.93,0.0,65.81,1.53,2.07,0.0,22.81,2.33,21.59,87.6,9.7
13
+ CodeLlama-34b-hf,EffiBench,10,0.34,2.76,4.46,0.0,2102.67,0.89,0.92,0.0,55.38,1.75,2.06,0.0,13.41,2.89,9.17,92.9,8.4
14
+ CodeLlama-34b-Instruct-hf,EffiBench,10,0.37,2.84,13.66,0.9,1850.17,0.89,0.93,0.0,61.31,1.62,2.56,0.0,18.53,2.68,31.46,87.4,11.1
15
+ CodeLlama-34b-Python-hf,EffiBench,10,0.39,3.02,45.19,0.9,2442.0,0.91,0.91,0.0,60.01,1.64,2.38,0.0,19.52,2.84,137.21,87.7,10.6
16
+ CodeLlama-70b-hf,EffiBench,10,0.42,3.18,13.92,4.4,2429.25,0.91,0.92,0.0,62.41,1.6,2.06,0.0,22.27,3.0,32.04,87.8,9.0
17
+ CodeLlama-70b-Instruct-hf,EffiBench,10,0.38,3.17,14.6,1.4,2469.0,0.93,0.93,0.0,54.04,1.79,2.06,0.0,18.27,5.45,33.69,90.3,7.2
18
+ deepseek-coder-1.3b-instruct,EffiBench,10,0.33,2.55,3.63,0.0,2552.0,0.93,0.93,0.0,57.73,1.66,2.03,0.0,13.11,2.92,8.13,88.9,4.5
19
+ deepseek-coder-6.7b-base,EffiBench,10,0.37,2.75,12.25,1.2,2473.25,0.91,0.92,0.0,62.78,1.58,2.14,0.0,19.55,2.21,23.39,89.7,16.5
20
+ deepseek-coder-6.7b-instruct,EffiBench,10,0.38,2.43,5.59,1.4,1261.0,0.48,0.75,0.0,73.73,1.42,2.57,0.0,26.84,1.83,13.81,88.4,6.9
21
+ deepseek-coder-33b-base,EffiBench,10,0.38,3.08,19.54,1.3,1955.36,0.85,0.92,0.0,60.3,1.82,37.39,0.4,22.05,3.88,604.13,91.9,23.5
22
+ gpt-3.5-turbo-0301,EffiBench,10,0.39,2.92,27.7,1.4,1907.38,0.88,0.95,0.0,60.53,1.61,2.05,0.0,19.06,2.52,70.62,89.1,42.3
23
+ gpt-3.5-turbo-0613,EffiBench,10,0.39,2.96,46.7,0.9,1912.42,0.88,0.94,0.0,59.82,1.64,2.64,0.0,19.11,2.68,161.12,89.9,46.4
24
+ gpt-3.5-turbo-1106,EffiBench,10,0.4,3.15,68.71,1.6,2177.43,0.91,1.18,0.0,59.34,1.66,9.12,0.2,19.39,2.85,182.63,90.9,49.3
25
+ gpt-4,EffiBench,10,0.37,2.88,13.89,1.0,1981.62,0.89,0.93,0.0,58.85,1.66,2.25,0.0,17.69,2.69,43.92,91.1,50.8
26
+ gpt-4-turbo-preview,EffiBench,10,0.38,3.02,27.0,1.2,2097.52,0.89,0.93,0.0,57.06,1.71,9.13,0.2,16.92,3.02,68.48,91.1,65.4
27
+ Magicoder-S-DS-6.7B,EffiBench,10,0.35,2.72,6.73,0.6,1731.36,0.71,0.74,0.0,60.12,1.62,2.61,0.0,16.84,2.32,14.24,89.0,36.3
28
+ Mistral-7B-codealpaca-lora,EffiBench,10,0.31,2.8,3.82,0.0,2099.0,0.79,0.79,0.0,51.51,1.91,2.36,0.0,10.5,5.46,9.2,88.5,2.6
29
+ OpenCodeInterpreter-DS-1.3B,EffiBench,10,0.35,2.5,3.93,0.0,1667.0,0.88,0.93,0.0,68.25,1.51,2.05,0.0,21.88,1.89,8.44,87.0,5.5
30
+ OpenCodeInterpreter-DS-6.7B,EffiBench,10,0.37,2.66,6.03,1.5,1880.0,0.91,0.94,0.0,63.41,1.58,2.37,0.0,19.17,2.21,14.14,87.9,13.2
31
+ OpenCodeInterpreter-DS-33B,EffiBench,10,0.39,2.95,26.06,1.7,1658.67,0.72,0.78,0.0,59.37,1.65,2.43,0.0,18.34,2.77,66.25,88.2,23.7
32
+ Phind-CodeLlama-34B-Python-v1,EffiBench,10,0.4,2.7,26.62,2.3,2504.14,0.93,0.93,0.0,71.23,1.47,2.31,0.0,26.23,1.89,90.38,89.5,13.3
33
+ Phind-CodeLlama-34B-v1,EffiBench,10,0.36,2.55,3.57,0.0,2466.33,0.92,0.92,0.0,67.63,1.51,2.06,0.0,22.61,2.07,7.76,88.0,11.7
34
+ Phind-CodeLlama-34B-v2,EffiBench,10,0.42,2.83,53.08,1.0,2226.0,0.91,0.93,0.0,70.53,1.46,2.6,0.0,26.24,1.94,139.88,86.4,19.1
35
+ starcoder,EffiBench,10,0.33,2.54,3.34,0.0,1657.0,0.87,0.91,0.0,65.23,1.55,2.06,0.0,17.67,2.03,6.88,85.3,3.4
36
+ starcoder2-3b,EffiBench,10,0.31,2.86,3.13,0.0,2842.0,1.07,1.07,0.0,51.58,1.87,2.04,0.0,10.55,5.42,6.61,92.3,1.3
37
+ starcoder2-7b,EffiBench,10,0.32,3.02,5.19,6.7,3281.0,1.2,1.2,0.0,48.55,1.98,2.06,0.0,10.63,6.29,12.69,100.0,1.5
38
+ WizardCoder-15B-V1.0,EffiBench,10,0.35,2.37,4.07,0.0,2214.33,1.02,1.03,0.0,72.72,1.45,2.06,0.0,20.63,1.76,9.51,83.3,3.0
39
+ WizardCoder-Python-13B-V1.0-GPTQ,EffiBench,10,0.46,2.75,16.48,2.9,1416.0,0.54,1.02,0.0,80.77,1.41,3.57,0.0,30.74,1.96,53.63,76.5,3.4
40
+ XwinCoder-13B,EffiBench,10,0.33,2.74,4.16,0.0,3227.5,1.2,1.21,0.0,57.7,1.68,2.05,0.0,14.4,2.64,8.95,92.8,8.4
41
+ XwinCoder-34B,EffiBench,10,0.34,2.75,6.32,0.5,3104.29,1.26,1.28,0.0,57.92,1.68,2.42,0.0,14.31,2.81,17.7,87.5,18.4
42
+ Yi-34B-200K,EffiBench,10,0.31,2.89,3.17,0.0,2106.0,0.88,0.96,0.0,49.88,1.93,2.06,0.0,10.23,5.72,6.78,91.7,3.6
43
+ Yi-34B-Chat,EffiBench,10,0.34,2.43,3.15,0.0,1719.0,1.01,1.03,0.0,68.99,1.49,2.05,0.0,19.09,1.84,6.69,89.3,2.8
44
+ Yi-34B,EffiBench,10,0.37,2.18,3.38,0.0,2868.0,1.08,1.08,0.0,83.42,1.37,2.05,0.0,26.71,1.39,7.13,88.5,2.6
45
+ Artigenz-Coder-DS-6.7B,MBPP,10,0.67,2.23,10.2,0.4,203.82,1.02,1.05,0.0,71.66,1.06,1.09,0.0,45.42,1.2,16.48,14.7,23.8
46
+ CodeFuse-DeepSeek-33B,MBPP,10,0.61,2.46,9.54,0.5,204.47,1.02,1.07,0.0,62.43,1.07,1.1,0.0,25.86,2.86,15.76,12.5,21.6
47
+ CodeLlama-7b-Instruct-hf,MBPP,10,0.38,1.7,2.37,0.0,205.86,1.03,1.05,0.0,62.37,1.07,1.1,0.0,15.32,2.07,3.01,0.0,5.0
48
+ CodeLlama-13b-Instruct-hf,MBPP,10,0.44,2.06,3.21,0.0,194.0,0.98,1.13,0.0,62.52,1.07,1.15,0.0,17.66,2.52,4.36,0.0,8.2
49
+ CodeLlama-34b-hf,MBPP,10,0.48,2.18,3.37,0.0,206.42,1.03,1.08,0.0,62.28,1.07,1.41,0.0,19.55,2.66,4.42,0.0,10.7
50
+ CodeLlama-34b-Instruct-hf,MBPP,10,0.55,2.07,3.55,0.0,206.0,1.04,1.06,0.0,62.39,1.07,1.11,0.0,22.45,2.29,4.62,0.0,12.4
51
+ CodeLlama-70b-Instruct-hf,MBPP,10,0.34,1.57,2.21,0.0,208.0,1.03,1.06,0.0,63.26,1.07,1.08,0.0,13.79,1.88,2.77,0.0,3.6
52
+ deepseek-coder-1.3b-instruct,MBPP,10,0.41,1.09,2.17,0.0,215.33,1.07,1.08,0.0,62.39,1.07,1.08,0.0,18.27,1.11,2.6,0.0,3.0
53
+ deepseek-coder-6.7b-instruct,MBPP,10,0.37,1.74,2.68,0.0,283.5,1.39,1.4,0.0,62.38,1.07,1.08,0.0,14.5,2.09,3.38,0.0,1.7
54
+ Magicoder-S-DS-6.7B,MBPP,10,0.66,2.45,5.14,0.9,201.7,1.01,1.05,0.0,62.63,1.06,1.1,0.0,26.86,2.45,7.07,9.4,22.4
55
+ Mistral-7B-codealpaca-lora,MBPP,10,0.48,2.04,3.39,0.0,205.5,1.03,1.06,0.0,62.34,1.07,1.1,0.0,19.85,2.37,4.65,0.0,8.9
56
+ OpenCodeInterpreter-DS-1.3B,MBPP,10,0.52,1.76,3.53,0.0,202.09,1.01,1.03,0.0,62.98,1.08,1.98,0.0,23.23,1.98,5.07,1.1,8.7
57
+ OpenCodeInterpreter-DS-6.7B,MBPP,10,0.6,2.5,9.54,1.4,202.75,1.02,1.04,0.0,62.37,1.07,1.1,0.0,25.39,3.0,16.14,2.8,14.3
58
+ OpenCodeInterpreter-DS-33B,MBPP,10,0.61,2.65,4.02,0.0,206.0,1.03,1.06,0.0,62.72,1.07,1.41,0.0,25.13,3.14,5.53,2.6,19.3
59
+ Phind-CodeLlama-34B-v2,MBPP,10,0.65,2.37,13.64,1.0,202.3,1.01,1.06,0.0,62.41,1.07,1.09,0.0,27.22,2.54,23.39,12.2,19.6
60
+ starcoder2-3b,MBPP,10,0.35,1.69,2.34,0.0,323.0,1.61,1.61,0.0,62.68,1.07,1.16,0.0,14.07,2.08,3.07,0.0,1.3
61
+ WizardCoder-Python-13B-V1.0-GPTQ,MBPP,10,0.47,1.58,2.9,0.0,204.6,1.04,1.06,0.0,62.37,1.07,1.1,0.0,19.8,1.67,4.12,0.0,5.7
62
+ WizardCoder-Python-34B-V1.0-GPTQ,MBPP,10,0.43,1.48,2.47,0.0,245.0,1.21,1.24,0.0,62.27,1.06,1.08,0.0,18.23,1.63,2.9,0.0,2.3
63
+ XwinCoder-13B,MBPP,10,0.59,2.5,4.23,0.0,202.9,1.01,1.03,0.0,62.36,1.07,1.08,0.0,24.18,2.93,5.16,2.0,15.2
64
+ XwinCoder-34B,MBPP,10,0.59,2.25,9.16,0.9,204.0,1.02,1.07,0.0,62.42,1.07,1.1,0.0,24.79,2.49,15.91,4.1,21.7
65
+ Artigenz-Coder-DS-6.7B,HumanEval,10,0.85,3.65,16.62,14.9,187.12,1.0,1.05,0.0,64.08,1.1,3.5,0.0,36.61,4.71,68.8,42.6,15.8
66
+ CodeFuse-DeepSeek-33B,HumanEval,10,0.86,3.69,20.03,6.2,184.57,0.99,1.02,0.0,64.06,1.1,3.5,0.0,37.87,4.88,88.91,45.8,15.6
67
+ CodeLlama-7b-Instruct-hf,HumanEval,10,0.87,3.68,19.48,9.5,186.88,1.0,1.04,0.0,65.03,1.14,3.51,0.0,36.71,4.62,74.88,19.0,7.8
68
+ CodeLlama-13b-Instruct-hf,HumanEval,10,0.86,3.58,5.18,2.8,187.5,1.0,1.03,0.0,63.77,1.06,1.14,0.0,37.64,4.69,7.15,52.8,11.3
69
+ CodeLlama-34b-hf,HumanEval,10,0.84,3.67,20.37,12.5,183.89,0.98,1.06,0.0,63.96,1.11,3.51,0.0,36.46,4.87,85.45,42.5,13.4
70
+ CodeLlama-34b-Instruct-hf,HumanEval,10,0.83,3.67,17.58,7.9,186.11,0.98,1.02,0.0,64.44,1.12,3.49,0.0,37.49,5.06,78.81,50.0,12.6
71
+ CodeLlama-70b-Instruct-hf,HumanEval,10,0.6,2.67,3.23,0.0,191.62,1.04,1.07,0.0,63.53,1.07,1.09,0.0,23.42,3.27,4.25,0.0,3.0
72
+ deepseek-coder-1.3b-instruct,HumanEval,10,0.66,2.91,4.01,0.0,201.8,1.01,1.02,0.0,64.32,1.06,1.09,0.0,26.82,3.65,5.56,20.0,3.7
73
+ deepseek-coder-6.7b-instruct,HumanEval,10,0.68,2.9,10.12,18.2,194.5,1.02,1.04,0.0,64.33,1.21,3.38,0.0,28.45,3.85,39.44,18.2,3.5
74
+ Magicoder-S-DS-6.7B,HumanEval,10,0.88,3.73,18.92,12.5,188.58,1.01,1.04,0.0,64.06,1.09,3.51,0.0,37.74,4.81,77.11,47.9,15.7
75
+ Mistral-7B-codealpaca-lora,HumanEval,10,0.84,3.63,20.28,9.3,189.53,1.01,1.04,0.0,64.06,1.11,3.5,0.0,36.72,4.79,87.18,46.5,14.6
76
+ OpenCodeInterpreter-DS-1.3B,HumanEval,10,0.81,3.43,11.73,12.5,192.86,1.01,1.04,0.0,64.09,1.09,3.4,0.0,33.8,4.31,47.74,33.3,6.5
77
+ OpenCodeInterpreter-DS-6.7B,HumanEval,10,0.82,3.67,9.31,19.2,188.43,1.02,1.05,0.0,62.89,1.11,3.49,0.0,34.27,4.76,37.83,42.3,10.4
78
+ OpenCodeInterpreter-DS-33B,HumanEval,10,0.89,3.82,19.14,4.3,189.79,1.01,1.05,0.0,64.0,1.09,3.51,0.0,39.06,5.07,89.48,53.2,14.6
79
+ Phind-CodeLlama-34B-v2,HumanEval,10,0.87,3.74,20.28,7.1,187.88,1.01,1.04,0.0,63.6,1.11,3.5,0.0,37.16,4.88,82.44,42.9,13.4
80
+ speechless-starcoder2-15b,HumanEval,10,0.54,2.38,3.05,0.0,271.4,1.38,1.39,0.0,62.3,1.06,1.08,0.0,22.03,3.0,3.84,0.0,1.7
81
+ starcoder2-3b,HumanEval,10,0.65,2.5,4.13,0.0,184.2,1.02,1.05,0.0,63.86,1.06,1.09,0.0,25.63,2.93,4.91,0.0,3.5
82
+ starcoder2-7b,HumanEval,10,0.5,1.94,2.71,0.0,278.33,1.45,1.47,0.0,66.65,1.06,1.08,0.0,20.87,2.31,3.37,0.0,1.6
83
+ WizardCoder-Python-7B-V1.0-GPTQ,HumanEval,10,0.8,3.46,4.58,0.0,190.4,1.02,1.04,0.0,63.75,1.08,1.73,0.0,32.37,4.3,7.11,28.6,10.5
84
+ WizardCoder-Python-13B-V1.0-GPTQ,HumanEval,10,0.65,2.7,4.09,0.0,193.91,1.0,1.02,0.0,62.8,1.09,1.74,0.0,26.59,3.37,8.69,6.7,5.2
85
+ WizardCoder-Python-34B-V1.0-GPTQ,HumanEval,10,0.77,3.29,4.96,0.0,193.13,1.03,1.06,0.0,63.67,1.08,1.73,0.0,32.73,4.29,7.08,30.0,11.2
86
+ XwinCoder-7B,HumanEval,10,0.87,3.74,16.11,18.0,188.72,1.0,1.06,0.0,64.04,1.1,3.5,0.0,38.09,4.95,67.87,46.0,16.4
87
+ XwinCoder-13B,HumanEval,10,0.87,3.75,20.24,10.4,189.03,1.01,1.04,0.0,64.09,1.11,3.49,0.0,37.54,4.89,77.02,47.9,15.3
88
+ XwinCoder-34B,HumanEval,10,0.9,3.89,18.92,14.0,186.87,1.0,1.05,0.0,63.97,1.1,3.51,0.0,39.18,5.1,79.99,54.0,15.7